Loading Events

« All Events

Hybrid Event

Huang, S. (CSE) – From Hallucination Detection to Self-Improvement: Towards Reliable LLMs through Fine-Grained Feedback

December 9 @ 10:00 am – 12:00 pm
Hybrid Event
Abstract digital illustration featuring gears and interconnected technology elements.

Large language models can produce unsupported claims in short phrases embedded in otherwise accurate responses. This PhD proposal investigates how to pinpoint and reduce these hallucinations using span-level supervision. I introduce SHAM-Bench, a benchmark spanning six generation tasks, and present a detector that uses retrieved evidence to identify hallucinated spans. The detector achieved the highest average rank in the SemEval 2025 multilingual hallucination detection challenge across 14 languages. In summarization experiments, I find that unlikelihood training is the most effective of the mitigation methods tested. In future work, I will investigate how reinforcement learning with verified reasoning steps can improve knowledge recall and whether jointly training an agent and a trajectory verifier enables self-improvement on agentic task performance.

Event Host: Sicong Huang, PhD Student, Computer Science & Engineering 

Advisor: Ian Lane

Zoom: https://ucsc.zoom.us/j/99455562030?pwd=ztbMAYTYNwcbLoYuTnp9kxEtTovVOI.1

Passcode: 012478

Details

Other

Room Number
SVC 3003