Papers by Chirag Agarwal
A Survey of Multilingual Reasoning in Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | This survey provides the first in-depth review of multilingual reasoning in Language Models. |
| Approach: | This survey provides the first in-depth review of multilingual reasoning in LMs. |
| Outcome: | The present study provides the first in-depth review of multilingual reasoning in LMs. |
EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding (2025.emnlp-main)
Copied to clipboard
Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar, Nishit Anand, Sonal Kumar, Sreyan Ghosh, Ramani Duraiswami, Chirag Agarwal, Dinesh Manocha
| Challenge: | Multimodal Large Language Models excel at visual perception and reasoning in third-person and egocentric videos, but are prone to hallucinations, generating coherent yet inaccurate responses. |
| Approach: | They propose to use a benchmark to evaluate MLLM hallucinations in egocentric videos. |
| Outcome: | EGOILLUSION comprises 1,400 videos paired with 8,000 human-annotated open and closed-ended questions designed to trigger hallucinations in both visual and auditory cues in egocentric videos. |
CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have produced strong performance in mathematical reasoning and code generation, but medical reasoning remains challenging because it requires domain knowledge. |
| Approach: | They propose a multilingual medical reasoning dataset with open-ended reasoning queries with a single verifiable answer that spans thirteen languages. |
| Outcome: | The proposed framework outperforms baselines and scales effectively across thirteen languages. |
A Graph Talks, But Who’s Listening? Rethinking Evaluations for Graph-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for Graph-Language Models (GLMs) do not assess true multimodal integration. |
| Approach: | They propose a benchmark to evaluate multimodal reasoning over graph topology and textual semantics. |
| Outcome: | The proposed benchmarks show that strong performance is achievable using textual or structural features in isolation, bypassing the need for joint reasoning. |
Towards Operationalizing Right to Data Protection (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent work introduces the concept of generating unlearnable datasets (by adding imperceptible spurious correlations to the clean data) this approach is limited by several practical constraints like requiring knowledge of the target model. |
| Approach: | They propose a framework that injects imperceptible spurious correlations into natural language datasets, rendering them unlearnable without affecting semantic content. |
| Outcome: | The proposed framework can restrict newer models like GPT-4o and Llama from learning on generated data, resulting in a drop in test accuracy compared to their zero-shot performance. |
On the Impact of Fine-Tuning on Chain-of-Thought Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models have emerged as powerful tools for general intelligence, showcasing advanced natural language processing capabilities. |
| Approach: | They propose to use supervised fine-tuning and Quantized Low-Rank Adapters to improve LLMs' task-specific performance to address privacy and safety risks. |
| Outcome: | The proposed model improves the accuracy of the chain-of-thought reasonings across four datasets and demonstrates that the faithfulness of CoT reasoning decreases. |
Towards Understanding the Robustness of Sparse Autoencoders (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. |
| Approach: | They propose to integrate pretrained Sparse Autoencoders into transformer residual streams at inference time without modifying model weights or blocking gradients. |
| Outcome: | The proposed model reduces jailbreak success rate by 5x compared to baseline models . compared with models with weak white-box attacks, the proposed model is more robust . |
A Mechanistic Perspective and Difficulty Metric for Unlearning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that machine unlearning success varies across samples . easy-to-unlearn samples are associated with shorter, shallower interactions . hard-to unlear rely on longer and deeper pathways closer to late-stage computation. |
| Approach: | They propose a pre-unlearning metric that assigns each sample a continuous difficulty score . they show that CUD reliably separates intrinsically easy and hard samples . |
| Outcome: | The proposed method reliably separates intrinsically easy and hard samples and remains stable across unlearning methods. |
Analyzing Memorization in Large Language Models through the Lens of Model Attribution (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing research has focused on extracting memorized content from LLMs or developing memorization metrics without exploring the underlying architectural factors that contribute to memorizing. |
| Approach: | They analyze how attention modules at different layers impact its memorization and generalization performance by using attribution techniques. |
| Outcome: | The proposed model can be used to mitigate memorization while keeping other components like layer normalization and MLP transformations intact. |