Papers by Shunjie Xing

2 papers
HEAL: A Hypothesis-Based Preference-Aware Analysis Framework (2025.findings-emnlp)

Copied to clipboard

Challenge: Preference optimization methods like DPO are often evaluated on a single response, overlooking other outputs.
Approach: They propose a Hypothesis-based PrEference-aware AnaLysis Framework that formulates preference alignment as a re-ranking process within hypothesis spaces.
Outcome: The proposed evaluation paradigm re-ranks preference alignment as a reranking process within hypothesis spaces.
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories.
Approach: They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision .
Outcome: The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision.

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