Author name cluster

Thomas L. Griffiths

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.

12 papers

1 author row

CLeaR Conference 2026 Conference Paper

Understanding Task Representations in Neural Networks via Bayesian Ablation

Andrew Joohun Nam
Declan Iain Campbell
Thomas L. Griffiths
Jonathan D. Cohen
Sarah-Jane Leslie

Neural networks are powerful tools for cognitive modeling due to their flexibility and emergent properties. However, interpreting their learned representations remains challenging due to their sub-symbolic semantics. We introduce a novel probabilistic framework for interpreting latent task representations in neural networks. Inspired by Bayesian inference, our approach defines a distribution over representational units to infer their causal contributions to task performance. Using ideas from information theory, we propose a suite of tools and metrics to illuminate key model properties, including representational distributedness, manifold complexity, and polysemanticity.

PDF Details

TMLR Journal 2025 Journal Article

Getting aligned on representational alignment

Ilia Sucholutsky
Lukas Muttenthaler
Adrian Weller
Andi Peng
Andreea Bobu
Been Kim
Bradley C. Love
Christopher J Cueva

Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the similarity between the representations formed by these diverse systems? Do similarities in representations then translate into similar behavior? If so, then how can a system's representations be modified to better match those of another system? These questions pertaining to the study of \emph{representational alignment} are at the heart of some of the most promising research areas in contemporary cognitive science, neuroscience, and machine learning. In this Perspective, we survey the exciting recent developments in representational alignment research in the fields of cognitive science, neuroscience, and machine learning. Despite their overlapping interests, there is limited knowledge transfer between these fields, so work in one field ends up duplicated in another, and useful innovations are not shared effectively. To improve communication, we propose a unifying framework that can serve as a common language for research on representational alignment, and map several streams of existing work across fields within our framework. We also lay out open problems in representational alignment where progress can benefit all three of these fields. We hope that this paper will catalyze cross-disciplinary collaboration and accelerate progress for all communities studying and developing information processing systems.

PDF Details

TMLR Journal 2025 Journal Article

What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions

Liyi Zhang
Michael Y. Li
R. Thomas McCoy
Theodore Sumers
Jian-Qiao Zhu
Thomas L. Griffiths

Autoregressive language models have demonstrated a remarkable ability to extract latent structure from text. The embeddings from large language models have been shown to capture aspects of the syntax and semantics of language. But what should embeddings represent? We show that the embeddings from autoregressive models correspond to predictive sufficient statistics. By identifying settings where the predictive sufficient statistics are interpretable distributions over latent variables, including exchangeable models and latent state models, we show that embeddings of autoregressive models encode these explainable quantities of interest. We conduct empirical probing studies to extract information from transformers about latent generating distributions. Furthermore, we show that these embeddings generalize to out-of-distribution cases, do not exhibit token memorization, and that the information we identify is more easily recovered than other related measures. Next, we extend our analysis of exchangeable models to more realistic scenarios where the predictive sufficient statistic is difficult to identify by focusing on an interpretable subcomponent of language, topics. We show that large language models encode topic mixtures inferred by latent Dirichlet allocation (LDA) in both synthetic datasets and natural corpora.

PDF Details

NeurIPS Conference 2024 Conference Paper

A Metalearned Neural Circuit for Nonparametric Bayesian Inference

Jake C. Snell
Gianluca M. Bencomo
Thomas L. Griffiths

Most applications of machine learning to classification assume a closed set of balanced classes. This is at odds with the real world, where class occurrence statistics often follow a long-tailed power-law distribution and it is unlikely that all classes are seen in a single sample. Nonparametric Bayesian models naturally capture this phenomenon, but have significant practical barriers to widespread adoption, namely implementation complexity and computational inefficiency. To address this, we present a method for extracting the inductive bias from a nonparametric Bayesian model and transferring it to an artificial neural network. By simulating data with a nonparametric Bayesian prior, we can metalearn a sequence model that performs inference over an unlimited set of classes. After training, this "neural circuit" has distilled the corresponding inductive bias and can successfully perform sequential inference over an open set of classes. Our experimental results show that the metalearned neural circuit achieves comparable or better performance than particle filter-based methods for inference in these models while being faster and simpler to use than methods that explicitly incorporate Bayesian nonparametric inference.

PDF Details DOI

TMLR Journal 2024 Journal Article

Cognitive Architectures for Language Agents

Theodore Sumers
Shunyu Yao
Karthik R Narasimhan
Thomas L. Griffiths

Recent efforts have augmented large language models (LLMs) with external resources (e.g., the Internet) or internal control flows (e.g., prompt chaining) for tasks requiring grounding or reasoning, leading to a new class of language agents. While these agents have achieved substantial empirical success, we lack a framework to organize existing agents and plan future developments. In this paper, we draw on the rich history of cognitive science and symbolic artificial intelligence to propose Cognitive Architectures for Language Agents (CoALA). CoALA describes a language agent with modular memory components, a structured action space to interact with internal memory and external environments, and a generalized decision-making process to choose actions. We use CoALA to retrospectively survey and organize a large body of recent work, and prospectively identify actionable directions towards more capable agents. Taken together, CoALA contextualizes today's language agents within the broader history of AI and outlines a path towards language-based general intelligence.

PDF Details

NeurIPS Conference 2024 Conference Paper

Learning Human-like Representations to Enable Learning Human Values

Andrea H. Wynn
Ilia Sucholutsky
Thomas L. Griffiths

How can we build AI systems that can learn any set of individual human values both quickly and safely, avoiding causing harm or violating societal standards for acceptable behavior during the learning process? We explore the effects of representational alignment between humans and AI agents on learning human values. Making AI systems learn human-like representations of the world has many known benefits, including improving generalization, robustness to domain shifts, and few-shot learning performance. We demonstrate that this kind of representational alignment can also support safely learning and exploring human values in the context of personalization. We begin with a theoretical prediction, show that it applies to learning human morality judgments, then show that our results generalize to ten different aspects of human values -- including ethics, honesty, and fairness -- training AI agents on each set of values in a multi-armed bandit setting, where rewards reflect human value judgments over the chosen action. Using a set of textual action descriptions, we collect value judgments from humans, as well as similarity judgments from both humans and multiple language models, and demonstrate that representational alignment enables both safe exploration and improved generalization when learning human values.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem

Declan Campbell
Sunayana Rane
Tyler Giallanza
Nicolò De Sabbata
Kia Ghods
Amogh Joshi
Alexander Ku
Steven M. Frankland

Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models are able to describe and generate a diverse array of complex, naturalistic images, yet they exhibit surprising failures on basic multi-object reasoning tasks -- such as counting, localization, and simple forms of visual analogy -- that humans perform with near perfect accuracy. To better understand this puzzling pattern of successes and failures, we turn to theoretical accounts of the binding problem in cognitive science and neuroscience, a fundamental problem that arises when a shared set of representational resources must be used to represent distinct entities (e. g. , to represent multiple objects in an image), necessitating the use of serial processing to avoid interference. We find that many of the puzzling failures of state-of-the-art VLMs can be explained as arising due to the binding problem, and that these failure modes are strikingly similar to the limitations exhibited by rapid, feedforward processing in the human brain.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Learning Rewards From Linguistic Feedback

Theodore R. Sumers
Mark K. Ho
Robert D. Hawkins
Karthik Narasimhan
Thomas L. Griffiths

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e. g. , commands). We propose a general framework which does not make this assumption, instead using aspect-based sentiment analysis to decompose feedback into sentiment over the features of a Markov decision process. We then infer the teacher’s reward function by regressing the sentiment on the features, an analogue of inverse reinforcement learning. To evaluate our approach, we first collect a corpus of teaching behavior in a cooperative task where both teacher and learner are human. We implement three artificial learners: sentimentbased “literal” and “pragmatic” models, and an inference network trained end-to-end to predict rewards. We then re-run our initial experiment, pairing human teachers with these artificial learners. All three models successfully learn from interactive human feedback. The inference network approaches the performance of the “literal” sentiment model, while the “pragmatic” model nears human performance. Our work provides insight into the information structure of naturalistic linguistic feedback as well as methods to leverage it for reinforcement learning.

PDF Details

IJCAI Conference 2017 Conference Paper

Adapting Deep Network Features to Capture Psychological Representations: An Abridged Report

Joshua C. Peterson
Joshua T. Abbott
Thomas L. Griffiths

Deep neural networks have become increasingly successful at solving classic perception problems (e. g. , recognizing objects), often reaching or surpassing human-level accuracy. In this abridged report of Peterson et al. [2016], we examine the relationship between the image representations learned by these networks and those of humans. We find that deep features learned in service of object classification account for a significant amount of the variance in human similarity judgments for a set of animal images. However, these features do not appear to capture some key qualitative aspects of human representations. To close this gap, we present a method for adapting deep features to align with human similarity judgments, resulting in image representations that can potentially be used to extend the scope of psychological experiments and inform human-centric AI.

PDF Details

AAMAS Conference 2016 Conference Paper

Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration

Chang Liu
Jessica B. Hamrick
Jaime F. Fisac
Anca D. Dragan
J. Karl Hedrick
S. Shankar Sastry
Thomas L. Griffiths

The study of human-robot interaction is fundamental to the design and use of robotics in real-world applications. Robots will need to predict and adapt to the actions of human collaborators in order to achieve good performance and improve safety and end-user adoption. This paper evaluates a human-robot collaboration scheme that combines the task allocation and motion levels of reasoning: the robotic agent uses Bayesian inference to predict the next goal of its human partner from his or her ongoing motion, and re-plans its own actions in real time. This anticipative adaptation is desirable in many practical scenarios, where humans are unable or unwilling to take on the cognitive overhead required to explicitly communicate their intent to the robot. A behavioral experiment indicates that the combination of goal inference and dynamic task planning significantly improves both objective and perceived performance of the humanrobot team. Participants were highly sensitive to the differences between robot behaviors, preferring to work with a robot that adapted to their actions over one that did not.

PDF

JMLR Journal 2011 Journal Article

Producing Power-Law Distributions and Damping Word Frequencies with Two-Stage Language Models

Sharon Goldwater
Thomas L. Griffiths
Mark Johnson

Standard statistical models of language fail to capture one of the most striking properties of natural languages: the power-law distribution in the frequencies of word tokens. We present a framework for developing statistical models that can generically produce power laws, breaking generative models into two stages. The first stage, the generator, can be any standard probabilistic model, while the second stage, the adaptor, transforms the word frequencies of this model to provide a closer match to natural language. We show that two commonly used Bayesian models, the Dirichlet-multinomial model and the Dirichlet process, can be viewed as special cases of our framework. We discuss two stochastic processes---the Chinese restaurant process and its two-parameter generalization based on the Pitman-Yor process---that can be used as adaptors in our framework to produce power-law distributions over word frequencies. We show that these adaptors justify common estimation procedures based on logarithmic or inverse-power transformations of empirical frequencies. In addition, taking the Pitman-Yor Chinese restaurant process as an adaptor justifies the appearance of type frequencies in formal analyses of natural language and improves the performance of a model for unsupervised learning of morphology. [abs] [ pdf ][ bib ] &copy JMLR 2011. ( edit, beta )

PDF Details

JMLR Journal 2011 Journal Article

The Indian Buffet Process: An Introduction and Review

Thomas L. Griffiths
Zoubin Ghahramani

The Indian buffet process is a stochastic process defining a probability distribution over equivalence classes of sparse binary matrices with a finite number of rows and an unbounded number of columns. This distribution is suitable for use as a prior in probabilistic models that represent objects using a potentially infinite array of features, or that involve bipartite graphs in which the size of at least one class of nodes is unknown. We give a detailed derivation of this distribution, and illustrate its use as a prior in an infinite latent feature model. We then review recent applications of the Indian buffet process in machine learning, discuss its extensions, and summarize its connections to other stochastic processes. [abs] [ pdf ][ bib ] &copy JMLR 2011. ( edit, beta )

PDF Details