Arrow Research search

Author name cluster

Ryan Cotterell

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

23 papers
2 author rows

Possible papers

23

NeurIPS Conference 2025 Conference Paper

Are Language Models Efficient Reasoners? A Perspective from Logic Programming

  • Andreas Opedal
  • Yanick Zengaffinen
  • Haruki Shirakami
  • Clemente Pasti
  • Mrinmaya Sachan
  • Abulhair Saparov
  • Ryan Cotterell
  • Bernhard Schölkopf

Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of reasoning: efficiency. In real-world reasoning scenarios, much of the available information is irrelevant, and effective deductive inference requires identifying and ignoring such distractions. We propose a framework for assessing LM reasoning efficiency through the lens of logic programming, introducing a simple method to align proofs written in natural language---as generated by an LM---with shortest proofs found by executing the logic program. Efficiency is quantified by measuring how well a model avoids unnecessary inference. Empirically, we construct a dataset of math word problems injected with various number of irrelevant axioms that vary in semantic overlap with the goal theorem. We find that current LMs show marked accuracy declines under such conditions---even with minimal, domain-consistent distractions---and the proofs they generate frequently exhibit detours through irrelevant inferences.

PDF Details

NeurIPS Conference 2025 Conference Paper

Better Estimation of the Kullback--Leibler Divergence Between Language Models

  • Afra Amini
  • Tim Vieira
  • Ryan Cotterell

Estimating the Kullback--Leibler (KL) divergence between language models has many applications, e. g. , reinforcement learning from human feedback (RLHF), interpretability, and knowledge distillation. However, computing the exact KL divergence between two arbitrary language models is intractable. Thus, practitioners often resort to sampling-based estimators. While it is easy to fashion a simple Monte Carlo (MC) estimator that provides an unbiased estimate of the KL divergence between language models, this estimator notoriously suffers from high variance and can even result in a negative estimate of the KL divergence, a non-negative quantity. In this paper, we introduce a Rao--Blackwellized estimator that is unbiased and provably has variance less than or equal to that of the standard Monte Carlo estimator. In an empirical study on sentiment-controlled fine-tuning, we show that our estimator provides more stable KL estimates and reduces variance substantially. Additionally, we derive an analogous Rao--Blackwellized estimator of the gradient of the KL divergence, which leads to more stable training and produces models that more frequently appear on the Pareto frontier of reward vs. KL compared to the ones trained with the MC estimator of the gradient.

PDF Details

NeurIPS Conference 2025 Conference Paper

Characterizing the Expressivity of Fixed-Precision Transformer Language Models

  • Jiaoda Li
  • Ryan Cotterell

Transformer-based language models (LMs) have achieved widespread empirical success, but their theoretical expressive power remains only partially understood. In this work, we analyze a restricted idealization of fixed-precision transformers with strict future masking, soft attention, and no positional encodings. We establish that this class of models is exactly as expressive as a specific fragment of linear temporal logic that contains only a single temporal operator: the $\texttt{past}$ operator. We further connect this fragment to established classes in formal language theory, automata theory, and algebra, yielding a unified framework for understanding transformer expressivity under this idealization. Finally, we present empirical results that align closely with our theory: transformers trained on languages within their characterized expressive capacity generalize reliably across sequence lengths, while they consistently fail to generalize on languages beyond it.

PDF Details

ICLR Conference 2025 Conference Paper

Controllable Context Sensitivity and the Knob Behind It

  • Julian Minder
  • Kevin Du
  • Niklas Stoehr
  • Giovanni Monea
  • Chris Wendler
  • Robert West 0001
  • Ryan Cotterell

When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamental functionality, as it enables the model to excel at tasks like retrieval-augmented generation and question-answering. In this paper, we search for a knob which controls this sensitivity, determining whether language models answer from the context or their prior knowledge. To guide this search, we design a task for controllable context sensitivity. In this task, we first feed the model a context ("Paris is in England") and a question ("Where is Paris?"); we then instruct the model to either use its prior or contextual knowledge and evaluate whether it generates the correct answer for both intents (either "France" or "England"). When fine-tuned on this task, instruct versions of Llama-3.1, Mistral-v0.3, and Gemma-2 can solve it with high accuracy (85-95%). Analyzing these high-performing models, we narrow down which layers may be important to context sensitivity using a novel linear time algorithm. Then, in each model, we identify a 1-D subspace in a single layer that encodes whether the model follows context or prior knowledge. Interestingly, while we identify this subspace in a fine-tuned model, we find that the exact same subspace serves as an effective knob in not only that model but also non-fine-tuned instruct and base models of that model family. Finally, we show a strong correlation between a model's performance and how distinctly it separates context-agreeing from context-ignoring answers in this subspace. These results suggest a single fundamental subspace facilitates how the model chooses between context and prior knowledge.

Details

ICML Conference 2025 Conference Paper

From Language Models over Tokens to Language Models over Characters

  • Tim Vieira
  • Benjamin LeBrun
  • Mario Giulianelli
  • Juan Luis Gastaldi
  • Brian DuSell
  • John Terilla
  • Timothy J. O'Donnell
  • Ryan Cotterell

Modern language models are internally—and mathematically—distributions over token strings rather than character strings, posing numerous challenges for programmers building user applications on top of them. For example, if a prompt is specified as a character string, it must be tokenized before passing it to the token-level language model. Thus, the tokenizer and consequent processing are very sensitive to the specification of the prompt (e. g. , whether the prompt ends with a space or not). This paper presents algorithms for converting token-level language models to character-level ones. We present both exact and approximate algorithms. In the empirical portion of the paper, we benchmark the practical runtime and approximation quality. Across four publicly available language models, we find that—even with a small computation budget—our method is able to accurately approximate the character-level distribution at reasonably fast speeds, and that a significant improvement in the language model’s compression rate (bits/byte) is achieved.

Details

ICLR Conference 2025 Conference Paper

Gumbel Counterfactual Generation From Language Models

  • Shauli Ravfogel
  • Anej Svete
  • Vésteinn Snæbjarnarson
  • Ryan Cotterell

Understanding and manipulating the causal generation mechanisms in language models is essential for controlling their behavior. Previous work has primarily relied on techniques such as representation surgery---e.g., model ablations or manipulation of linear subspaces tied to specific concepts---to intervene on these models. To understand the impact of interventions precisely, it is useful to examine counterfactuals---e.g., how a given sentence would have appeared had it been generated by the model following a specific intervention. We highlight that counterfactual reasoning is conceptually distinct from interventions, as articulated in Pearl's causal hierarchy. Based on this observation, we propose a framework for generating true string counterfactuals by reformulating language models as a structural equation model using the Gumbel-max trick, which we called Gumbel counterfactual generation. This reformulation allows us to model the joint distribution over original strings and their counterfactuals resulting from the same instantiation of the sampling noise. We develop an algorithm based on hindsight Gumbel sampling that allows us to infer the latent noise variables and generate counterfactuals of observed strings. Our experiments demonstrate that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.

Details

ICML Conference 2025 Conference Paper

Language Models over Canonical Byte-Pair Encodings

  • Tim Vieira
  • Tianyu Liu 0004
  • Clemente Pasti
  • Yahya Emara
  • Brian DuSell
  • Benjamin LeBrun
  • Mario Giulianelli
  • Juan Luis Gastaldi

Modern language models represent probability distributions over character strings as distributions over (shorter) token strings derived via a deterministic tokenizer, such as byte-pair encoding. While this approach is highly effective at scaling up language models to large corpora, its current incarnations have a concerning property: the model assigns nonzero probability mass to an exponential number of noncanonical token encodings of each character string—these are token strings that decode to valid character strings but are impossible under the deterministic tokenizer (i. e. , they will never be seen in any training corpus, no matter how large). This misallocation is both erroneous, as noncanonical strings never appear in training data, and wasteful, diverting probability mass away from plausible outputs. These are avoidable mistakes! In this work, we propose methods to enforce canonicality in token-level language models, ensuring that only canonical token strings are assigned positive probability. We present two approaches: (1) canonicality by conditioning, leveraging test-time inference strategies without additional training, and (2) canonicality by construction, a model parameterization that guarantees canonical outputs but requires training. We demonstrate that fixing canonicality mistakes improves the likelihood of held-out data for several models and corpora.

Details

TMLR Journal 2025 Journal Article

On the Challenges and Opportunities in Generative AI

  • Laura Manduchi
  • Clara Meister
  • Kushagra Pandey
  • Robert Bamler
  • Ryan Cotterell
  • Sina Däubener
  • Sophie Fellenz
  • Asja Fischer

The field of deep generative modeling has grown rapidly in the last few years. With the availability of massive amounts of training data coupled with advances in scalable unsupervised learning paradigms, recent large-scale generative models show tremendous promise in synthesizing high-resolution images and text, as well as structured data such as videos and molecules. However, we argue that current large-scale generative AI models exhibit several fundamental shortcomings that hinder their widespread adoption across domains. In this work, our objective is to identify these issues and highlight key unresolved challenges in modern generative AI paradigms that should be addressed to further enhance their capabilities, versatility, and reliability. By identifying these challenges, we aim to provide researchers with insights for exploring fruitful research directions, thus fostering the development of more robust and accessible generative AI solutions.

PDF Details

ICLR Conference 2025 Conference Paper

Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo

  • João Loula
  • Benjamin LeBrun
  • Li Du
  • Ben Lipkin
  • Clemente Pasti
  • Gabriel Grand
  • Tianyu Liu 0004
  • Yahya Emara

A wide range of LM applications require generating text that conforms to syntactic or semantic constraints. Imposing such constraints can be naturally framed as _probabilistic conditioning_, but exact generation from the resulting distribution—which can differ substantially from the LM’s base distribution—is generally intractable. In this work, we develop an architecture for controlled LM generation based on sequential Monte Carlo (SMC). Our SMC framework allows us to flexibly incorporate domain- and problem-specific constraints at inference time, and efficiently reallocate computational resources in light of new information during the course of generation. By comparing to a number of alternatives and ablations on four challenging domains---Python code generation for data science, text-to-SQL, goal inference, and molecule synthesis—we demonstrate that, with little overhead, our approach allows small open-source language models to outperform models over 8$\times$ larger, as well as closed-source, fine-tuned ones. In support of the probabilistic perspective, we show that these performance improvements are driven by better approximation to the posterior distribution. [Our system](https://github.com/probcomp/genlm-control) builds on the framework of Lew et al. (2023) and integrates with its _language model probabilistic programming language_, giving users a simple, programmable way to apply SMC to a broad variety of controlled generation problems.

Details

ICLR Conference 2025 Conference Paper

The Foundations of Tokenization: Statistical and Computational Concerns

  • Juan Luis Gastaldi
  • John Terilla
  • Luca Malagutti
  • Brian DuSell
  • Tim Vieira
  • Ryan Cotterell

Tokenization — the practice of converting strings of characters from an alphabet into sequences of tokens over a vocabulary — is a critical step in the NLP pipeline. The use of token representations is widely credited with increased model performance but is also the source of many undesirable behaviors, such as spurious ambiguity or inconsistency. Despite its recognized importance as a standard representation method in NLP, the theoretical underpinnings of tokenization are not yet fully understood. In particular, the impact of tokenization on language model estimation has been investigated primarily through empirical means. The present paper contributes to addressing this theoretical gap by proposing a unified formal framework for representing and analyzing tokenizer models. Based on the category of stochastic maps, this framework enables us to establish general conditions for a principled use of tokenizers and, most importantly, the necessary and sufficient conditions for a tokenizer model to preserve the consistency of statistical estimators. In addition, we discuss statistical and computational concerns crucial for designing and implementing tokenizer models, such as inconsistency, ambiguity, finiteness, and sequentiality. The framework and results advanced in this paper contribute to building robust theoretical foundations for representations in neural language modeling that can inform future theoretical and empirical research.

Details

ICLR Conference 2025 Conference Paper

Training Neural Networks as Recognizers of Formal Languages

  • Alexandra Butoi
  • Ghazal Khalighinejad
  • Anej Svete
  • Josef Valvoda
  • Ryan Cotterell
  • Brian DuSell

Characterizing the computational power of neural network architectures in terms of formal language theory remains a crucial line of research, as it describes lower and upper bounds on the reasoning capabilities of modern AI. However, when empirically testing these bounds, existing work often leaves a discrepancy between experiments and the formal claims they are meant to support. The problem is that formal language theory pertains specifically to recognizers: machines that receive a string as input and classify whether it belongs to a language. On the other hand, it is common instead to evaluate language models on proxy tasks, e.g., language modeling or sequence-to-sequence transduction, that are similar in only an informal sense to the underlying theory. We correct this mismatch by training and evaluating neural networks directly as binary classifiers of strings, using a general method that can be applied to a wide variety of languages. As part of this, we extend an algorithm recently proposed by Snæbjarnarson et al. (2025) for efficient length-controlled sampling of strings from regular languages. We provide results on a variety of languages across the Chomsky hierarchy for three neural architectures: a simple RNN, an LSTM, and a causally-masked transformer. We find that the RNN and LSTM often outperform the transformer, and that auxiliary training objectives such as language modeling can help, although no single objective uniformly improves performance across languages and architectures. Our contributions will facilitate theoretically sound empirical testing of language recognition claims in future work. We have released our datasets as a benchmark called FLaRe (Formal Language Recognition), along with our code.

Details

ICLR Conference 2025 Conference Paper

Variational Best-of-N Alignment

  • Afra Amini
  • Tim Vieira
  • Elliott Ash
  • Ryan Cotterell

Best-of-N (BoN) is a popular and effective algorithm for aligning language models to human preferences. The algorithm works as follows: at inference time, N samples are drawn from the language model, and the sample with the highest reward, as judged by a reward model, is returned as the output. Despite its effectiveness, BoN is computationally expensive; it reduces sampling throughput by a factor of N. To make BoN more efficient at inference time, one strategy is to fine-tune the language model to mimic what BoN does during inference. To achieve this, we derive the distribution induced by the BoN algorithm. We then propose to fine-tune the language model to minimize backward KL divergence to the BoN distribution. Our approach is analogous to mean-field variational inference and, thus, we term it variational BoN (vBoN). To the extent this fine-tuning is successful and we end up with a good approximation, we have reduced the inference cost by a factor of N. Our experiments on controlled generation and summarization tasks show that BoN is the most effective alignment method, and our variational approximation to BoN achieves the closest performance to BoN and surpasses models fine-tuned using the standard KL-constrained RL objective. In the controlled generation task, vBoN appears more frequently on the Pareto frontier of reward and KL divergence compared to other alignment methods. In the summarization task, vBoN achieves high reward values across various sampling temperatures.

Details

ICML Conference 2024 Conference Paper

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

  • Andreas Opedal
  • Alessandro Stolfo
  • Haruki Shirakami
  • Ying Jiao
  • Ryan Cotterell
  • Bernhard Schölkopf
  • Abulhair Saparov
  • Mrinmaya Sachan

There is increasing interest in employing large language models (LLMs) as cognitive models. For such purposes, it is central to understand which properties of human cognition are well-modeled by LLMs, and which are not. In this work, we study the biases of LLMs in relation to those known in children when solving arithmetic word problems. Surveying the learning science literature, we posit that the problem-solving process can be split into three distinct steps: text comprehension, solution planning and solution execution. We construct tests for each one in order to understand whether current LLMs display the same cognitive biases as children in these steps. We generate a novel set of word problems for each of these tests, using a neuro-symbolic approach that enables fine-grained control over the problem features. We find evidence that LLMs, with and without instruction-tuning, exhibit human-like biases in both the text-comprehension and the solution-planning steps of the solving process, but not in the final step, in which the arithmetic expressions are executed to obtain the answer.

Details

IROS Conference 2024 Conference Paper

NARRATE: Versatile Language Architecture for Optimal Control in Robotics

  • Seif Ismail
  • Antonio Arbues
  • Ryan Cotterell
  • René Zurbrügg
  • Carmen Amo Alonso

The impressive capabilities of Large Language Models (LLMs) have led to various efforts in enabling robots to be controlled through natural language instructions, opening exciting possibilities for human-robot interaction. The goal is for the motor-control task to be performed accurately, efficiently and safely while also enjoying the flexibility imparted by LLMs to specify and adjust the task through natural language. In this work, we demonstrate how a careful layering of an LLM in combination with a Model Predictive Control (MPC) formulation allows for accurate and flexible robotic control via natural language while taking into consideration safety constraints. In particular, we rely on the LLM to effectively frame constraints and objective functions as mathematical expressions, which are later used in the motor-control module via MPC. The transparency of the optimization formulation allows for interpretability of the task and enables adjustments through human feedback. We demonstrate the validity of our method through extensive experiments on long-horizon reasoning, contact-rich, and multi-object interaction tasks. Our evaluations show that NARRATE outperforms current existing methods on these benchmarks and effectively transfers to the real world on two different embodiments. Videos, Code and Prompts at narrate-mpc.github.io

Details

NeurIPS Conference 2024 Conference Paper

On Affine Homotopy between Language Encoders

  • Robin S. Chan
  • Reda Boumasmoud
  • Anej Svete
  • Yuxin Ren
  • Qipeng Guo
  • Zhijing Jin
  • Shauli Ravfogel
  • Mrinmaya Sachan

Pre-trained language encoders---functions that represent text as vectors---are an integral component of many NLP tasks. We tackle a natural question in language encoder analysis: What does it mean for two encoders to be similar? We contend that a faithful measure of similarity needs to be \emph{intrinsic}, that is, task-independent, yet still be informative of \emph{extrinsic} similarity---the performance on downstream tasks. It is common to consider two encoders similar if they are \emph{homotopic}, i. e. , if they can be aligned through some transformation. In this spirit, we study the properties of \emph{affine} alignment of language encoders and its implications on extrinsic similarity. We find that while affine alignment is fundamentally an asymmetric notion of similarity, it is still informative of extrinsic similarity. We confirm this on datasets of natural language representations. Beyond providing useful bounds on extrinsic similarity, affine intrinsic similarity also allows us to begin uncovering the structure of the space of pre-trained encoders by defining an order over them.

PDF Details DOI

ICML Conference 2024 Conference Paper

Principled Gradient-Based MCMC for Conditional Sampling of Text

  • Li Du
  • Afra Amini
  • Lucas Torroba Hennigen
  • Xinyan Velocity Yu
  • Holden Lee
  • Jason Eisner
  • Ryan Cotterell

We consider the problem of sampling text from an energy-based model. This arises, for example, when sampling text from a neural language model subject to soft constraints. Although the target distribution is discrete, the internal computations of the energy function (given by the language model) are differentiable, so one would like to exploit gradient information within a method such as MCMC. Alas, all previous attempts to generalize gradient-based MCMC to text sampling fail to sample correctly from the target distribution. We propose a solution, along with variants, and study its theoretical properties. Through experiments on various forms of text generation, we demonstrate that our unbiased samplers are able to generate more fluent text while better adhering to the control objectives. The same methods could be used to sample from discrete energy-based models unrelated to text.

Details

ICML Conference 2024 Conference Paper

Representation Surgery: Theory and Practice of Affine Steering

  • Shashwat Singh 0001
  • Shauli Ravfogel
  • Jonathan Herzig
  • Roee Aharoni
  • Ryan Cotterell
  • Ponnurangam Kumaraguru

Language models often exhibit undesirable behavior, e. g. , generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model’s representations. Thus, one natural (and common) approach to prevent the model from exhibiting undesirable behavior is to steer the model’s representations in a manner that reduces the probability of it generating undesirable text. This paper investigates the formal and empirical properties of steering functions, i. e. , transformation of the neural language model’s representations that alter its behavior. First, we derive two optimal, in the least-squares sense, affine steering functions under different constraints. Our theory provides justification for existing approaches and offers a novel, improved steering approach. Second, we offer a series of experiments that demonstrate the empirical effectiveness of the methods in mitigating bias and reducing toxic generation.

Details

AAAI Conference 2023 Conference Paper

A Latent-Variable Model for Intrinsic Probing

  • Karolina Stańczak
  • Lucas Torroba Hennigen
  • Adina Williams
  • Ryan Cotterell
  • Isabelle Augenstein

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of linguistic knowledge as they have brought about large empirical improvements on a wide variety of NLP tasks, which suggests they are learning true linguistic generalization. In this work, we focus on intrinsic probing, an analysis technique where the goal is not only to identify whether a representation encodes a linguistic attribute but also to pinpoint where this attribute is encoded. We propose a novel latent-variable formulation for constructing intrinsic probes and derive a tractable variational approximation to the log-likelihood. Our results show that our model is versatile and yields tighter mutual information estimates than two intrinsic probes previously proposed in the literature. Finally, we find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.

PDF Details DOI

ICML Conference 2023 Conference Paper

Controlled Text Generation with Natural Language Instructions

  • Wangchunshu Zhou
  • Yuchen Eleanor Jiang
  • Ethan Wilcox
  • Ryan Cotterell
  • Mrinmaya Sachan

Large language models can be prompted to pro- duce fluent output for a wide range of tasks without being specifically trained to do so. Nevertheless, it is notoriously difficult to control their generation in such a way that it satisfies user-specified constraints. In this paper, we present InstructCTG, a simple controlled text generation framework that incorporates different constraints by verbalizing them as natural language instructions. We annotate natural texts through a combination of off-the-shelf NLP tools and simple heuristics with the linguistic and extra-linguistic constraints they satisfy. Then, we verbalize the constraints into natural language instructions to form weakly supervised training data, i. e. , we prepend the natural language verbalizations of the constraints in front of their corresponding natural language sentences. Next, we fine-tune a pre-trained language model on the augmented corpus. Compared to existing methods, InstructCTG is more flexible in terms of the types of constraints it allows the practitioner to use. It also does not require any modification of the decoding procedure. Finally, InstructCTG allows the model to adapt to new constraints without re-training through the use of in-context learning.

Details

NeurIPS Conference 2023 Conference Paper

LEACE: Perfect linear concept erasure in closed form

  • Nora Belrose
  • David Schneider-Joseph
  • Shauli Ravfogel
  • Ryan Cotterell
  • Edward Raff
  • Stella Biderman

Concept erasure aims to remove specified features from a representation. It can improve fairness (e. g. preventing a classifier from using gender or race) and interpretability (e. g. removing a concept to observe changes in model behavior). We introduce LEAst-squares Concept Erasure (LEACE), a closed-form method which provably prevents all linear classifiers from detecting a concept while changing the representation as little as possible, as measured by a broad class of norms. We apply LEACE to large language models with a novel procedure called concept scrubbing, which erases target concept information from every layer in the network. We demonstrate our method on two tasks: measuring the reliance of language models on part-of-speech information, and reducing gender bias in BERT embeddings. Our code is available at https: //github. com/EleutherAI/concept-erasure.

PDF Details

ICLR Conference 2023 Conference Paper

On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation

  • Tiago Pimentel
  • Clara Meister
  • Ryan Cotterell

A good automatic evaluation metric for language generation ideally correlates highly with human judgements of text quality. Yet, there is a dearth of such metrics, which inhibits the rapid and efficient progress of language generators. One exception is the recently proposed Mauve. In theory, Mauve measures an information-theoretic divergence between two probability distributions over strings: one representing the language generator under evaluation; the other representing the true natural language distribution. Mauve's authors argue that its success comes from the qualitative properties of their proposed divergence. Yet in practice, as this divergence is uncomputable, Mauve approximates it by measuring the divergence between multinomial distributions over clusters instead, where cluster assignments are attained by grouping strings based on a pretrained language model's embeddings. As we show, however, this is not a tight approximation---in either theory or practice. This begs the question: why does Mauve work so well? In this work, we show that \mauve was right for the wrong reasons, and that its newly proposed divergence is not necessary for its high performance. In fact, classical divergences paired with its proposed cluster-based approximation may actually serve as better evaluation metrics. We finish the paper with a probing analysis; this analysis leads us to conclude that---by encoding syntactic- and coherence-level features of text, while ignoring surface-level features---such cluster-based approximations to string distributions may simply be better for evaluating state-of-the-art language generators.

Details

NeurIPS Conference 2023 Conference Paper

Structured Voronoi Sampling

  • Afra Amini
  • Li Du
  • Ryan Cotterell

Gradient-based sampling algorithms have demonstrated their effectiveness in text generation, especially in the context of controlled text generation. However, there exists a lack of theoretically grounded and principled approaches for this task. In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods. We use discrete distributions given by language models to define densities and develop an algorithm based on Hamiltonian Monte Carlo to sample from them. We name our gradient-based technique Structured Voronoi Sampling (SVS). In an experimental setup where the reference distribution is known, we show that the empirical distribution of SVS samples is closer to the reference distribution compared to alternative sampling schemes. Furthermore, in a controlled generation task, SVS is able to generate fluent and diverse samples while following the control targets significantly better than other methods.

PDF Details

ICML Conference 2022 Conference Paper

Linear Adversarial Concept Erasure

  • Shauli Ravfogel
  • Michael Twiton
  • Yoav Goldberg
  • Ryan Cotterell

Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to control their content becomes an increasingly important problem. In this work, we formulate the problem of identifying a linear subspace that corresponds to a given concept, and removing it from the representation. We formulate this problem as a constrained, linear minimax game, and show that existing solutions are generally not optimal for this task. We derive a closed-form solution for certain objectives, and propose a convex relaxation that works well for others. When evaluated in the context of binary gender removal, the method recovers a low-dimensional subspace whose removal mitigates bias by intrinsic and extrinsic evaluation. Surprisingly, we show that the method—despite being linear—is highly expressive, effectively mitigating bias in the output layers of deep, nonlinear classifiers while maintaining tractability and interpretability.

Details
v2026.09.13