Papers by Hang Zhu
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models (2025.emnlp-main)
Copied to clipboard
Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, JingBo Zhu
| Challenge: | Recent training-based TTS methods, such as continued reinforcement learning, have surged in popularity, while training-free TTS approaches are gradually fading from prominence. |
| Approach: | They propose a fine-grained sequential scaling method guided by process verification that integrates training-free TTS methods with other classical parallel scaling methods at the step level. |
| Outcome: | Experiments on five instruction-tuned large language models (LLMs) show that training-free TTS methods can extend reasoning performance boundaries. |
Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods of fine-tuning vision-language navigation models require extra human-labeled data and lack self-exploration capabilities in environments. |
| Approach: | They propose a method that can self-explore environments without human labeling . they use a large-scale cross-modal pretrained model to build an in-domain dataset . |
| Outcome: | The proposed model can self-explore environments without human labeling without human supervision and generates structured instructions without human intervention. |
Unified Demonstration Retriever for In-Context Learning (2023.acl-long)
Copied to clipboard
Xiaonan Li, Kai Lv, Hang Yan, Tianyang Lin, Wei Zhu, Yuan Ni, Guotong Xie, Xiaoling Wang, Xipeng Qiu
| Challenge: | In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction. |
| Approach: | They propose a single model to retrieve demonstrations for a wide range of tasks by combining training signals from various tasks into a unified list-wise ranking formulation by language model’s feedback. |
| Outcome: | The proposed model outperforms baselines on 30+ tasks across 13 task families and multiple data domains. |
Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)
Copied to clipboard
Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang
| Challenge: | Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data. |
| Approach: | They propose a framework that imposes strong typing constraints and incorporates key relationships from schema. |
| Outcome: | The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider. |
EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records (2024.emnlp-main)
Copied to clipboard
Wenqi Shi, Ran Xu, Yuchen Zhuang, Yue Yu, Jieyu Zhang, Hang Wu, Yuanda Zhu, Joyce Ho, Carl Yang, May Dongmei Wang
| Challenge: | EHRAgent enables clinicians to interact with EHRs using natural language . reliance on rule-based conversion systems often necessitates additional training or effort from data engineers. |
| Approach: | They propose a large language model agent that generates and executes code in natural language to facilitate clinicians in directly interacting with EHRs. |
| Outcome: | The proposed agent outperforms the strongest baseline by up to 29.6% in success rate on three real-world EHR datasets. |
Generating then Refining for Reliable Knowledge Base Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge base question answering methods generate LFs that are non-executable due to semantic hallucination issue of large language models. |
| Approach: | They propose a "generate-verify-refine" framework for reliable LF generation . they propose ARI-KBQA to generate query paths based on hop-by-hop reasoning . |
| Outcome: | The proposed framework significantly improves model performance with a reduced search space . ARI-KBQA can generate LFs that are non-executable due to semantic hallucination issue . |
RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing solutions to reasoning tasks require extensive human annotations or fail in scenarios with inconsistent responses. |
| Approach: | They propose a new method that enables LLMs to self-rank their responses without additional resources. |
| Outcome: | The proposed method improves reasoning performance of ChatGPT and GPT-4 with 13% improvement over existing methods. |
Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing video fake news detection benchmarks focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process. |
| Approach: | They propose a process-oriented video fake news detection benchmark that evaluates MLLMs' perception, understanding, and reasoning capabilities in VFND. |
| Outcome: | The proposed model achieves sota performance on video fake news detection tasks. |
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that Large Language Models can generate diverse solutions during the rollout phase. |
| Approach: | They propose a new approach that leverages Semantic Neighbor Mixing to generate diverse input representations by mixing anchor tokens and nearest semantic neighbors. |
| Outcome: | Experimental results show that the proposed approach improves on strong baselines and generalizes on out-of-distribution tasks. |
How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models excel at capturing semantic correlations within utterance embeddings but fail to determine specific causal relationships. |
| Approach: | They propose to incorporate i.i.d. noise terms into conversation process to build a structural causal model . they propose to use unstructured conversation data to facilitate deep learning . |
| Outcome: | The proposed approach can be implemented in unstructured conversation data and a synthetic dataset that includes i.i.d. noise. |
Hybrid Alignment Training for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to align large language models with instructions and preferences are conflicting . et al., 2023b) show that hybrid alignment training can outperform baselines . |
| Approach: | They propose a hybrid alignment training approach based on alternating alignment and modified elastic weight consolidation methods to achieve better collaboration between different alignment tasks. |
| Outcome: | The proposed approach outperforms baseline alignment training methods on summarization and dialogue tasks. |
Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning tasks and general tasks. |
| Approach: | They propose a "Verifier-free Intrinsic Gradient-Norm Reward" that uses only the policy model itself. |
| Outcome: | The proposed reward outperforms the state-of-the-art RLIF baseline INTUITOR on math benchmarks and shows cross-domain transfer to code benchmarks when trained only on math data. |
Quantifying Semantic Emergence in Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods for large language models (LLMs) focus on coarse-grained text, not providing interpretations for the behavior of finergrained tokens. |
| Approach: | They propose a quantitative metric to measure large language models’ ability to extract semantics from input tokens. |
| Outcome: | The proposed metric compares the entropy reduction observed for a sequence of tokens and individual tokens. |
Benchmarking Diverse-Modal Entity Linking with Generative Models (2023.findings-acl)
Copied to clipboard
Sijia Wang, Alexander Hanbo Li, Henghui Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, Jie Ma, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng
| Challenge: | Existing models for diverse-mode entity linking (EL) work well on per modality configurations, but it is more challenging to design a unified model for diverse modality. |
| Approach: | They propose a generative diverse-modal model that integrates text, image and table . they propose combining a multimodal encoder-decoder paradigm with a fine-tuning GDMM . |
| Outcome: | The proposed model outperforms state-of-the-art models by 8.51 F1 on average for diverse-modal EL. |
HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. |
| Approach: | They propose a method that selects attention heads crucial to the model's prediction as inducing heads and induces hallucinations by dispersing attention of these inducers. |
| Outcome: | The proposed method significantly improves performance on tasks requiring contextual faithfulness, reading comprehension, and question answering. |
Improving Autoregressive Grammatical Error Correction with Non-autoregressive Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive models assign low probabilities to tokens that need corrections . grammatical error correction (GEC) is widely applied to natural language processing tasks . |
| Approach: | They propose to use a non-autoregressive model as an auxiliary model to train GEC models to correct grammatical errors in sentences. |
| Outcome: | The proposed method outperforms baselines on English and Chinese GEC tasks significantly. |
HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application (2026.acl-long)
Copied to clipboard
| Challenge: | Existing agent benchmarks neglect hierarchical rule application in real-world domains . a critical gap persists in numerous real-life professional domains where decision-making is governed by expert-written rules. |
| Approach: | They propose a benchmark requiring agents to assign a unique 10-digit Harmonized System (HS) Code to products by aligning their fuzzy attributes with strict tariff classification rules. |
| Outcome: | The proposed benchmarks lack hierarchical rule application capability in real-world domains . the proposed benchmark is based on e-commerce and is open-source . |
PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries (2025.naacl-long)
Copied to clipboard
Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu, Anuj Chauhan, Chung-Wei Hang, Shuaichen Chang, Lin Pan, Wuwei Lan, Henghui Zhu, Jiarong Jiang, Patrick Ng, Zhiguo Wang
| Challenge: | Existing text-to-SQL systems focus on user questions with clear intentions that can be answered, but real user questions can be ambiguous with multiple interpretations or unanswerable due to a lack of relevant data. |
| Approach: | They construct a conversational text-to-SQL dataset called PRACTIQ, consisting of ambiguous and unanswerable questions inspired by real-world user questions. |
| Outcome: | The proposed system generates conversations with four turns, generating the user’s question, an assistant response seeking clarification, and the user's clarified SQL response with the natural language explanation of the execution results. |
Unified Active Retrieval for Retrieval Augmented Generation (2024.findings-emnlp)
Copied to clipboard
Qinyuan Cheng, Xiaonan Li, Shimin Li, Qin Zhu, Zhangyue Yin, Yunfan Shao, Linyang Li, Tianxiang Sun, Hang Yan, Xipeng Qiu
| Challenge: | Existing active retrieval methods struggle with handling various types of instructions. |
| Approach: | They propose a unified active retrieval framework for retrieval-augmented generation . they propose to combine four orthogonal criteria into plug-and-play classification tasks . |
| Outcome: | The proposed framework outperforms existing methods on four representative types of user instructions on four types of instructions. |
Teaching Language Models to Self-Improve by Learning from Language Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) generate content that can be untruthful or harmful. |
| Approach: | They propose a method that leverages model feedback for alignment . they use a base language model to generate initial responses, critiqued and refined . |
| Outcome: | The proposed method outperforms strong baselines across diverse tasks and model sizes. |
What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects (2026.findings-eacl)
Copied to clipboard
Naihao Deng, Sheng Zhang, Henghui Zhu, Shuaichen Chang, Jiani Zhang, Alexander Hanbo Li, Chung-Wei Hang, Hideo Kobayashi, Yiqun Hu, Patrick Ng
| Challenge: | a series of paradigm shifts have come with distinct characteristics and challenges associated with table modeling. |
| Approach: | They propose to replicate four table LLMs by instruction-tuning three foundation models on four existing datasets. |
| Outcome: | The results show that base model choice plays a more dominant role than training data itself. |