Papers by Zhongxiang Sun
Large Language Model-Enhanced Multi-Armed Bandits (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been used to sequential decision-making tasks like multi-armed bandits where an LLM is tasked with selecting arms in each iteration is often suboptimal. |
| Approach: | They propose to combine MAB and LLMs to leverage the in-context learning capability of LLM for reward prediction. |
| Outcome: | The proposed approach outperforms LLM-based direct arm selection on synthetic tasks where only preference feedback between arm pairs is available. |
Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work studies RLVR through token entropy, arguing that high-entropies drive exploration and should receive stronger updates. |
| Approach: | They propose a correctness-aware reinforcement framework that performs fine-grained advantage modulation over low-entropy segments. |
| Outcome: | The proposed framework improves accuracy over strong RL baselines across three backbones and six math benchmarks while maintaining high-entropy exploration. |
Streaming Hallucination Detection in Long Chain-of-Thought Reasoning (2026.findings-acl)
Copied to clipboard
Haolang Lu, Minghui Pan, Ripeng LI, Guoshun Nan, Jialin Zhuang, Zijie Zhao, Zhongxiang Sun, Kun Wang, Yang Liu
| Challenge: | Long chain-of-thought reasoning improves performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps. |
| Approach: | They propose to treat step-level hallucination judgments as local observations and introduce a cumulative prefix-level signal that tracks the global evolution of the reasoning state over the entire trajectory. |
| Outcome: | The proposed method enables streaming hallucination detection in long CoT reasoning, providing real-time, interpretable evidence. |
When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Personalization can inadvertently distort factual reasoning when faced with factual queries. |
| Approach: | They propose a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior. |
| Outcome: | Experiments across multiple LLM backbones and personalization methods show that FPPS significantly improves factual accuracy while maintaining personalized performance. |