5 papers
The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining
Vy Nguyen, Ziqi Xu, Jeffrey Chan +5
Language models (LMs) often hallucinate by committing to confident answers rather than abstaining, even when they do not have enough information to answer reliably. A large body of…
Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning
Vy Nguyen, Ziqi Xu, Jeffrey Chan +5
Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided evidence. When evidence is insufficient, it is desirable that models abstain rathe…
The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion
Chenglong Ma, Xinye Wanyan, Danula Hettiachchi +2
LLM-generated search queries are widely used to augment IR evaluation, yet they may contain concepts that presuppose answer-side document knowledge, violating the information-acces…
Task-Aware Automated User Profile Generation for Recommendation Simulation Using Large Language Models
Xinye Wanyan, Chenglong Ma, Danula Hettiachchi +2
Large Language Model (LLM)-based agent simulation has emerged as a promising approach to meet the increasing demand for real-time and rigorous evaluation in modern recommender syst…
Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
Vy Nguyen, Ziqi Xu, Jeffrey Chan +3
Large Language Models (LLMs) often produce fluent but factually incorrect responses, a phenomenon known as hallucination. Abstention, where the model chooses not to answer and inst…