Papers by Sriram Balasubramanian

3 papers
Tool Preferences in Agentic LLMs are Unreliable (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) can now access a wide range of external tools thanks to the Model Context Protocol (MCP).
Approach: They expose a vulnerability in prevalent tool/function-calling protocols by editing tool descriptions to find out which tools are used by LLMs.
Outcome: The proposed changes in the tool descriptions can increase the usage of tools from LLMs when competing with alternatives.
A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Chain-of-thought reasoning improves performance of large language models, but is it faithfully reflecting internal processes?
Approach: They propose a new evaluation pipeline for categorizing bias articulation patterns and a novel evaluation pipeline to examine CoT faithfulness in large vision-language models.
Outcome: The proposed evaluation pipeline enables significantly more precise analysis of CoT reasoning than previous methods.
Decomposition-Enhanced Training for Post-Hoc Attributions in Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for extractive QA struggle in multi-hop, abstractive, and semi-extractive settings.
Approach: They propose a method that prompts models to produce answer decompositions as intermediate reasoning steps.
Outcome: The proposed method outperforms existing methods and matches or exceeds state-of-the-art frontier models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations