Papers by Chetan Bansal
CARMO: Dynamic Criteria Generation for Context Aware Reward Modelling (2025.findings-acl)
Copied to clipboard
Taneesh Gupta, Shivam Shandilya, Xuchao Zhang, Rahul Madhavan, Supriyo Ghosh, Chetan Bansal, Huaxiu Yao, Saravan Rajmohan
| Challenge: | Reward modeling in large language models is susceptible to reward hacking . flawed reward signals often lead to outputs that optimize for spurious correlates . |
| Approach: | They propose a new approach that generates dynamic, context-relevant criteria to ground the reward model prior to producing reward scores. |
| Outcome: | The proposed approach generates dynamic, context-relevant criteria to ground the model prior to producing reward scores. |
Learning Optimal Message Representations for Agentic Communication (2026.findings-acl)
Copied to clipboard
Shashwat Gupta, Anson Bastos, Mayukh Das, Supriyo Ghosh, Nagarajan Natarajan, Chetan Bansal, Saravan Rajmohan
| Challenge: | Existing approaches lack the intelligence necessary to understand, learn or apply optimal communication representations adaptively. |
| Approach: | They propose to dynamically learn the optimal message representations to enhance agentic performance by using an Expanding Markov Decision Process. |
| Outcome: | The proposed framework improves agentic performance while maintaining efficiency. |
SynthAgent: Adapting Web Agents with Synthetic Supervision (2026.acl-long)
Copied to clipboard
Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao
| Challenge: | Existing studies have focused on synthetic supervision but have encountered data quality issues. |
| Approach: | They propose a fully synthetic supervision framework that aims at improving data quality via dual refinement of both tasks and trajectories. |
| Outcome: | The proposed framework outperforms existing methods on standardized benchmarks and shows promising results on a standardized test. |
Verifiable Format Control for Large Language Model Generations (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods focus on benchmarking general instruction following while overlooking how to improve specific format following ability for small LLMs. |
| Approach: | They propose to synthesize massive datasets to improve LLMs' format following abilities by using a verifiable format following feature. |
| Outcome: | The proposed method improves the format following ability of small LLMs with about 7B parameters. |
Synergistic Weak-Strong Collaboration by Aligning Preferences (2025.acl-long)
Copied to clipboard
Yizhu Jiao, Xuchao Zhang, Zhaoyang Wang, Yubo Ma, Zhun Deng, Rujia Wang, Chetan Bansal, Saravan Rajmohan, Jiawei Han, Huaxiu Yao
| Challenge: | Current Large Language Models excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. |
| Approach: | They propose a collaborative framework that pairs a specialized weak model with a general strong model to optimize collaboration. |
| Outcome: | The proposed framework outperforms each model alone by leveraging complementary strengths. |