5 citations · 21 across the 17 of their papers we have counts for
20 papers
Same Answer, Different Reasons: Trace-Level Divergence in Multilingual Large Language Models
Rui Sun, Peizhao Mei, Xiewei Cheng +4
Multilingual large language models are increasingly deployed in settings where visible reasoning traces support verification, education, and safety auditing, yet standard evaluatio…
Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning
Dongwon Jung, Hemanth Neelgund Ramesh, Yifan Wang +7
Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment of trajectory-level advantages t…
Model-Aware Data Selection from In-and-Out Information Interplay
Yifan Wang, Xiaomin Li, Yuexing Hao +7
LLMs are effective representations that assimilate vast amounts of knowledge during pretraining, but post-training is necessary for models to reliably access this knowledge and "kn…
AgentAbstain: Do LLM Agents Know When Not to Act?
Xun Liu, Yi Evie Zhang, Vira Kasprova +5
Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents…
Layer-Targeted Multilingual Knowledge Erasure in Large Language Models
Taoran Li, Varun Chandrasekaran, Zhiyuan Yu
Recent work has demonstrated that machine unlearning in Large Language Models (LLMs) fails to generalize across languages: knowledge erased in one language frequently remains acces…
AMUN: Adversarial Machine UNlearning
Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran
Machine unlearning, where users can request the deletion of a forget dataset, is becoming increasingly important because of numerous privacy regulations. Initial works on ``exact''…
MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation
Siddharth Joshi, Besmira Nushi, Vidhisha Balachandran +4
Vision-language models (VLMs) are highly effective but often underperform on specialized tasks; for example, Llava-1.5 struggles with chart and diagram understanding due to scarce…
The Efficacy of Transfer-based No-box Attacks on Image Watermarking: A Pragmatic Analysis
Qilong Wu, Varun Chandrasekaran
Watermarking approaches are widely used to identify if images being circulated are authentic or AI-generated. Determining the robustness of image watermarking methods in the ``no-b…
Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models
Rishabh Adiga, Besmira Nushi, Varun Chandrasekaran
We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing bet…
Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models
Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran +6
With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance i…
LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran
Transferability of adversarial examples is a well-known property that endangers all classification models, even those that are only accessible through black-box queries. Prior work…
BenchAgents: Multi-Agent Systems for Structured Benchmark Creation
Natasha Butt, Varun Chandrasekaran, Neel Joshi +2
Evaluation insights are limited by the availability of high-quality benchmarks. As models evolve, there is a need to create benchmarks that can measure progress on new and complex…
Generative Monoculture in Large Language Models
Fan Wu, Emily Black, Varun Chandrasekaran
We introduce {\em generative monoculture}, a behavior observed in large language models (LLMs) characterized by a significant narrowing of model output diversity relative to availa…
Bypassing LLM Watermarks with Color-Aware Substitutions
Qilong Wu, Varun Chandrasekaran
Watermarking approaches are proposed to identify if text being circulated is human or large language model (LLM) generated. The state-of-the-art watermarking strategy of Kirchenbau…
Designing Informative Metrics for Few-Shot Example Selection
Rishabh Adiga, Lakshminarayanan Subramanian, Varun Chandrasekaran
Pretrained language models (PLMs) have shown remarkable few-shot learning capabilities when provided with properly formatted examples. However, selecting the "best" examples remain…
Teaching Language Models to Hallucinate Less with Synthetic Tasks
Erik Jones, Hamid Palangi, Clarisse Simões +5
Large language models (LLMs) frequently hallucinate on abstractive summarization tasks such as document-based question-answering, meeting summarization, and clinical report generat…
KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval
Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran +5
We study the ability of state-of-the art models to answer constraint satisfaction queries for information retrieval (e.g., 'a list of ice cream shops in San Diego'). In the past, s…
Privately Aligning Language Models with Reinforcement Learning
Fan Wu, Huseyin A. Inan, Arturs Backurs +3
Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training ins…
Diversity of Thought Improves Reasoning Abilities of LLMs
Ranjita Naik, Varun Chandrasekaran, Mert Yuksekgonul +2
Large language models (LLMs) are documented to struggle in settings that require complex reasoning. Nevertheless, instructing the model to break down the problem into smaller reaso…
Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones +5
We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constrain…