Author name cluster

Cyrus Rashtchian

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

2 author rows

NeurIPS Conference 2025 Conference Paper

A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning

Guan Zhe Hong
Nishanth Dikkala
Enming Luo
Cyrus Rashtchian
Xin Wang
Rina Panigrahy

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a specific problem localized to certain parts of the network? Do they break down the reasoning problem into modular components that are then executed as sequential steps as we go deeper in the model? To better understand the reasoning capability of LLMs, we study a minimal propositional logic problem that requires combining multiple facts to arrive at a solution. By studying this problem on Mistral and Gemma models, up to 27B parameters, we illuminate the core components the models use to solve such logic problems. From a mechanistic interpretability point of view, we use causal mediation analysis to uncover the pathways and components of the LLMs' reasoning processes. Then, we offer fine-grained insights into the functions of attention heads in different layers. We not only find a sparse circuit that computes the answer, but we decompose it into sub-circuits that have four distinct and modular uses. Finally, we reveal that three distinct models -- Mistral-7B, Gemma-2-9B and Gemma-2-27B -- contain analogous but not identical mechanisms.

PDF Details

ICLR Conference 2025 Conference Paper

Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating

Olivia Wiles
Chuhan Zhang
Isabela Albuquerque
Ivana Kajic
Su Wang 0001
Emanuele Bugliarello
Yasumasa Onoe
Pinelopi Papalampidi

While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While many metrics and benchmarks have been proposed to evaluate T2I models and alignment metrics, the impact of the evaluation components (prompt sets, human annotations, evaluation task) has not been systematically measured. We find that looking at only *one slice of data*, i.e. one set of capabilities or human annotations, is not enough to obtain stable conclusions that generalise to new conditions or slices when evaluating T2I models or alignment metrics. We address this by introducing an evaluation suite of $>$100K annotations across four human annotation templates that comprehensively evaluates models' capabilities across a range of methods for gathering human annotations and comparing models. In particular, we propose (1) a carefully curated set of prompts -- *Gecko2K*; (2) a statistically grounded method of comparing T2I models; and (3) how to systematically evaluate metrics under three *evaluation tasks* -- *model ordering, pair-wise instance scoring, point-wise instance scoring*. Using this evaluation suite, we evaluate a wide range of metrics and find that a metric may do better in one setting but worse in another. As a result, we introduce a new, interpretable auto-eval metric that is consistently better correlated with human ratings than such existing metrics on our evaluation suite--across different human templates and evaluation settings--and on TIFA160.

Details

ICLR Conference 2025 Conference Paper

Sufficient Context: A New Lens on Retrieval Augmented Generation Systems

Hailey Joren
Jianyi Zhang
Chun-Sung Ferng
Da-Cheng Juan
Ankur Taly
Cyrus Rashtchian

Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whether errors arise because LLMs fail to utilize the context from retrieval or the context itself is insufficient to answer the query. To shed light on this, we develop a new notion of sufficient context, along with a method to classify instances that have enough information to answer the query. We then use sufficient context to analyze several models and datasets. By stratifying errors based on context sufficiency, we find that larger models with higher baseline performance (Gemini 1.5 Pro, GPT 4o, Claude 3.5) excel at answering queries when the context is sufficient, but often output incorrect answers instead of abstaining when the context is not. On the other hand, smaller models with lower baseline performance (Llama 3.1, Mistral 3, Gemma 2) hallucinate or abstain often, even with sufficient context. We further categorize cases when the context is useful, and improves accuracy, even though it does not fully answer the query and the model errs without the context. Building on our findings, we explore ways to reduce hallucinations in RAG systems, including a new selective generation method that leverages sufficient context information for guided abstention. Our method improves the fraction of correct answers among times where the model responds by 2--10% for Gemini, GPT, and Gemma. Code for our selective generation method and the prompts used in our autorater analysis are available on our [github](https://github.com/hljoren/sufficientcontext).

Details

NeurIPS Conference 2024 Conference Paper

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models

Jianyi Zhang
Da-Cheng Juan
Cyrus Rashtchian
Chun-Sung Ferng
Heinrich Jiang
Yiran Chen

Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Logits Evolution Decoding (SLED), a novel decoding framework that enhances the truthfulness of LLMs without relying on external knowledge bases or requiring further fine-tuning. From an optimization perspective, our SLED framework leverages the latent knowledge embedded within the LLM by contrasting the output logits from the final layer with those from early layers. It then utilizes an approximate gradient approach to enable latent knowledge to guide the self-refinement of outputs, thereby effectively improving factual accuracy. Extensive experiments have been conducted on established benchmarks across a diverse range of model families (LLaMA 2, LLaMA 3, Gemma) and scales (from 2B to 70B), including more advanced architectural configurations such as the mixture of experts (MoE). Our evaluation spans a wide variety of tasks, including multi-choice, open-generation, and adaptations to chain-of-thought reasoning tasks. The results demonstrate that SLED consistently improves factual accuracy by up to 20\% compared to existing decoding methods while maintaining natural language fluency and negligible latency overhead. Furthermore, it can be flexibly combined with other decoding methods to further enhance their performance.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Benchmarking Robustness to Adversarial Image Obfuscations

Florian Stimberg
Ayan Chakrabarti
Chun-Ta Lu
Hussein Hazimeh
Otilia Stretcu
Wei Qiao
Yintao Liu
Merve Kaya

Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfortunately, resourceful actors try to bypass automated filters in a bid to post content that violate platform policies and codes of conduct. To reach this goal, these malicious actors may obfuscate policy violating images (e. g. , overlay harmful images by carefully selected benign images or visual patterns) to prevent machine learning models from reaching the correct decision. In this paper, we invite researchers to tackle this specific issue and present a new image benchmark. This benchmark, based on ImageNet, simulates the type of obfuscations created by malicious actors. It goes beyond Image-Net-C and ImageNet-C-bar by proposing general, drastic, adversarial modifications that preserve the original content intent. It aims to tackle a more common adversarial threat than the one considered by lp-norm bounded adversaries. We evaluate 33 pretrained models on the benchmark and train models with different augmentations, architectures and training methods on subsets of the obfuscations to measure generalization. Our hope is that this benchmark will encourage researchers to test their models and methods and try to find new approaches that are more robust to these obfuscations.

PDF Details

TMLR Journal 2023 Journal Article

Probing Predictions on OOD Images via Nearest Categories

Yao-Yuan Yang
Cyrus Rashtchian
Ruslan Salakhutdinov
Kamalika Chaudhuri

We study out-of-distribution (OOD) prediction behavior of neural networks when they classify images from unseen classes or corrupted images. To probe the OOD behavior, we introduce a new measure, nearest category generalization (NCG), where we compute the fraction of OOD inputs that are classified with the same label as their nearest neighbor in the training set. Our motivation stems from understanding the prediction patterns of adversarially robust networks, since previous work has identified unexpected consequences of training to be robust to norm-bounded perturbations. We find that robust networks have consistently higher NCG accuracy than natural training, even when the OOD data is much farther away than the robustness radius. This implies that the local regularization of robust training has a significant impact on the network’s decision regions. We replicate our findings using many datasets, comparing new and existing training methods. Overall, adversarially robust networks resemble a nearest neighbor classifier when it comes to OOD data.

PDF Details

NeurIPS Conference 2022 Conference Paper

A Theoretical View on Sparsely Activated Networks

Cenk Baykal
Nishanth Dikkala
Rina Panigrahy
Cyrus Rashtchian
Xin Wang

Deep and wide neural networks successfully fit very complex functions today, but dense models are starting to be prohibitively expensive for inference. To mitigate this, one promising research direction is networks that activate a sparse subgraph of the network. The subgraph is chosen by a data-dependent routing function, enforcing a fixed mapping of inputs to subnetworks (e. g. , the Mixture of Experts (MoE) paradigm in Switch Transformers). However, there is no theoretical grounding for these sparsely activated models. As our first contribution, we present a formal model of data-dependent sparse networks that captures salient aspects of popular architectures. Then, we show how to construct sparse networks that provably match the approximation power and total size of dense networks on Lipschitz functions. The sparse networks use much fewer inference operations than dense networks, leading to a faster forward pass. The key idea is to use locality sensitive hashing on the input vectors and then interpolate the function in subregions of the input space. This offers a theoretical insight into why sparse networks work well in practice. Finally, we present empirical findings that support our theory; compared to dense networks, sparse networks give a favorable trade-off between number of active units and approximation quality.

PDF Details

NeurIPS Conference 2020 Conference Paper

A Closer Look at Accuracy vs. Robustness

Yao-Yuan Yang
Cyrus Rashtchian
Hongyang Zhang
Russ R. Salakhutdinov
Kamalika Chaudhuri

Current methods for training robust networks lead to a drop in test accuracy, which has led prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning. We take a closer look at this phenomenon and first show that real image datasets are actually separated. With this property in mind, we then prove that robustness and accuracy should both be achievable for benchmark datasets through locally Lipschitz functions, and hence, there should be no inherent tradeoff between robustness and accuracy. Through extensive experiments with robustness methods, we argue that the gap between theory and practice arises from two limitations of current methods: either they fail to impose local Lipschitzness or they are insufficiently generalized. We explore combining dropout with robust training methods and obtain better generalization. We conclude that achieving robustness and accuracy in practice may require using methods that impose local Lipschitzness and augmenting them with deep learning generalization techniques.

PDF Details

ICML Conference 2020 Conference Paper

Explainable k-Means and k-Medians Clustering

Michal Moshkovitz
Sanjoy Dasgupta
Cyrus Rashtchian
Nave Frost

Many clustering algorithms lead to cluster assignments that are hard to explain, partially because they depend on all the features of the data in a complicated way. To improve interpretability, we consider using a small decision tree to partition a data set into clusters, so that clusters can be characterized in a straightforward manner. We study this problem from a theoretical viewpoint, measuring cluster quality by the k-means and k-medians objectives. In terms of negative results, we show that popular top-down decision tree algorithms may lead to clusterings with arbitrarily large cost, and any clustering based on a tree with k leaves must incur an Omega(log k) approximation factor compared to the optimal clustering. On the positive side, for two means/medians, we show that a single threshold cut can achieve a constant factor approximation, and we give nearly-matching lower bounds; for general k > 2, we design an efficient algorithm that leads to an O(k) approximation to the optimal k-medians and an O(k^2) approximation to the optimal k-means. Prior to our work, no algorithms were known with provable guarantees independent of dimension and input size.

Details

NeurIPS Conference 2017 Conference Paper

Clustering Billions of Reads for DNA Data Storage

Cyrus Rashtchian
Konstantin Makarychev
Miklos Racz
Siena Ang
Djordje Jevdjic
Sergey Yekhanin
Luis Ceze
Karin Strauss

Storing data in synthetic DNA offers the possibility of improving information density and durability by several orders of magnitude compared to current storage technologies. However, DNA data storage requires a computationally intensive process to retrieve the data. In particular, a crucial step in the data retrieval pipeline involves clustering billions of strings with respect to edit distance. Datasets in this domain have many notable properties, such as containing a very large number of small clusters that are well-separated in the edit distance metric space. In this regime, existing algorithms are unsuitable because of either their long running time or low accuracy. To address this issue, we present a novel distributed algorithm for approximately computing the underlying clusters. Our algorithm converges efficiently on any dataset that satisfies certain separability properties, such as those coming from DNA data storage systems. We also prove that, under these assumptions, our algorithm is robust to outliers and high levels of noise. We provide empirical justification of the accuracy, scalability, and convergence of our algorithm on real and synthetic data. Compared to the state-of-the-art algorithm for clustering DNA sequences, our algorithm simultaneously achieves higher accuracy and a 1000x speedup on three real datasets.

PDF Details

SODA Conference 2017 Conference Paper

Massively-Parallel Similarity Join, Edge-Isoperimetry, and Distance Correlations on the Hypercube

Paul Beame
Cyrus Rashtchian

We study distributed protocols for finding all pairs of similar vectors in a large dataset. Our results pertain to a variety of discrete metrics, and we give concrete instantiations for Hamming distance. In particular, we give improved upper bounds on the overhead required for similarity defined by Hamming distance r > 1 and prove a lower bound showing qualitative optimality of the overhead required for similarity over any Hamming distance r. Our main conceptual contribution is a connection between similarity search algorithms and certain graph-theoretic quantities. For our upper bounds, we exhibit a general method for designing one-round protocols using edge-isoperimetric shapes in similarity graphs. For our lower bounds, we define a new combinatorial optimization problem, which can be stated in purely graph-theoretic terms yet also captures the core of the analysis in previous theoretical work on distributed similarity joins. As one of our main technical results, we prove new bounds on distance correlations in subsets of the Hamming cube.

Details

MFCS Conference 2016 Conference Paper

Shattered Sets and the Hilbert Function

Shay Moran
Cyrus Rashtchian

We study complexity measures on subsets of the boolean hypercube and exhibit connections between algebra (the Hilbert function) and combinatorics (VC theory). These connections yield results in both directions. Our main complexity-theoretic result demonstrates that a large and natural family of linear program feasibility problems cannot be computed by polynomial-sized constant-depth circuits. Moreover, our result applies to a stronger regime in which the hyperplanes are fixed and only the directions of the inequalities are given as input to the circuit. We derive this result by proving that a rich class of extremal functions in VC theory cannot be approximated by low-degree polynomials. We also present applications of algebra to combinatorics. We provide a new algebraic proof of the Sandwich Theorem, which is a generalization of the well-known Sauer-Perles-Shelah Lemma. Finally, we prove a structural result about downward-closed sets, related to the Chvatal conjecture in extremal combinatorics.

Details