Papers by Qingyang Zhang
Towards Reward Fairness in RLHF: From a Resource Allocation Perspective (2025.acl-long)
Copied to clipboard
| Challenge: | if rewards are imperfect, they can adversely affect the alignment of large language models (LLMs). |
| Approach: | They propose a bias-agnostic method to address the issue of reward unfairness from a resource allocation perspective without specifically designing for each type of bias . they apply methods Fairness Regularization and Fairness Coefficient to achieve fairness in rewards. |
| Outcome: | The proposed method achieves fairness in rewards while minimizing biases . it can be applied to verification and reinforcement learning scenarios . |
USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)
Copied to clipboard
Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang
| Challenge: | Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations. |
| Approach: | They propose a framework that covers 61 risk categories across four modality interactions to address this gap. |
| Outcome: | The proposed framework covers 61 risk categories across four distinct modality interactions. |
Reasoning or Knowledge: Stratified Evaluation of Biomedical LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Medical reasoning in large language models is a complex cognitive process through which clinicians interpret patient data and make diagnostic and therapeutic decisions. |
| Approach: | They propose an evaluation framework that disentangles knowledge recall from reasoning by training a PubMedBERT-based classifier and applying it to 11 widely used biomedical QA benchmarks. |
| Outcome: | The proposed evaluation framework disentangles knowledge recall from reasoning by training a PubMedBERT-based classifier and applying it to 11 widely used biomedical QA benchmarks. |
Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for function calling require expert effort and prompt engineering becomes inefficient. |
| Approach: | They propose a method that performs fine-grained, stepwise retrieval from a continually updated experience pool. |
| Outcome: | The proposed method achieves an average improvement of 6.1% on easy and 4.7% on hard questions. |
Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes (2024.naacl-long)
Copied to clipboard
| Challenge: | Our work explores the potential of large language models (LLMs) to close the novice-expert knowledge gap in remediating math mistakes. |
| Approach: | They propose a method that uses cognitive task analysis to translate an expert’s latent thought process into a decision-making model for remediation. |
| Outcome: | The proposed model can bridge the novice-expert knowledge gap by using cognitive task analysis to translate an expert’s latent thought process into a decision-making model for remediation. |
DECOR: Improving Coherence in L2 English Writing with a Novel Benchmark for Incoherence Detection, Reasoning, and Rewriting (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing automated writing evaluation systems only detect incoherence in writing . a recent study has found that incorporating specific reasons for incohence improves the quality of rewrites . |
| Approach: | They propose a benchmark that includes expert annotations for detecting incoherence in L2 English writing, identifying the underlying reasons, and rewriting the incoerent sentences. |
| Outcome: | The proposed benchmark improves coherence in L2 English writing by fine-tuning models . the authors find that incorporating specific reasons improves quality of rewrites . |
Just Ask One More Time! Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios (2024.findings-acl)
Copied to clipboard
Lei Lin, Jiayi Fu, Pengli Liu, Qingyang Li, Yan Gong, Junchen Wan, Fuzheng Zhang, Zhongyuan Wang, Di Zhang, Kun Gai
| Challenge: | chain-of-thought (CoT) prompting has been shown to be effective on complex reasoning tasks, but the naive greedy decoding used in CoT prompting causes the repetitiveness and local optimality. |
| Approach: | They propose a generalizable ensemble-optimization method that uses a set of reasoning paths to prompt a language model one more time to determine the optimal answer. |
| Outcome: | The proposed method can be generalized to almost all scenarios where the type of input questions and answer format of reasoning paths may be unknown. |
On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)
Copied to clipboard
Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie
| Challenge: | under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors. |
| Approach: | They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients . |
| Outcome: | The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets. |
SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to improve numerical and logical reasoning of Large Language Models are limited . existing approaches rely on prompt engineering and pretrained knowledge to ensure correctness . |
| Approach: | They propose to train LLMs with process-based reasoning using a dynamic value margin . they use the Bellman optimality equation to derive a value margin for step-level preference optimization . |
| Outcome: | The proposed method is equivalent to on-policy policy gradient methods under constrained reward functions. |
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. |
| Approach: | They propose a framework that uses pre-trained language to model each speaker separately . it can be generalized to more challenging, non-collaborative tasks such as persuasion . |
| Outcome: | The proposed framework outperforms or is on par with state-of-the-art methods on two popular datasets: CamRest676 and MultiWOZ. |
Coarse-to-Fine Grounded Memory for LLM Agent Planning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to enhance LLM with offline experiences or online trajectory analysis focus on single-granularity memory derived from dynamic environmental interactions. |
| Approach: | They propose a framework that grounds coarse-to-fine memories with LLM to enable flexible adaptation to diverse scenarios. |
| Outcome: | Extensive experiments on AlfWorld, Webshop and ScienceWorld show that the proposed framework outperforms baselines and comprehensively optimizes memory-enhanced LLM Agent system. |
Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large language models (LLMs) lack a coherent representation of reasoning steps. |
| Approach: | They propose a set of latent reasoning interventions that enable latent thinking and decode-time interventions that refine the latent process by imposing the identified geometric and semantic priors. |
| Outcome: | The proposed models unlock latent capabilities and improve reasoning accuracy without any parameter updates. |