collaborators

7 papers

cs.CL2026

A Unified Definition of Hallucination: It's The World Model, Stupid!

Emmy Liu, Varun Gangal, Chelsea Zou +7

Despite numerous attempts at mitigation since the inception of language models, hallucinations remain a persistent problem even in today's frontier LLMs. Why is this? We review exi…

cs.CR2026

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents

Yoshinari Fujinuma, Varun Gangal, Traian Rebedea +4

Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a new attack surface for agents…

cs.CL2026

HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models

Emmy Liu, Varun Gangal, Michael Yu +4

Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization, question answering, retrieval-…

cs.CL2026

To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval

Karan Singh, Michael Yu, Varun Gangal +4

Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. In this work, we system…

cs.AI2025

MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environments

Darshan Deshpande, Varun Gangal, Hersh Mehta +3

Recent works on context and memory benchmarking have primarily focused on conversational instances but the need for evaluating memory in dynamic enterprise environments is crucial…

cs.CL2025

Sparse Rewards Can Self-Train Dialogue Agents

Barrett Martin Lattimer, Varun Gangal, Ryan McDonald +1

Recent advancements in state-of-the-art (SOTA) Large Language Model (LLM) agents, especially in multi-turn dialogue tasks, have been primarily driven by supervised fine-tuning and…