Papers by Sheng Wan
CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve the reasoning performance of LLMs suffer from two major shortcomings: too lengthy input contexts and overconfidence dilemma. |
| Approach: | They propose a method to debating among LLM agents using a sparse debator graph . they use a module called McKinsey-based Debate Matter to optimize the debators . |
| Outcome: | The proposed method has been well demonstrated across eight datasets from four task types. |
Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing prompting methods struggle with complex tasks and reasoning stability, limiting their practical deployment. |
| Approach: | They propose a framework that adaptively balances reasoning accuracy and computational efficiency by employing a lightweight Derailer mechanism to assess reasoning stability and selectively triggers an advanced Rerailer verification process only when necessary. |
| Outcome: | The proposed framework achieves significant accuracy improvements (8-11%) while maintaining 2-3 times better efficiency than existing verification methods. |
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)
Copied to clipboard
Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Gong Yifan, Sheng Zhang
| Challenge: | Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting. |
| Approach: | They propose a representation-aware model merging framework for continual learning without access to historical data. |
| Outcome: | The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios. |
SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models (2025.acl-long)
Copied to clipboard
Zhen Wan, Chao-Han Huck Yang, Yahan Yu, Jinchuan Tian, Sheng Li, Ke Hu, Zhehuai Chen, Shinji Watanabe, Fei Cheng, Chenhui Chu, Sadao Kurohashi
| Challenge: | SIQ quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models. |
| Approach: | They propose a human cognition-inspired evaluation pipeline for voice understanding large language models (LLM_Voice) that quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models. |
| Outcome: | The proposed framework quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM_Voice. |
CoVoGER: A Multilingual Multitask Benchmark for Speech-to-text Generative Error Correction with Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models can fix recognition or translation errors that traditional rescoring cannot fix. |
| Approach: | They propose a benchmark for GER that covers both ASR and speech-to-text translation across 15 languages and 28 language pairs. |
| Outcome: | The proposed benchmark is built on common voice 20.0 and CoVoST-2 with Whisper and SeamlessM4T. |
Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) generate reasoning paths before answers, but lack a systematic approach to determine optimal number of samples or select the most faithful rationale. |
| Approach: | They propose a framework that evaluates the quality of reasoning and consistency of answers for each generated sample and uses criteria-based stopping and weighted majority voting to guide early stopping decisions and rationale selection. |
| Outcome: | The proposed framework outperforms existing methods while maintaining accuracy. |
COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context (2026.acl-long)
Copied to clipboard
| Challenge: | Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents. |
| Approach: | They propose a framework that separates tactical execution, strategic oversight, and context organization into three specialized components. |
| Outcome: | The proposed framework improves accuracy by 20% relative to baselines on GAIA, BrowseComp, and Humanity’s Last Exam tasks. |