activity
20242026
collaborators
Showing cs.CLShow all

9 papers · 1 filter

cs.CL2026

PreUnlearn: Auditing Collateral Knowledge Damage Before Large Language Model Unlearning

Bo Su, Ankit Shah, Thai Le

Machine unlearning for large language models (LLMs) aims to remove specified knowledge while preserving the rest of the model's capabilities. However, the boundary between knowledg…

cs.CL2026

Inference Time Optimization with Confidence Dynamics

Yu Wang, Minghao Liu, Jiayun Wang +3

Inference time optimization techniques, such as repeated sampling, have significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, the critical rol…

cs.CL2026

Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems

Mohammad Parsa Hosseini, Ankit Shah, Saiyra Qureshi +3

Multi-agent large language model (LLM) systems enable complex, long-horizon reasoning by composing specialized agents, but practical deployment remains hindered by inefficient rout…

cs.CL2025

ProRefine: Inference-Time Prompt Refinement with Textual Feedback

Deepak Pandita, Tharindu Cyril Weerasooriya, Ankit Parag Shah +3

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications…

cs.CL2025

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Zhenting Wang, Qi Chang, Hemani Patel +8

We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter cont…

cs.CL2025

Enhancing Retrieval for ESGLLM via ESG-CID -- A Disclosure Content Index Finetuning Dataset for Mapping GRI and ESRS

Shafiuddin Rehan Ahmed, Ankit Parag Shah, Quan Hung Tran +5

Climate change has intensified the need for transparency and accountability in organizational practices, making Environmental, Social, and Governance (ESG) reporting increasingly c…