Papers by Bin Hu

EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution (2026.acl-long)

Challenge:	Existing safety controls fail to provide runtime intervention or cross-architecture portability for autonomous LLM agents.
Approach:	They propose a model-agnostic, plug-and-play module to provide arbitrary agent safety control and auditability.
Outcome:	The proposed module improves the secure-solution rate by 2.9–11.2 percentage points . it adds only 3.2s to end-to-end latency and a negligible average cost of 5.37 10-4 per scenario .

Copied to clipboard

Shiyu He, Minchi Kuang, Mengxian Wang, Bin Hu, Tingxiang Gu

Challenge:	Existing systems suffer from social memory stacking and narrative-spatial dissonance . long-horizon narratives suffer from conflicting relational states without resolution .
Approach:	They propose a framework to sustain logically coherent long-horizon narratives within endogenous interactive agent societies.
Outcome:	Experiments show that the framework outperforms baselines across paradigms.

F2RL: Factuality and Faithfulness Reinforcement Learning Framework for Claim-Guided Evidence-Supported Counterspeech Generation (2024.emnlp-main)

Copied to clipboard

Haiyang Wang, Yuchen Pan, Xin Song, Xuechen Zhao, Minghao Hu, Bin Zhou

Formally Specifying the Intended Behavior of the Program: LLM-Driven Neuro-Symbolic Program Specification Synthesis (2026.acl-demo)

Challenge:	Existing methods for generating evidence-supported counterspeech lack clear guidance with a core claim for organizing evidence.
Approach:	They propose a Factuality and Faithfulness Reinforcement Learning framework for generating claim-guided and evidence-supported counterspeech (F2RL) they generate counter-claims based on hate speech and design a self-evaluation mechanism to select the most appropriate one.
Outcome:	The proposed framework achieves excellent performance on three benchmark datasets with strong factuality and faithfulness.

Copied to clipboard

Cheng Wen, Hu Junjie, YiKun Hu, Jie Su, Bin Yu, Dugang Liu, Zhiwu Xu, Weidi Sun, Shengchao Qin, Cong Tian

Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors (2026.acl-long)

Challenge:	Formal verification typically requires developers to write detailed formal specifications . a formal verification system that generates candidate specifications is costly and error-prone .
Approach:	They propose an LLM-driven neuro-symbolic demonstration system that reframes specification writing as constrained structured synthesis.
Outcome:	The proposed system reduces hallucinations and produces proof-ready annotations.

Copied to clipboard

Zhiwei Zhang, Fei Zhao, Rui Wang, Zezhong Wang, Bin Liang, Jiakang Wang, Yao Hu, Shaosheng Cao, Kam-Fai Wong

Robustness in NLP

Challenge:	Large language models (LLMs) can call tools effectively, but they remain brittle in multi-turn execution.
Approach:	They propose a framework that converts execution errors into on-policy corrective supervision within the RL training loop.
Outcome:	The proposed framework improves the error recovery rate of Qwen3-8B by 5.7% absolute and overall accuracy by 4.0% on BFCL v4 Multi-Turn.

ZoomRAG: Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG (2026.findings-acl)

Copied to clipboard

Xianming Hu, Jingyang Chen, Bin Tang, Yihe Liu, Yihong Huang, Hongbo Zhao, Nuoyi Chen, Jie Zhang, Ping Li, Kai Zhang

Structured Data in NLP

Challenge:	retrieval-augmented generation (RAG) is a powerful tool for NLP applications . but it is challenging to encode large knowledge bases as compact offline structures .
Approach:	They propose a coarse-to-fine hierarchical graph inference method that uses random walks to retrieve information from a corpus of documents.
Outcome:	The proposed method reduces offline indexing costs and accelerates retrieval.

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)

Copied to clipboard

Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu

How LLMs Comprehend Temporal Meaning in Narratives: A Case Study in Cognitive Evaluation of LLMs (2025.acl-long)

Challenge:	Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression.
Approach:	They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks.
Outcome:	The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks.

Copied to clipboard

Karin De Langis, Jong Inn Park, Andreas Schramm, Bin Hu, Khanh Chi Le, Dongyeop Kang

Challenge:	Large language models exhibit increasingly sophisticated linguistic capabilities, yet the extent to which these models reflect human-like cognition versus advanced pattern recognition remains an open question.
Approach:	They conduct a series of targeted experiments to assess whether LLMs construct semantic representations and pragmatic inferences in a human-like manner.
Outcome:	The proposed framework can be used to assess the cognitive and linguistic capabilities of large language models (LLMs).

OSCBench: Benchmarking Object State Change in Text-to-Video Generation (2026.acl-long)

Copied to clipboard

Xianjing Han, Bin Zhu, Shiqi Hu, Franklin Mingzhe Li, Patrick Carrington, Roger Zimmermann, Jingjing Chen

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models (2024.findings-emnlp)

Challenge:	Existing benchmarks focus on perceptual quality, text–video alignment, or physical plausibility, leaving a critical aspect of action understanding unexplored.
Approach:	They introduce a benchmark specifically designed to assess OSC performance in T2V models.
Outcome:	The proposed benchmark assesses the performance of open-source and proprietary T2V models on object state change (OSC) in the context of novel and compositional scenarios.

Copied to clipboard

Wenhao Shi, Zhiqiang Hu, Yi Bin, Junhua Liu, Yang Yang, See-Kiong Ng, Lidong Bing, Roy Lee

Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting (2021.findings-emnlp)

Challenge:	Existing image instruction fine-tuning datasets do not fully exploit visual information to enhance multimodal reasoning capabilities of Large language models (LLMs).
Approach:	They propose a LLaVA-based model fine-tuned with MathV360K to bridge this gap by collecting 40K high-quality images with question-answer pairs from 24 existing datasets and synthesizing 320K new pairs.
Outcome:	The proposed model improves the multimodal reasoning capabilities of LLaVA-1.5 and demonstrates enhanced generalizability on the MMMU benchmark.

Copied to clipboard

Yi Feng, Ting Wang, Chuanyi Li, Vincent Ng, Jidong Ge, Bin Luo, Yucheng Hu, Xiaopeng Zhang

Information Retrieval

Challenge:	a method for user targeting is developed to identify online users to whom an ad should be targeted.
Approach:	They propose a method for automatic augmentation of positive and negative clickthrough data for user targeting models.
Outcome:	The proposed method can increase positive and negative instances of positive training instances on two datasets.

VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making (2025.emnlp-main)

Copied to clipboard

Zuojin Tang, Bin Hu, Chenyang Zhao, De Ma, Gang Pan, Bin Liu

PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning (2025.coling-main)

Challenge:	Recent large-scale pretrained models are built upon a multi-input single-output paradigm . tasks compete for a shared output channel, creating mutual exclusion effects .
Approach:	They propose a multi-input single-output (MISO) paradigm for large pretrained models . they propose unified training framework that enables concurrent multi-task outputs .
Outcome:	Experiments on autonomous driving platform show that MIMO-VLA outperforms state-of-the-art models in MIMO settings.

Copied to clipboard

Qibin Wang, Xiaolin Hu, Weikai Xu, Wei Liu, Jian Luan, Bin Wang

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)

Challenge:	Low-rank adaptation and its variants have been popular due to their ability to avoid excessive inference costs.
Approach:	They propose a low-rank adaptation method that enables high-rank updates with low costs while leveraging semantic and linguistic information inherent in pre-trained weight.
Outcome:	The proposed method outperforms LoRA and other fine-tuning methods across tasks with less trainable parameters.

Copied to clipboard

Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong

TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Industry Systems (2024.emnlp-industry)

Challenge:	Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models.
Approach:	They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.
Outcome:	The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models.

Copied to clipboard

Yilun Kong, Jingqing Ruan, YiHong Chen, Bin Zhang, Tianpeng Bao, Shi Shiwei, Du Qing, Xiaoru Hu, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao, Xueqian Wang

Semantic Text Processing

Challenge:	Large language models have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools.
Approach:	They propose a framework to enhance the task planning and tool usage abilities of LLMs in industrial systems.
Outcome:	The proposed framework enhances the task planning and tool usage abilities of LLM-based agents in industrial systems.

WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models (2023.emnlp-industry)

Copied to clipboard

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Yusen Hu, Bin Luo, Yifeng Geng, Xuansong Xie

PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)

Challenge:	Existing typography solutions lack adaptability, creativity, and computational efficiency.
Approach:	They propose a user-driven framework for artistic typography synthesis based on the Large Language Model (LLM) the LLM Engine interprets user inputs and generates actionable prompts for the other modules, transforming abstract concepts into tangible designs.
Outcome:	The proposed framework incorporates four key modules: the LLM Engine, SemTypo, StyTyPo, and TexTyPO.

Copied to clipboard

Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu

Adaptive Zooming via Relevance-Informed Positional Resource Allocation for Training-free LLM Context Extension (2026.findings-acl)

Challenge:	Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback.
Approach:	They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states.
Outcome:	The proposed model outperforms baselines in faithfulness and pedagogical value.

Copied to clipboard

Hongbo Zhao, Huibin Wang, Bin Tang, Xianming Hu, Yihong Huang, Yijun Shen, Nuoyi Chen, Ping Li, Kai Zhang

Information Retrieval

Challenge:	Existing training-free methods for extrapolating beyond training context lengths are semantics-agnostic . Existing methods that focus on relative token distances can indiscriminately blur semantically relevant and irrelevant tokens .
Approach:	They propose an adaptive positional zooming method that uses semantic relevance to extrapolate beyond training context lengths.
Outcome:	Experiments show that RiPRA outperforms existing training-free extrapolation methods . relevant tokens get higher positional resolution, while irrelevant tokens are compressed .

AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Copied to clipboard

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Challenge:	Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach:	They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome:	The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.

GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)

Copied to clipboard

Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song

AMPO: Automatic Multi-Branched Prompt Optimization (2024.emnlp-main)

Challenge:	a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks.
Approach:	They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains .
Outcome:	a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively .

Copied to clipboard

Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding, Anbang Hu, Yuan Fang, Yunsong Li, Junyan Chen, Linjun Yang

Universal Information Extraction with Meta-Pretrained Self-Retrieval (2023.findings-acl)

Challenge:	Existing prompt engineering techniques are limited to producing single flow instructions, struggling with handling diverse patterns.
Approach:	They propose an automatic prompt optimization method that iteratively develops a multi-branched prompt using failure cases as feedback.
Outcome:	The proposed method achieves the best results across five tasks and demonstrates significant optimization efficiency due to adoption of a minimal search strategy.

Copied to clipboard

Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang

Semantic Text Processing

Challenge:	Existing methods for IE are task-specific, resulting in specialized and isolated approaches for different tasks.
Approach:	They propose a method to retrieve task-specific knowledge from pretrained language models to enhance universal IE by using a Meta-Pretraining Algorithm.
Outcome:	The proposed method achieves the new state-of-the-art on 4 IE tasks, 12 datasets under fully-supervised, low-resource and few-shot scenarios.

MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds (2025.emnlp-main)

Copied to clipboard

Junxi Wu, Jinpeng Wang, Zheng Liu, Bin Chen, Dongjian Hu, Hao Wu, Shu-Tao Xia

Text Generation

Challenge:	Existing methods neglect stylistic modeling and rely on static thresholds, which greatly limits the detection performance.
Approach:	They propose a framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation.
Outcome:	The proposed framework achieves an average improvement 11.34% in detection performance compared to baselines.

Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism (2020.coling-main)

Copied to clipboard

Pan Xie, Zhi Cui, Xiuying Chen, XiaoHui Hu, Jianwei Cui, Bin Wang

BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models (2023.findings-acl)

Challenge:	Existing non-autoregressive models generate target words in parallel, but with a large latency due to the left-to-right dependency.
Approach:	They propose to train a conditional masked translation model and refine results within several iterations to remedy a flawed translation by non-autoregressive models.
Outcome:	The proposed model outperforms state-of-the-art models by over 1 BLEU while using less training computations.

Copied to clipboard

Shibo Hao, Bowen Tan, Kaiwen Tang, Bin Ni, Xiyan Shao, Hengzhe Zhang, Eric Xing, Zhiting Hu

Semantic Text Processing

Challenge:	Existing methods to construct knowledge graphs are limited to a small set of relations due to manual cost or restrictions in text corpus.
Approach:	They propose to automatically construct knowledge graphs (KGs) of diverse new relations from pretrained language models that accept knowledge queries with prompts.
Outcome:	The proposed framework extracts knowledge of over 400 new relations from pretrained language models, including RoBERTaNet, with minimal input of a relation definition and a few shot of example entity pairs.

Strong Memory, Weak Control: An Empirical Study of Executive Functioning in LLMs (2026.eacl-long)

Copied to clipboard

Karin de Langis, Jong Inn Park, Bin Hu, Khanh Chi Le, Andreas Schramm, Michael C. Mensink, Andrew Elfenbein, Dongyeop Kang

MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)

Challenge:	Working memory is a critical component of human intelligence and executive functioning . it is correlated with performance on various cognitive tasks, including fluid intelligence .
Approach:	They apply working memory tasks to large language models to estimate working memory capacity . they find that LLMs exceed normative human scores, but not executive functioning benchmarks .
Outcome:	The proposed models do not show higher performance on executive functioning tasks or problem solving benchmarks.

Copied to clipboard

Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang

Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond (2025.findings-emnlp)

Challenge:	Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited.
Approach:	They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments.
Outcome:	Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning.

Copied to clipboard

Yinghao Hu, Yaoyao Yu, Leilei Gan, Bin Wei, Kun Kuang, Fei Wu

Why Can Distillation Work with Limited Resources? A Systematic Study (2026.findings-acl)

Challenge:	Experimental results show that Legal-R1 delivers competitive performance across diverse tasks.
Approach:	They propose to evaluate 12 large language models across 17 legal tasks across statutory and case-law traditions to determine their general reasoning performance.
Outcome:	The proposed model performs well across 17 legal tasks across statutory and case-law traditions.

Copied to clipboard

Xiao Hu, Xingyu Lu, Liyuan Mao, YiFan Zhang, Tianke Zhang, Bin Wen, Fan Yang, Tingting Gao, Guorui Zhou

OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework (2025.emnlp-demos)

Challenge:	Recent advances in large language models have driven reasoning performance . low-resource distillation can boost models' performance, but a framework is missing .
Approach:	They conduct a controlled experiment to find out why low-resource distillation can boost model performance . they find that distillation enhances the presence of advanced cognitive behaviors .
Outcome:	The proposed model shows more flexible reasoning, the authors show . they show that distillation enhances the presence of advanced cognitive behaviors .

Copied to clipboard

Jian Hu, Xibin Wu, Wei Shen, Jason Klein Liu, Weixun Wang, Songlin Jiang, Haoran Wang, Hao Chen, Bin Chen, Wenkai Fang, null Xianyu, Yu Cao, Haotian Xu, Yiming Liu