Papers by Zhenwen Li
Verified Critical Step Optimization for LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Critical Step Optimization (CSO) focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Approach: | They propose a method which focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Outcome: | The proposed method outperforms the existing methods on GAIA-Text-103 and XBench-DeepSearch while requiring supervision at only 16% of trajectory steps. |
Exploring the Secrets Behind the Learning Difficulty of Meaning Representations for Semantic Parsing (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that the design of Meaning Representation (MR) greatly influences the final model performance of a neural semantic parser. |
| Approach: | They propose a data-aware metric called ISS to measure the final performance of MRs. |
| Outcome: | The proposed metric denoting incremental structural stability (ISS) of MRs can be used as an indicator for MR design to avoid the costly training-testing process. |
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning (2025.findings-acl)
Copied to clipboard
Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu, Xusheng Chen, Tao Xie, Yizhou Shan
| Challenge: | Large Language Models (LLMs) have demonstrated strong capabilities across various domains, but their large-scale deployment faces a major obstacle: the high computational cost of long-sequence inference. |
| Approach: | They propose an algorithm that retains key-value vectors until they are no longer needed to solve reasoning tasks. |
| Outcome: | The proposed algorithm achieves high accuracy with O(L) time but O(N) memory complexities. |
Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience (2026.acl-long)
Copied to clipboard
| Challenge: | Existing verifiers operate on the surface text or on confidence proxies derived from token probabilities, which can be brittle. |
| Approach: | They propose a training-free, non-parametric verifier that summarizes each reasoning trace by an activation delta and compares it to two class centroids computed from labeled experience. |
| Outcome: | The proposed model improves selection and reranking on large and less-calibrated models. |
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP) Existing cost analyses regulate only the number of sampling passes, ignoring the substantial disparities in sampling costs. |
| Approach: | They propose to integrate two complementary methods into a unified EconRL pipeline to increase pass rates under constrained sampling passes. |
| Outcome: | The proposed method reduces token usage and sample passes while maintaining the original performance. |
Composing Elementary Discourse Units in Abstractive Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Abstractive summarization uses a single document sentence to generate a summary, but this can cause performance degradation. |
| Approach: | They propose to use elementary discourse unit (EDU) as the summarization unit to extract and group informative EDUs and then an EDU fusion model to fuse the EDU in each group into one sentence. |
| Outcome: | The proposed model can be used to combine informative EDUs into one sentence and reward selection actions. |
Benchmarking Meaning Representations in Neural Semantic Parsing (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on meaning representations is not comprehensively evaluated due to the lack of readily-available execution engines. |
| Approach: | They propose a unified benchmark on meaning representations by integrating existing semantic parsing datasets, completing the missing logical forms, and implementing the missing execution engines. |
| Outcome: | The proposed benchmark combines existing parsing datasets, completes missing logical forms, and implements missing execution engines. |