Papers by Sidi Lu
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data (2026.acl-short)
Copied to clipboard
| Challenge: | Strong base models saturate benchmarks, resulting in weaker performance, a paradox . a new approach to Reinforcement Learning (RL) is needed to improve performance . |
| Approach: | They propose a method that uses constrained uniform top-k sampling to flatten the local optimization landscape by sampling uniformly from constrained high-confidence candidates. |
| Outcome: | Experiments show that the proposed approach prevents policy degeneration and boosts out-of-domain generalization. |
Role-Guided Annotation and Prototype-Aligned Representation Learning for Historical Literature Sentiment Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work focused on using sentiment lexicons or leveraging large language models for annotation . lexiconics are often unavailable for historical texts due to limited linguistic resources . |
| Approach: | They propose a role-guided annotation strategy that prompts LLMs to simulate historical perspectives when labeling sentiment. |
| Outcome: | The proposed method outperforms state-of-the-art baselines across historical literature datasets. |
Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reinforcement learning methods rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions. |
| Approach: | They propose a process reward model that rewards correct steps only when they detect errors . they propose VPPO, which rewards the correct prefix and an erroneous suffix . |
| Outcome: | a new approach outperforms sparse-reward RL and prior PRM-guided baselines on Pass@1 and Pass@K . a process reward model (PRM) outperformed sparser-rebound RL on multiple reasoning benchmarks . |