Papers by Sandesh Swamy
Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing evaluations for visual hallucinations are narrow. |
| Approach: | They propose a framework that decomposes reasoning chains into perception versus reasoning steps and uses off-the-shelf VLM judges for step-level faithfulness. |
| Outcome: | The proposed framework reduces Unfaithful Perception Rate while preserving final-answer accuracy. |
Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies show that large pre-trained language models can be adapted to task-oriented dialog systems. |
| Approach: | They propose to use contextual dynamic prompting to generate prompts in dialogs . they propose to distill useful prompting signals from dialog contexts based on contextual dynamic . |
| Outcome: | The proposed approach improves response generation by 3 points and 17 points when dialog states are incorporated. |
The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing literature on uncooperative behavior degrades collective outcomes and requires more resilient multi-agent systems. |
| Approach: | They propose a game theory-based taxonomy of uncooperative agent behaviors and a structured, multi-stage simulation pipeline that dynamically generates and refines uncooperation behaviors as agents’ states evolve. |
| Outcome: | The proposed framework achieves 96.7% accuracy in generating realistic uncooperative behaviors, validated by human evaluations. |