Papers by Han Yang

Penetrative AI: Making LLMs Comprehend the Physical World (2024.findings-acl)

Challenge:	On-policy distillation (OPD) requires expensive on-the-fly sampling of the student policy during training, which substantially increases training cost.
Approach:	They propose to use on-policy distillation to sample trajectories from student model . they propose to terminate the sampling early during distillation .
Outcome:	The proposed method matches the performance of full OPD in long reasoning outputs while reducing training FLOP by 2x–40x.

Copied to clipboard

Huatao Xu, Liying Han, Qirui Yang, Mo Li, Mani Srivastava

Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers (2026.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of tasks.
Approach:	They explore how LLMs can be extended to interact with and reason about the physical world through IoT sensors and actuators, a concept that they call "Penetrative AI".
Outcome:	The proposed approach extends LLMs' capabilities to interact with and reason about the physical world through IoT sensors and actuators.

Copied to clipboard

Van Yang, Shouren Wang, Debargha Ganguly, Xinpeng Li, Chaoda Song, Vikash Singh, Vipin Chaudhary, Xiaotian Han

Low-Resource NLP

Challenge:	Explicit /think> tags are used to expose intermediate reasoning and enable hybrid thinking behaviors.
Approach:	They propose a training-free prompting format that combines these triggers to achieve intermediate-budget reasoning, outperforming fixed-token and prompt-based baselines in terms of the accuracy–length trade-off.
Outcome:	The proposed method outperforms fixed-token and prompt-based prompts in accuracy–length trade-offs while improving Qwen3-8B on AIME from 69.8% to 72.4% and on GPQA from 58.5% to 61.1%.

CamoQuery: Language-Guided Reasoning Camouflaged Object Segmentation (2026.acl-long)

Copied to clipboard

Tianxin Han, Qing Dong, Xingwei Wang, Jie Jia, Gang Wu, Bowen Yang, Fu Zhang

Towards a Unified Multi-Dimensional Evaluator for Text Generation (2022.emnlp-main)

Challenge:	Existing methods for camouflaged object segmentation are limited to vision-only mask prediction under fixed task assumptions.
Approach:	They propose a language-guided reasoning camouflaged object segmentation task that generates an intent-consistent segmentation mask from an image and an implicit query text instruction.
Outcome:	The proposed task can generate an intent-consistent segmentation mask from a camouflaged image and an implicit query text instruction.

Copied to clipboard

Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, Jiawei Han

Text Generation

Challenge:	Existing evaluation frameworks for natural language generation are dominated by similarity-based metrics.
Approach:	They propose a multi-dimensional evaluator for natural language generation that integrates multiple dimensions into one evaluer.
Outcome:	The proposed evaluator improves on three typical NLG tasks and improves with external knowledge.

ALTER: Augmentation for Large-Table-Based Reasoning (2025.naacl-long)

Copied to clipboard

Han Zhang, Yuheng Ma, Hanfang Yang

DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation (2026.acl-long)

Challenge:	Recent studies have focused on the use of large language models (LLMs) for table-based reasoning, but most approaches struggle with scalability when applied to large tables.
Approach:	They propose a framework to harness latent augmentation potential in tabular data . they use only a small subset of relevant data from the table to supplement it with schema .
Outcome:	The proposed framework outperforms all other approaches and exhibits robustness and efficiency against perturbations in large-table scenarios.

Copied to clipboard

Boyu Guan, Chuang Han, Yang Zhao, Chengqing Zong

Second-Order Unsupervised Neural Dependency Parsing (2020.coling-main)

Challenge:	Video-guided Machine Translation (VMT) uses short video clips to enhance translation quality, but many samples are text-sufficient.
Approach:	They propose a framework that integrates multimodal large language models’ multimodal reasoning into video-guided machine translation by using a pipeline for constructing training data based on multimodal relevance to translation.
Outcome:	The proposed framework improves multimodal information utilization in video-guided machine translation, yielding gains in translation quality and computational efficiency.

Copied to clipboard

Songlin Yang, Yong Jiang, Wenjuan Han, Kewei Tu

SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation (2025.emnlp-main)

Challenge:	supervised dependency parsers can reach a very high accuracy, but they require treebanks for training.
Approach:	They propose a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information.
Outcome:	The proposed model achieves 10% improvement over the previous state-of-the-art model on the full WSJ dataset.

Copied to clipboard

Boyu Guan, Chuang Han, Yining Zhang, Yupu Liang, Zhiyang Zhang, Yang Zhao, Chengqing Zong

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)

Challenge:	Video-guided machine translation (VMT) aims to improve translation quality by integrating contextual information from paired short video clips.
Approach:	They propose a plug-and-play framework for video-guided machine translation with multimodal large language models.
Outcome:	The proposed framework improves performance of MLLMs while reducing computational cost.

Copied to clipboard

Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)

Challenge:	Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored.
Approach:	They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs.
Outcome:	The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs.

Copied to clipboard

Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs (2025.findings-acl)

Challenge:	Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy.
Approach:	They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges.
Outcome:	The proposed framework reduces retrieval time while maintaining high model performance.

Copied to clipboard

Hongming Yang, Shi Lin, Jun Shao, Changting Lin, Donghai Zhu, Meng Han, Qinglei Kong

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning (2025.findings-acl)

Challenge:	Existing prompt optimization methods rely on extensive manual effort or meta-cognitive abilities, making them less effective for LwLLMs.
Approach:	They propose a direct behavior optimization parameter that transforms the optimization of complex prompts into discrete, quantifiable execution sequences using a gradient-free Monte Carlo Tree Search.
Outcome:	The proposed method outperforms current prompt optimization methods on seven challenging tasks where state-of-the-art LLMs excel but LwLLMs generally underperform.

Copied to clipboard

Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Challenge:	Large Language Models (LMMs) struggle with simple tasks such as geometry, e.g., arithmetic, and reasoning.
Approach:	They propose to leverage code as supervision for cross-modal alignment . they propose to use FigCodifier and ImgCode-8.6M to synthesize novel mathematical figures .
Outcome:	The proposed model surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%.

Copied to clipboard

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin

Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training (2025.naacl-long)

Challenge:	Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach:	They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome:	The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)

Copied to clipboard

Sun Ao, Weilin Zhao, Xu Han, Cheng Yang, Xinrong Zhang, Zhiyuan Liu, Chuan Shi, Maosong Sun

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)

Challenge:	Current PP methods face severe bottlenecks, including pipeline bubbles and memory footprint.
Approach:	They propose a sequence-level one-forward-one-backward (1F1B) PP method for training LLMs on long sequences with high throughput and memory efficiency.
Outcome:	The proposed method achieves 1.14X training throughput with half memory footprint compared to baseline methods . it trains an LLM with 30B parameters on sequences up to 64k tokens using 64X NVIDIA A100 GPUs .

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020.aacl-main)

Challenge:	Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters.
Approach:	They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety.
Outcome:	The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings.

Copied to clipboard

Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Jie Zhou, Maosong Sun

Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection (2024.lrec-main)

Challenge:	Existing methods for extracting relational facts from text have been successful . but with explosion of Web text, human knowledge is increasing drastically .
Approach:	They propose to improve relation extraction methods to extract relational facts from text . they analyze existing methods and show promising directions towards more powerful RE .
Outcome:	The proposed methods can extract relational facts from text, but they are still lacking in the current field.

Copied to clipboard

Chuanpeng Yang, Fuqing Zhu, Yaxin Liu, Jizhong Han, Songlin Hu

ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language Models (2026.findings-acl)

Challenge:	Existing methods for detecting hate speech ignore misalignment and uncertainty between modalities . social media platforms have become conduits for the rapid dissemination of hate speech .
Approach:	They propose an uncertainty-aware cross-modal alignment framework for hate speech detection that minimizes the misalignment of image and text in memes.
Outcome:	The proposed framework produces a competitive performance compared with existing methods.

Copied to clipboard

Zhuowen Han, Lei Yang, Renren Jin, Dan Shi, Chenxi Sun, Deyi Xiong

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values (2025.emnlp-main)

Challenge:	Existing efforts to improve reasoning efficiency of large language models focus on modifying the reinforcement learning reward, such as adding length penalties.
Approach:	They propose a training framework that elicits efficient reasoning through reasoning vectors and a framework that allows the model to generate high-quality responses during reinforcement learning.
Outcome:	The proposed framework reduces reasoning length by 30% while maintaining stability, while retaining high accuracy.

Copied to clipboard

Hongbo Zhang, Han Cui, Guangsheng Bao, Linyi Yang, Jun Wang, Yue Zhang

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Challenge:	Existing offline preference optimization methods rely on preference labels to optimize large language models.
Approach:	They propose an offline method for enhancing large language models in reasoning tasks that utilizes value signals at individual reasoning steps.
Outcome:	The proposed framework outperforms offline preference optimization techniques by 4% to 6% on math reasoning, commonsense reasoning, and coding tasks.

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum

Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning (2024.acl-long)

Challenge:	Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window.
Approach:	They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window.
Outcome:	The proposed model scales to multi-million-token effective TTC without exceeding context limits.

Copied to clipboard

Zhaorui Yang, Tianyu Pang, Haozhe Feng, Han Wang, Wei Chen, Minfeng Zhu, Qian Liu

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding (2021.acl-long)

Challenge:	Experimental results show that fine-tuning of large language models for specific tasks can be challenging . distribution shift during fine-timing can lead to performance degradation in general task capabilities .
Approach:	They propose a new approach that bridges the distribution gap between task datasets and LLMs by guiding fine-tuning with a distilled dataset generated by the model itself.
Outcome:	The proposed approach achieves comparable or superior performance on downstream tasks compared to the vanilla approach.

Copied to clipboard

Shan Wu, Bo Chen, Chunlei Xin, Xianpei Han, Le Sun, Weipeng Zhang, Jiansong Chen, Fan Yang, Xunliang Cai

Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval (2025.findings-acl)

Challenge:	Experimental results show that Synchronous Semantic Decoding (SSD) can achieve state-of-the-art unsupervised semantic parsing performance on multiple datasets.
Approach:	They propose an unsupervised method which solves the semantic gap and the structure gap by leveraging paraphrasing and grammar-constrained decoding.
Outcome:	The proposed method can solve the semantic gap and structure gap on multiple datasets.

Copied to clipboard

Yubai Wei, Jiale Han, Yi Yang

Representation Learning

Challenge:	Text embedding models show strong performance on generic benchmarks, but their effectiveness diminishes when applied to private datasets.
Approach:	They propose a method for adapting general-purpose text embedding models to private datasets . they construct supervisory signals from the ranking of keyword-based retrieval results .
Outcome:	The proposed method improves retrieval performance across domains, datasets, and models.

TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification (2025.acl-long)

Copied to clipboard

Yindu Su, Huike Zou, Lin Sun, Ting Zhang, Haiyang Yang, Chen Li Yu, David Lo, Qingheng Zhang, Shuguang Han, Jufeng Chen

pEBR: A Probabilistic Approach to Embedding Based Retrieval (2025.emnlp-industry)

Challenge:	Existing methods for product attribute value identification face critical challenges . seller-provided attribute values are often incomplete or inaccurate .
Approach:	They propose a retrieval-based method that uses taxonomy-aware contrastive learning . they use product profiles and candidate values to encode and retrieve attributes based on similarity .
Outcome:	The proposed method is based on a taxonomy-aware, hard negative sampling and adaptive inference with dynamic thresholds.

Copied to clipboard

Han Zhang, Yunjiang Jiang, Mingming Li, Haowei Yuan, Yiming Qiu, Wen-Yun Yang

Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration (2026.eacl-long)

Challenge:	Existing embedding-based retrieval systems rely on heuristic and suboptimal cutoffs for item retrieval.
Approach:	They propose a probabilistic Embedding-Based Retrieval framework that learns a shared semantic representation space for both queries and items.
Outcome:	The proposed framework improves retrieval precision and recall, and ablation studies show it captures the differences between head-to-tail queries.

Copied to clipboard

Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng, Xianpei Han

Linguistics & Cognitive NLP

Challenge:	Existing methods for dynamic web navigation rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models.
Approach:	They propose a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration.
Outcome:	The proposed framework surpasses the proprietary model Claude-3.5 Sonnet on the WebArena benchmark.

Selective Test-Time Debiasing for CLIP via Reward Gating (2026.acl-long)

Copied to clipboard

Jaeho Han, Jisoo Yang, Hyeondong Woo, Mingyu Jeon, Sunjae Yoon, Junyeong Kim

Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty? (2025.findings-emnlp)

Challenge:	Existing methods for debiasing use uniform bias corrections across all input queries . weak debiases retains bias in sensitive queries, while weak dealiases in biased ones .
Approach:	They propose a framework that selectively applies debiasing based on input sensitivity . RG-TTA adaptively triggers fairness regularization based upon bias sensitivity of each input .
Outcome:	Experiments show that debiasing improves zero-shot performance while maintaining fairness . weak debiased queries distort semantically meaningful information while weak ones fail to mitigate stereotypes .

Copied to clipboard

Yang Nan, Pengfei He, Ravi Tandon, Han Xu

Challenge:	Large language models can produce unreliable or misleading outputs, posing challenges for real-world applications.
Approach:	They employ an auxiliary LLM to analyze the patterns of disagreement among LLMs . they validate their framework on AmbigQA, OpenBookQA, and MMLU-Pro .
Outcome:	The proposed model can be used to diagnose uncertainty sources in a model with an auxiliary model.

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

DynaMiTE: Discovering Explosive Topic Evolutions with User Guidance (2023.findings-acl)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Nishant Balepur, Shivam Agarwal, Karthik Venkat Ramanan, Susik Yoon, Diyi Yang, Jiawei Han

Topic Modeling

Challenge:	Existing Dynamic topic models are either fully supervised, requiring expensive human annotations, or fully unsupervised, producing topic evolutions that often do not cater to a user’s needs.
Approach:	They propose to use a framework that ensembles semantic similarity, category indicative, and time indicative scores to produce informative topic evolutions.
Outcome:	The proposed framework can be used to discover topic evolutions from temporal corpora that align with user-provided category names and uniquely capture topics at each time step.

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (2023.emnlp-main)

Copied to clipboard

Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have produced models that exhibit remarkable performance across a variety of NLP tasks.
Approach:	They analyze a large-scale collection of user-GPT conversations to identify a significant gap between academic research in NLP and the needs of real-world NLP applications.
Outcome:	The proposed model outperforms existing models in a large-scale collection of user-GPT conversations and identifies a significant gap between the tasks that users frequently request from LLMs and the tasks commonly studied in academic research.

Copied to clipboard

Dongjie Yang, Xiaodong Han, Yan Gao, Yao Hu, Shilin Zhang, Hai Zhao

Challenge:	Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation.
Approach:	They propose a method that compresses the KV cache by layer-wise retaining crucial context.
Outcome:	The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction .

Language Model is Suitable for Correction of Handwritten Mathematical Expressions Recognition (2023.emnlp-main)

Copied to clipboard

Zui Chen, Jiaqi Han, Chaofan Yang, Yi Zhou

CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers (2024.acl-long)

Challenge:	Existing approaches to handwritten mathematical expression recognition are limited by CFGs and pre-generated triplet data.
Approach:	They propose an architecture that integrates recognition and language features to output corrected sequences while optimizing with a string decoder recognition model.
Outcome:	The proposed architecture outperforms state-of-the-art methods on CROHME datasets.

Copied to clipboard

Longwei Zou, Qingyang Wang, Han Zhao, Jiangangkong Jiangangkong, Yi Yang, Yangdong Deng

GSID: Generative Semantic Indexing for E-Commerce Product Understanding (2025.emnlp-industry)

Challenge:	Existing methods to improve inference efficiency target to reduce per-layer latency, but ignore cumulative latency due to number of layers.
Approach:	They propose to identify quasi-independent layers that can be concurrently computed to significantly decrease inference latency.
Outcome:	Empirical results show that the proposed method reduces latency by 48.3% on LLaMA-33B while maintaining close level of performance.

Copied to clipboard

Haiyang Yang, Qinye Xie, Qingheng Zhang, Chen Li Yu, Huike Zou, Chengbao Lian, Shuguang Han, Fei Huang, Jufeng Chen, Bo Zheng

Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)

Challenge:	Structured product information is a major bottleneck for the efficiency of e-commerce platforms.
Approach:	They propose a data-driven approach to generate product structured representations using product metadata.
Outcome:	Extensive experiments show that GSID can generate better product representations on real-world e-commerce platforms.

Copied to clipboard

Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han

Challenge:	Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents.
Approach:	They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation.
Outcome:	Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks.

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Copied to clipboard

Junxiao Yang, Haoran Liu, Jinzhe Tu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Jiaqi Weng, Jialing Tao, Hui Xue, Hongning Wang, Han Qiu, Minlie Huang

Challenge:	Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach:	They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome:	The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).

Towards Database-Free Text-to-SQL Evaluation: A Graph-Based Metric for Functional Correctness (2025.coling-main)

Copied to clipboard

Yi Zhan, Longjie Cui, Han Weng, Guifeng Wang, Yu Tian, Boyi Liu, Yingxiang Yang, Xiaoming Yin, Jiajun Xie, Yang Sun

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection (2026.eacl-long)

Challenge:	Existing metrics for evaluating functional correctness of SQL queries are prone to false positives due to inadequately prepared test databases.
Approach:	They propose a graph-based metric that uses a relational operator tree to extract rich semantic information from the logical execution plan of SQL queries and embed it into a diagram.
Outcome:	The proposed method eliminates the need for extensive test database preparation and performs graph matching on unseen SQL queries.

Copied to clipboard

Yuhang Liu, Pengxiang Li, Zishu Wei, Congkai Xie, Xueyu Hu, Xinchen Xu, Shengyu Zhang, Xiaotian Han, Hongxia Yang, Fei Wu

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification (P19-1)

Challenge:	Existing GUI Agents face challenges in multi-step reasoning and reliance on textual annotations, limiting their effectiveness.
Approach:	They propose an MLLM-based GUI Agent with a two-stage supervised fine-tuning pipeline that enhances GUI understanding and grounding.
Outcome:	InfiGUIAgent achieves competitive performance on several GUI benchmarks, highlighting the impact of native reasoning skills in enhancing GUI interaction for automation tasks.

Copied to clipboard

Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun

RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)

Challenge:	Existing methods to extract information from evidence are unable to grasp relational and logical information among the evidence.
Approach:	They propose a graph-based evidence aggregating and reasoning framework to integrate evidence from multiple pieces of evidence.
Outcome:	The proposed framework achieves significant performance improvements on a large-scale benchmark dataset.

Copied to clipboard

Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun

MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering (2025.findings-acl)

Challenge:	Existing benchmarks focus on character-centric approach and fail to reflect real-world applications.
Approach:	RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.
Outcome:	RMTBench features 80 diverse characters and over 8,000 dialogue rounds.

Copied to clipboard

Shuo Yang, Caren Han, Siwen Luo, Eduard Hovy

Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)

Challenge:	Existing Large Vision-Language Models (LVLMs) lack integrated commonsense knowledge . lack of integrated common knowledge limits their robustness and accuracy in VQA .
Approach:	They propose a framework to enhance multimodal inference by integrating commonsense reasoning.
Outcome:	MAGIC-VQA improves comprehensive benchmark datasets, surpassing existing models in tasks requiring advanced commonsense reasoning.

Copied to clipboard

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

Improving Conversational Recommendation Systems’ Quality with Context-Aware Item Meta-Information (2022.findings-naacl)

Challenge:	Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.
Approach:	They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities.
Outcome:	The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict.

Copied to clipboard

Bowen Yang, Cong Han, Yu Li, Lei Zuo, Zhou Yu

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning (2025.emnlp-main)

Challenge:	Existing approaches to integrate the recommendation function and dialog generation function smoothly are lacking.
Approach:	They propose to integrate dialog context for recommendation and dialog generation better using a pre-trained language model and an item metadata encoder to integrate the recommendation and dialogue generation.
Outcome:	The proposed architecture improves the integration of recommendation and dialog generation functions.

Copied to clipboard

Yunhao Gou, Hansi Yang, Zhili Liu, Kai Chen, Yihan Zeng, Lanqing Hong, Zhenguo Li, Qun Liu, Bo Han, James Kwok, Yu Zhang

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)

Challenge:	Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), but its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content and poor OCR quality.
Approach:	They propose a corruption-robust training paradigm that surpasses existing strategies for mitigating the effects of corrupted data.
Outcome:	The proposed training paradigm surpasses existing strategies for mitigating the effects of corrupted data.

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

LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)

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.

Copied to clipboard

Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang

CSP:Code-Switching Pre-training for Neural Machine Translation (2020.emnlp-main)

Challenge:	LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases .
Approach:	They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website .
Outcome:	The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks.

Copied to clipboard

Zhen Yang, Bojie Hu, Ambyera Han, Shen Huang, Qi Ju

Multilinguality

Challenge:	Existing methods to train neural machine translation models are data-hungry and low-resource . et al., 2018; Radford e.t., 2019; Yang ee.,2019) proposes a new pre-training method for NMT .
Approach:	They propose a new pre-training method which randomly replaces some words in the input sentence with their translation words in target language.
Outcome:	The proposed method improves on unsupervised and supervised NMT models by making full use of monolingual corpora.

Topic-Oriented Open Relation Extraction with A Priori Seed Generation (2024.emnlp-main)

Copied to clipboard

Linyi Ding, Jinfeng Xiao, Sizhe Zhou, Chaoqi Yang, Jiawei Han

Retrieval Enhanced Model for Commonsense Generation (2021.findings-acl)

Challenge:	Existing methods for open relation extraction give sub-optimal results on specific topics.
Approach:	They propose a method that leverages the built-in knowledge of large language models to maintain a dynamic seed relation dictionary for the topic.
Outcome:	The proposed approach empowers better topic-oriented control over the generated relations and improves ORE performance along the five dimensions, especially on specialized and narrow topics.

Copied to clipboard

Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants’ API Invocation Capabilities (2024.lrec-main)

Challenge:	Existing frameworks for commonsense generation are lacking for pre-trained models.
Approach:	They propose a framework that uses concept matching to retrieve prototype sentences and trainable sentence retriever to enhance pre-training and fine-tuning.
Outcome:	The proposed framework achieves state-of-the-art on the large-scale Common-Gen benchmark.

Copied to clipboard

Honglin Mu, Yang Xu, Yunlong Feng, Xiaofeng Han, Yitong Li, Yutai Hou, Wanxiang Che

Challenge:	Existing evaluation methods for human-machine interactions are static and can be misleading.
Approach:	They propose to use a LLM-based user agent to assess an assistant's API call capability without human involvement.
Outcome:	The proposed method mirrors real human conversation patterns in human-machine interactions, and shows that it aligns more closely with human assessment.

Logits-Based Finetuning (2025.emnlp-main)

Copied to clipboard

Jingyao Li, Senqiao Yang, Sitong Wu, Han Shi, Chuanyang Zheng, Hong Xu, Jiaya Jia

Covariance Matrix-Driven Image Channel Allocation for Multimodal Fake News Detection (2026.findings-acl)

Challenge:	Existing methods for developing compact and efficient large language models lack token-level dependencies and linguistic diversity.
Approach:	They propose a logits-based fine-tuning framework that integrates supervised learning and knowledge distillation to build enriched training targets using teacher logits and ground truth labels.
Outcome:	The proposed method outperforms existing methods on a large-scale logits dataset and a series of science-focused models.

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Yan Song, Dong Yu, Wang Min

Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs (2026.acl-long)

Challenge:	Existing methods focus on designing efficient multimodal fusion frameworks to bridge the semantic gap between images and texts.
Approach:	They propose a covariance matrix-driven image channel allocation method that expands the number of original channel maps and assigns importance scores to the expanded channel maps.
Outcome:	The proposed method achieves state-of-the-art on three public multimodal fake news detection benchmark datasets.

Copied to clipboard

Binxing Xu, Hao Gu, Lujun Li, Hao Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Xintong Yang, Chao Li, Sirui Han, Yike Guo

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning (2025.emnlp-main)

Challenge:	Existing approaches to training LLMs at ultra-low precisions suffer from convergence instability and substantial training costs.
Approach:	They propose a progressive QAT framework with outlier channel splitting to address these issues . they use nested structure of integer quantization grids to enable a "train once, deploy any precision" paradigm .
Outcome:	The proposed framework outperforms baselines on both Llama2/3 and W2A16, with an 11 speedup over BF16.

Copied to clipboard

Jingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao

A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)

Challenge:	Existing reward models assume a global reward function, limiting personalization and pluralistic alignment.
Approach:	They propose a framework that leverages binary preference datasets to enhance personalized preference learning.
Outcome:	The proposed framework captures diverse human preferences without fine-grained annotations and significantly improves personalized preference learning on downstream tasks.

Copied to clipboard

Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Challenge:	Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs .
Approach:	They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding .
Outcome:	The proposed model shows an increase in performance in KIE and VQA tasks.

Copied to clipboard

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents (2025.acl-long)

Challenge:	Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach:	They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome:	The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.

Copied to clipboard

Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji

GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking (2025.acl-long)

Challenge:	Existing language model agents excel in planning and reasoning, but lack creativity in unfamiliar environments.
Approach:	They propose a benchmark suite of room escape game environments to challenge agents with creative reasoning, unconventional tool use and iterative problem-solving to uncover implicit goals.
Outcome:	The proposed framework can perform with 40% fewer steps and hints and performs robustly across difficulty levels.

Copied to clipboard

Yingjian Chen, Haoran Liu, Yinhong Liu, Jinxiang Xie, Rui Yang, Han Yuan, Yanran Fu, Peng Yuan Zhou, Qingyu Chen, James Caverlee, Irene Li

Structured Data in NLP

Challenge:	Existing fact-checking methods that use large language models often generate subtle factual errors.
Approach:	They propose a fact-checking framework that uses extracted knowledge graphs to enhance text representation.
Outcome:	GraphCheck outperforms existing specialized fact-checkers on seven benchmarks spanning general and medical domains . Graph Neural Networks process extracted knowledge graphs as a soft prompt, enabling efficient fact- checking in a single inference call.

Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)

Copied to clipboard

Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li

DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification (2022.coling-1)

Challenge:	Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization .
Approach:	They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume.
Outcome:	Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency.

Copied to clipboard

Hui Chen, Wei Han, Diyi Yang, Soujanya Poria

What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma (2025.acl-long)

Challenge:	Existing methods to improve the robustness of text classification models are token-, sentence-, and hiddenlevel augmentation.
Approach:	They propose an interpolation-based data augmentation approach called DoubleMix to improve the robustness of text classification models by learning the “shifted” features in hidden space.
Outcome:	The proposed approach outperforms several popular methods on six text classification benchmark datasets and visual analysis shows that the model features are highly interpretable.

Copied to clipboard

Han Meng, Yancan Chen, Yunan Li, Yitian Yang, Jungup Lee, Renwen Zhang, Yi-Chieh Lee

Linguistic Theories

Challenge:	Existing resources for training neural models to finely classify mental-health stigma are limited, relying primarily on social media or synthetic data without theoretical underpinnings.
Approach:	They propose to use an expert-annotated corpus of human-chatbot interviews to finely classify mental-health stigma.
Outcome:	The proposed corpus can facilitate research on computationally detecting, neutralizing, and counteracting mental-health stigma.

SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction (2022.naacl-main)

Copied to clipboard

Yuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, Jiawei Han

Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models (2026.findings-acl)

Challenge:	Existing methods for relation extraction only implicitly learn to model relevant contexts and entity types while being trained for RE.
Approach:	They propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for RE.
Outcome:	The proposed method outperforms the runner-up method on three benchmarks by 5.04% . textual contexts and entity types are the major information sources that lead to the success of previous approaches.

Copied to clipboard

Bajian Xiang, Tingwei Guo, Xuan Chen, Yang Han

Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)

Challenge:	Large Speech Language Models (LSLMs) typically operate at high token rates to ensure acoustic fidelity, yet this results in sequence lengths that exceed the underlying semantic content, incurring prohibitive inference costs.
Approach:	They propose a token-based token merging mechanism that uses a training-free token pooling mechanism to reduce prefilling FLOPs by 27.48% while maintaining competitive accuracy.
Outcome:	The proposed method reduces prefilling FLOPs by 27.48% while maintaining competitive accuracy.

Copied to clipboard

Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong

Challenge:	Existing evaluation methods are inadequate to evaluate large language models (LLMs).
Approach:	They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models.
Outcome:	The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results.

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings (2025.findings-acl)

Copied to clipboard

Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu

MSIA: Adaptive Medical Multimodal Multi-turn Semantic Jailbreak (2026.findings-acl)

Challenge:	Recent studies show that character substitutions in toxic Chinese text can confuse state-of-the-art LLMs.
Approach:	They propose a taxonomy of 3 perturbation strategies and 8 specific approaches in Chinese text to assess if they can detect perturbed Chinese toxic contents.
Outcome:	The proposed model can detect perturbed Chinese text with 8 different approaches . the proposed model is compared with 9 other LLMs from the US and China .

Copied to clipboard

Zhiheng Han, Yao Zhang, Jun Wang, Zhenglu Yang

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)

Challenge:	Medical large language models exhibit high domain specificity and condensed semantics, making them vulnerable to diagnostic errors in real-world clinical settings.
Approach:	They propose a framework for modeling and inducing multi-turn medical semantic jailbreaks in clinical dialogues.
Outcome:	Experiments on chest X-ray-based multimodal medical dialogues show that MSIA outperforms existing jailbreak methods with an average success rate of 76.67%.

Copied to clipboard

Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen

Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio (2026.acl-long)

Challenge:	Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models.
Approach:	They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model.
Outcome:	The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD.

Copied to clipboard

Kaixiong Gong, Kaituo Feng, Bohao Li, Yibing Wang, Mofan Cheng, Shijia Yang, Jiaming Han, Benyou Wang, Yutong Bai, Zhuoran Yang, Xiangyu Yue

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)

Challenge:	Recent multimodal large language models lack robust audio-visual integration ability and performance on DeafTest is highly correlated with AV-Odyssey accuracy.
Approach:	They propose a benchmarking tool that integrates audio-visual reasoning with audio-video cues to infer solutions.
Outcome:	The proposed model performs well on DeafTest, but lacks audio perception in simple audio tasks.

Copied to clipboard

Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong

Grounding Agent Memory in Contextual Intent (2026.findings-acl)

Challenge:	Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages.
Approach:	They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English.
Outcome:	The proposed model outperforms open-source and Tibetan-focused models on diverse tasks.

Copied to clipboard

Ruozhen Yang, Yucheng Jiang, Yueqi Jiang, Priyanka Kargupta, Yunyi Zhang, Jiawei Han

MedTem2.0: Prompt-based Temporal Classification of Treatment Events from Discharge Summaries (2023.acl-srw)

Challenge:	Large language models are deployed in long-horizon tasks that require agents to track interleaved goals, resolve references to prior information, and coordinate actions over extended trajectories.
Approach:	They propose an agentic memory system that indexes each trajectory step with a structured retrieval cue, contextual intent, and retrieves history by matching the current step’s intent.
Outcome:	The proposed system outperforms the strongest benchmark by 35.6%, with the largest gains as trajectory length increases.

Copied to clipboard

Yang Cui, Lifeng Han, Goran Nenadic

Compositional Data Augmentation for Abstractive Conversation Summarization (2023.acl-long)

Challenge:	Clinical texts contain important temporal information, such as medication start and end dates, appointment dates, and diagnosis dates.
Approach:	They propose to use prompt-based learning and fine-tuning to classify temporal relations between treatments and hospitalisation periods in discharge summaries.
Outcome:	The proposed method identifies whether a treatment was administered between the time of admission and discharge from the hospital.

Copied to clipboard

Siru Ouyang, Jiaao Chen, Jiawei Han, Diyi Yang

SafeMT: Multi-turn Safety for Multimodal Language Models (2026.acl-long)

Challenge:	Abstractive conversation summarization systems rely on large-scale annotated summaries, but collecting and annotating these conversations can be time-consuming and labor-intensive.
Approach:	They propose a method for generating diverse and high-quality pairs of conversations and summaries by extracting conversation structures and organizing meaningful conversation snippets.
Outcome:	The proposed method outperforms baseline methods on SAMSum and DialogSum datasets and achieves a 10% increase in ROUGE scores with limited data.

Copied to clipboard

Han Zhu, Juntao Dai, Jiaming Ji, Haoran Li, Chengkun Cai, Pengcheng Wen, Chi-Min Chan, Boyuan Chen, Yaodong Yang, Sirui Han, Yike Guo

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Challenge:	Multi-turn dialogues pose a greater risk than single prompts, but existing safety benchmarks do not account for this situation.
Approach:	They propose a benchmark that features dialogues of varying lengths generated from harmful queries accompanied by images.
Outcome:	The proposed model reduces multi-turn Attack Success Rate (ASR) compared to existing guard models.

Copied to clipboard

Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun

Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation (2025.findings-acl)

Challenge:	Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach:	They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome:	The proposed framework improves performance of commercial and open-source models.

Copied to clipboard

Hongji Yang, Yucheng Zhou, Wencheng Han, Jianbing Shen

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)

Challenge:	Existing methods for rewriting text-to-image models require specialized vocabulary . a new approach uses large vision language models to optimize text-based models .
Approach:	They propose a prompt optimization framework that rephrases a user prompt into a text-to-image model by using large vision language models as solver and reward model.
Outcome:	The proposed model outperforms existing models on two popular datasets.

Copied to clipboard

Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao

InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model (2024.findings-acl)

Challenge:	Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications.
Approach:	They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions.
Outcome:	The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions.

Copied to clipboard

Haogeng Liu, Quanzeng You, Yiqi Wang, Xiaotian Han, Bohan Zhai, Yongfei Liu, Wentao Chen, Yiren Jian, Yunzhe Tao, Jianbo Yuan, Ran He, Hongxia Yang

EventPlus: A Temporal Event Understanding Pipeline (2021.naacl-demos)

Challenge:	InfiMM is a multimodal large language model that adapts to complex vision-language tasks.
Approach:	They present a Multimodal Large Language Model that adapts to intricate vision-language tasks using large-scale training data and comprehensive training strategies.
Outcome:	Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding.

Copied to clipboard

Mingyu Derek Ma, Jiao Sun, Mu Yang, Kung-Hsiang Huang, Nuan Wen, Shikhar Singh, Rujun Han, Nanyun Peng

RRADistill: Distilling LLMs’ Passage Ranking Ability for Long-Tail Queries Document Re-Ranking on a Search Engine (2024.emnlp-industry)

Challenge:	Event information is a type of common sense knowledge that helps people understand how stories evolve and provides predictive hints for future events.
Approach:	They propose a temporal event understanding pipeline that integrates state-of-the-art components.
Outcome:	The proposed pipeline can be easily adapted to other domains, including biomedical domains.

Copied to clipboard

Nayoung Choi, Youngjune Lee, Gyu-Hwung Cho, Haeyu Jeong, Jungmin Kong, Saehun Kim, Keunchan Park, Sarah Cho, Inchang Jeong, Gyohee Nam, Sunghoon Han, Wonil Yang, Jaeho Choi

Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media (2025.emnlp-main)

Challenge:	Large Language Models excel at understanding the semantic relationships between queries and documents, even with lengthy and complex long-tail queries.
Approach:	They propose an efficient label generation pipeline and novel sLLM training methods for both encoder and decoder models.
Outcome:	The proposed method improves re-ranking for long-tail queries on a Korean-based search platform.

Copied to clipboard

Yujie Wang, Yunwei Zhao, Jing Yang, Han Han, Shiguang Shan, Jie Zhang

Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA (2025.findings-acl)

Challenge:	Digital media platforms often contribute to cognitive-behavioral fixation, a phenomenon in which users exhibit sustained and repetitive engagement with narrow content domains.
Approach:	They propose a multimodal topic extraction module and a cognitive-behavioral fixation quantification module that collaboratively enable adaptive, hierarchical, and interpretable assessment of user behavior.
Outcome:	The proposed framework lays the groundwork for scalable computational analysis of cognitive fixation.

Copied to clipboard

Chi-Min Chan, Chunpu Xu, Junqi Zhu, Jiaming Ji, Donghai Hong, Pengcheng Wen, Chunyang Jiang, Zhen Ye, Yaodong Yang, Wei Xue, Sirui Han, Yike Guo

Question Answering

Challenge:	Experimental results show that our approach can effectively improve the performance of both the policy model and the reward model.
Approach:	They propose to use Monte Carlo Tree Search for both policy model improvement and reward model improvement to bridge it to more subtle open-domain question answering.
Outcome:	The proposed approach surpasses existing methods for annotation and training data with fewer data points and achieves better performance in test-time scaling strategies.

Adversarial Attack against Cross-lingual Knowledge Graph Alignment (2021.emnlp-main)

Copied to clipboard

Zeru Zhang, Zijie Zhang, Yang Zhou, Lingfei Wu, Sixing Wu, Xiaoying Han, Dejing Dou, Tianshi Che, Da Yan

Robustness in NLP

Challenge:	Existing studies on cross-lingual entity alignment under adversarial attacks have not been conducted.
Approach:	They propose to use adversarial attack techniques to perturb cross-lingual entity alignment under adversarials.
Outcome:	The proposed model hides the attacked entities in dense regions in two KGs, and reduces the gradient vanishing issues in the process of adversarial attacks for further improving the attack effectiveness.

Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking (2025.findings-emnlp)

Copied to clipboard

Yunyi Zhang, Ruozhen Yang, Siqi Jiao, SeongKu Kang, Jiawei Han

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)

Challenge:	Recent studies also use large language models (LLMs) for query understanding, but these methods lack grounding in corpus-specific knowledge and may generate unreliable or unfaithful content.
Approach:	They propose a paper retrieval framework that combines large language models (LLMs) with a concept-based semantic index to capture scientific concepts.
Outcome:	The proposed framework improves the performance of various base retrievers, surpasses strong existing LLM-based baselines, and remains highly efficient.

Copied to clipboard

Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, Tong Zhang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences.
Approach:	They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles.
Outcome:	The proposed method improves performance across reward objectives and targets.

GAMEBoT: Transparent Assessment of LLM Reasoning in Games (2025.acl-long)

Copied to clipboard

Wenye Lin, Jonathan Roberts, Yunhan Yang, Samuel Albanie, Zongqing Lu, Kai Han

Robust and Scalable Model Editing for Large Language Models (2024.lrec-main)

Challenge:	Existing efforts to create benchmarks that move beyond superficial pattern recognition to delve into the profound reasoning skills required for problemsolving face challenges such as insufficient interpretability, performance saturation or data contamination.
Approach:	They propose a gaming arena designed for rigorous assessment of LLM reasoning capabilities.
Outcome:	The proposed framework decomposes complex reasoning into predefined modular subproblems and generates ground truth for these subproblem types.

Copied to clipboard

Yingfa Chen, Zhengyan Zhang, Xu Han, Chaojun Xiao, Zhiyuan Liu, Chen Chen, Kuai Li, Tao Yang, Maosong Sun

TOXIFRENCH: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection (2026.findings-acl)

Challenge:	Existing methods that ignore contextual knowledge fail to reliably fall back to parametric knowledge when presented with irrelevant context.
Approach:	They propose to use contextual knowledge to update and correct LLMs' knowledge by in-context editing instead of retraining.
Outcome:	The proposed method outperforms current state-of-the-art methods by a large margin on a dataset that contains irrelevant questions.

Copied to clipboard

Axel Delaval, Shujian Yang, Haicheng Wang, Han Qiu, Jialiang LU

Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL (2026.findings-acl)

Challenge:	toxicity detection in French remains underdeveloped due to the lack of culturally relevant, human-annotated, large-scale datasets.
Approach:	They propose a method that generalizes French online comments using a semi-automated annotation pipeline that reduces manual labeling to only 10% through high-confidence LLM-based pre-annotation and human verification.
Outcome:	The proposed model outperforms GPT-4o and DeepSeek-R1 on the benchmark while maintaining cross-lingual capabilities.

Copied to clipboard

Yang Zerui, Weichuan Wang, Yanwei Xu, Linqi Song, Yudai Matsuda, Wei Han, Bo Bai

Programming Languages in NLP

Challenge:	Existing NL2SQL systems rely on in-context learning with only correct examples . current test-time scaling methods often decompose questions arbitrarily, resulting in poor performance .
Approach:	They propose a structured decomposition and experience-aware self-correction framework for NL2SQL . they build a dynamic memory of successful queries and historical error–fix pairs .
Outcome:	The proposed framework achieves 68.5% execution accuracy on BIRD, setting new state of the art among open, zero-fine-tuning methods.

A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings (2022.findings-acl)

Copied to clipboard

Haochen Tan, Wei Shao, Han Wu, Ke Yang, Linqi Song

HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)

Challenge:	Existing approaches to contrastive learning are heavily affected by superficial features like sentence length and syntax.
Approach:	They propose a semantic-aware contrastive learning framework for sentence embeddings that explores the pseudo-token space representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax.
Outcome:	The proposed framework outperforms the state-of-the-art on six standard semantic textual similarity tasks while maintaining an additional queue to store the representation of sentence embeddings.

Copied to clipboard

An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu

An LLM-based Temporal-spatial Data Generation and Fusion Approach for Early Detection of Late Onset Alzheimer’s Disease (LOAD) Stagings Especially in Chinese and English-speaking Populations (2025.findings-emnlp)

Challenge:	Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization.
Approach:	They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts .
Outcome:	The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters.

Copied to clipboard

Yang Han, Jacqueline C.k. Lam, Victor O.k. Li, Lawrence Y. L. Cheung

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)

Challenge:	Existing approaches struggle with temporal-spatial challenges in capturing subtle linguistic shifts across different disease stages.
Approach:	They propose a large language model-driven T-S fusion framework that integrates multilingual LLMs, contrastive learning and interpretable marker discovery to revolutionize late onset AD detection.
Outcome:	The proposed framework achieves state-of-the-art performance in late onset AD detection while enabling cross-linguistic diagnostics.

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Challenge:	Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks.
Approach:	They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies.
Outcome:	The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%.

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification (2026.findings-acl)

Copied to clipboard

Jingwei Song, Xinyu Wang, Hanbin Wang, Xiaoxuan Lei, Tianyu Shi, Shixin Han, Eric Yang, Xiao-Wen Chang, Lynn Ai

Challenge:	Autoregressive large language models suffer from high inference latency due to memorybandwidth constraints.
Approach:	They propose a method that decouples generation and verification by decoupling tokens and a lightweight draft model.
Outcome:	The proposed method delivers consistent and significant speedups over state-of-the-art baselines while preserving generation quality across diverse benchmarks.

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Copied to clipboard

Yiyang Zhou, Linjie Li, Shi Qiu, Zhengyuan Yang, Yuyang Zhao, Siwei Han, Yangfan He, Kangqi Li, Haonian Ji, Zihao Zhao, Haibo Tong, Lijuan Wang, Huaxiu Yao

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)

Challenge:	Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach:	They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome:	The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.

Copied to clipboard

Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says .
Approach:	They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions.
Outcome:	a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures .

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

Failure makes the agent stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions (2026.findings-acl)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Junhao Su, Yuanliang Wan, Junwei Yang, Hengyu Shi, Tianyang Han, Yurui Qiu, Junfeng Luo

Non-Autoregressive Math Word Problem Solver with Unified Tree Structure (2023.emnlp-main)

Challenge:	Existing approaches to self-reflection rely on heuristic prompting or unidirectional reasoning traces.
Approach:	They propose a structured reflection method that transforms the "from error to repair" process into a first-class, controllable, and trainable action.
Outcome:	The proposed method improves multi-turn tool-call success rates and error recovery while reducing redundant calls.

Copied to clipboard

Yi Bin, Mengqun Han, Wenhao Shi, Lei Wang, Yang Yang, See-Kiong Ng, Heng Shen

Numerical Reasoning

Challenge:	Existing MWP solvers do not handle variants that can be derived via mathematical manipulation.
Approach:	They propose a non-autoregressive solver to present a solution expression and decode it from a given problem description.
Outcome:	The proposed solver is able to decode multiple expression variants and correct them . it is based on a unified tree structure and is available on Math23K and MAWPS.

Multi-Scale Spectral Selection and Entropy-Guided Uncertainty Fusion for Multimodal Rumor Detection (2026.findings-acl)

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Fan Li, Dong Yu, Yan Song, null Zhangfengzhen

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Existing methods for multimodal content detection fail to capture cross-modal semantic inconsistencies and ignore inherent noise in multimodal features.
Approach:	They propose a multimodal rumor detection method based on a frequency domain spectral selection method and entropy-guided uncertainty fusion method to capture cross-modal semantic inconsistencies.
Outcome:	The proposed method outperforms state-of-the-art methods in multimodal rumor detection . it shows stronger detection capability and robustness on multiple datasets .

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

From Scaffolding to Assimilation: Progressive Structural Internalization for Format-Constrained Creative Text Generation (2026.findings-acl)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Wenhao Li, Yuwei Yang, Xiaoqing Wu, Yufeng Han, Cunliang Kong, Yuzhuo Bai, Xin Cong, Maosong Sun

Text Generation

Challenge:	Existing paradigms rely on unreliable prompting or rigid constrained decoding strategies to achieve aesthetic unity.
Approach:	They propose a framework to embed external constraints into the model’s intrinsic intuition and use it to generate open-ended creative texts.
Outcome:	The proposed framework surpasses baselines in both strict constraint adherence and literary aesthetics.

EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection (2026.acl-long)

Copied to clipboard

Shuo Yang, Caren Han, Xueqi Ma, Yan Li, Mohammad Reza Ghasemi Madani, Eduard Hovy

Challenge:	Existing approaches to optimize tool-use policies are monolithic and prone to entangling behaviors.
Approach:	They propose a framework that decomposes agent’stool-use policy into four modules and improves them via three mechanisms.
Outcome:	The proposed framework outperforms strong baselines on bothGPT-4.1 and Qwen3-8B while maintaining superior efficiency and transferability.

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models (2025.emnlp-main)

Copied to clipboard

Cheng Wang, Gelei Deng, Xianglin Yang, Han Qiu, Tianwei Zhang

Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification (2025.emnlp-industry)

Challenge:	Large Audio-Language Models (LALMs) are augmented with the ability to perceive audio, but their reliability when faced with conflicting inputs remains largely unexplored.
Approach:	They examine how LALMs prioritize information when presented with inconsistent audio-text pairs.
Outcome:	The proposed models display a significant bias toward textual input when presented with inconsistent audio-text pairs.

Copied to clipboard

Huike Zou, Haiyang Yang, Yindu Su, Chen Li Yu, Qinye Xie, Chengbao Lian, Qingheng Zhang, Shuguang Han, Fei Huang, Jufeng Chen

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)

Challenge:	Existing methods for product attribute value identification suffer from cascading errors and lack of generalization capability.
Approach:	They propose a multi-level retrieval scheme that uses products and attribute values as distinct hierarchical levels in PAVI domain.
Outcome:	The proposed method performs better than the state-of-the-art methods on a real-world industrial dataset.

Copied to clipboard

Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

Level-Up: Learning to Improve Proficiency Level of Essays (P19-3)

Challenge:	Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs.
Approach:	They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn.
Outcome:	The proposed framework improves strategy selection preferences at each dialogue turn.

Copied to clipboard

Wen-Bin Han, Jhih-Jie Chen, Chingyu Yang, Jason Chang

Syntactic Text Processing

Challenge:	Many essays are submitted to tutoring services by English learners on the Web every day . few systems provide focused suggestions on how to raise the level of proficiency.
Approach:	They propose a method for generating suggestions on a sentence for improving proficiency . they propose identifying grammatical elements and ranking related elements to provide suggestions .
Outcome:	The proposed method helps english learners improve their writing and reading skills.

From Generalist to Specialist: A Survey of Large Language Models for Chemistry (2025.coling-main)

Copied to clipboard

Yang Han, Ziping Wan, Lu Chen, Kai Yu, Xin Chen

MANBench: Is Your Multimodal Model Smarter than Human? (2025.findings-acl)

Challenge:	Existing studies on pretraining of LLMs on extensive web-based texts are insufficient for advanced scientific discovery, especially in chemistry.
Approach:	They outline methodologies for incorporating domain-specific chemistry knowledge and multi-modal information into LLMs and conceptualize chemistry LLM agents using chemistry tools.
Outcome:	The proposed models are based on domain-specific chemistry knowledge and multi-modal information and are capable of accelerating scientific research.

Copied to clipboard

Han Zhou, Qitong Xu, Yiheng Dong, Xin Yang

HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy (2024.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have been gaining popularity in multimodal tasks . a bilingual benchmark is available for MLLM users to evaluate their multimodal capabilities .
Approach:	They propose a bilingual multimodal ability norms benchmark that measures multimodality across nine tasks.
Outcome:	The proposed benchmark compared human performance against state-of-the-art MLLMs.

Copied to clipboard

Mengxi Xiao, Qianqian Xie, Ziyan Kuang, Zhicheng Liu, Kailai Yang, Min Peng, Weiguang Han, Jimin Huang

InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) can be used in psychotherapy to overcome challenges such as shame, distrust, and resource scarcity.
Approach:	They propose a cognitive reframing therapy method that uses empathetic dialogue to address deep-rooted negative thoughts and fosters rational, balanced perspectives.
Outcome:	The proposed model outperforms other models in terms of empathy, guidance, and logical coherence, demonstrating its effectiveness and potential positive impact on psychotherapy.

Copied to clipboard

Xiaotian Han, Yiren Jian, Xuefeng Hu, Haogeng Liu, Yiqi Wang, Qihang Fan, Yuang Ai, Huaibo Huang, Ran He, Zhenheng Yang, Quanzeng You

ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)

Challenge:	InfiMM-WebMath-40B is a dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Approach:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it contains 24 million web pages, 85 million image URLs, and 40 billion text tokens .
Outcome:	InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens .

Copied to clipboard

Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Luke Simon, Sijia Liu, Tianlong Chen, Xi Liu

100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability? (2025.findings-acl)

Challenge:	Recent advances in multimodal recommenders lack explicit reasoning and self-awareness of uncertainty.
Approach:	They propose a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline.
Outcome:	The proposed agent improves ranking metrics and performance on four standard recommendation tasks across five real-world datasets.

Copied to clipboard

Van Yang, Hongye Jin, Shaochen Zhong, Song Jiang, Qifan Wang, Vipin Chaudhary, Xiaotian Han

Challenge:	Existing benchmarks for long-context capability are too synthetic and do not represent the real world usage of LLMs.
Approach:	They propose a length-controllable, real-life reflective benchmark that disentangles baseline knowledge from long-context capabilities.
Outcome:	Experiments show that the proposed benchmarks disentangle baseline knowledge from long-context capabilities.

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors (2026.acl-long)

Copied to clipboard

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)

Challenge:	Large language models (LLMs) perform well on table tasks, but they still make data referencing errors (DREs) prior studies have only offered limited, small-scale analyses.
Approach:	They propose inference-time strategies and lightweight critics to mitigate data referencing errors.
Outcome:	The proposed model achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-difference DREs and assists inference for larger models.

Copied to clipboard

Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)

Challenge:	Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs.
Approach:	They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics.
Outcome:	The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility.

Copied to clipboard

Ruochong Xiong, Qien Li, Wangwang Lian, Yulong Wan, Hanlin Xue, Zhouxing Tan, Han Yang, Fengyu Lu, Junfei Liu

Text Generation

Challenge:	Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability.
Approach:	They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures.
Outcome:	The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios.

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Copied to clipboard

Nan He, Weichen Xiong, Hanwen Liu, Yi Liao, Lei Ding, Kai Zhang, Guohua Tang, Xiao Han, Yang Wei

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)

Challenge:	Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach:	They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome:	The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.

Copied to clipboard

Hao Gu, Hao Wang, Jiacheng Liu, Lujun Li, Qiyuan Zhu, Bei Liu, Binxing Xu, Lei Wang, Xintong Yang, Sida Lin, Sirui Han, Yike Guo

Challenge:	Recent work has shown that reinforcement learning with simple rule-based reward functions (RLVR) can induce emergent reasoning behaviors and yield gains in challenging domains such as math problem solving.
Approach:	They propose a rollout-alignment-quantization-aware RL which aligns training-side forward with the quantized rollout to minimize mismatch.
Outcome:	The proposed approach outperforms quantized-rollout training by +5.5 on Qwen3-30B-A3B MoE for math problems while maintaining low-bit throughput.

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models (2025.acl-long)

Copied to clipboard

Hieu Tran, Zonghai Yao, Zhichao Yang, Junda Wang, Yifan Zhang, Shuo Han, null Feiyun Ouyang, Hong Yu

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning (2026.acl-long)

Challenge:	Existing work aims to improve reasoning accuracy and factual integrity across large language models for knowledge-intensive tasks such as medical and commonsense reasoning.
Approach:	They propose a versatile extension to the mutual reasoning framework (rStar) that enhances reasoning accuracy and factual integrity across large language models.
Outcome:	The proposed extension to the mutual reasoning framework improves reasoning accuracy and factual integrity across large language models for complex, knowledge-intensive tasks.

Copied to clipboard

Changyu Liu, Yiyang Liu, Taowen Wang, Qiao Zhuang, James Chenhao Liang, Wenhao Yang, Renjing Xu, Qifan Wang, Dongfang Liu, Cheng Han

Uncertainty-Guided Modal Rebalance for Hateful Memes Detection (2024.acl-long)

Challenge:	Existing vision-language-action models are unsuitable for simulated or physical-world deployments . current methods fail when confronted with inherent real-world dynamic variability.
Approach:	They propose a test-time reinforcement learning framework that enables on-the-fly policy adaptation during inference.
Outcome:	Empirical results show that the proposed framework improves adaptability, stability and task success in dynamic, previously unseen scenarios.

Copied to clipboard

Chuanpeng Yang, Yaxin Liu, Fuqing Zhu, Jizhong Han, Songlin Hu

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)

Challenge:	Existing methods for integrating hate information from different modalities ignore the modality uncertainty caused by the contribution degree of each modality to hate sentiment.
Approach:	They propose an Uncertainty-guided Modal Rebalance framework for hateful memes detection . they propose to combine cross-modal fusion features with unimodal features .
Outcome:	The proposed framework produces state-of-the-art performance on four widely-used datasets.

Copied to clipboard

Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang

Challenge:	Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours.
Approach:	They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs .
Outcome:	The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models.

DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models (2025.naacl-long)

Copied to clipboard

Wei He, Kai Han, Yehui Tang, Chengcheng Wang, Yujie Yang, Tianyu Guo, Yunhe Wang

Format Inertia: A Failure Mechanism of LLMs in Medical Pre-Consultation (2025.emnlp-industry)

Challenge:	Large language models (LLMs) face excessive computational and memory requirements due to the commonly used Transformer architecture.
Approach:	They propose a method to enhance the flow of hidden information between layers in large language models by selectively integrating shallow-layer hidden states into deeper layers.
Outcome:	The proposed method maintains parallelizability and inference efficiency of SSMs while significantly boosting performance on public benchmarks.

Copied to clipboard

Seungseop Lim, Gibaeg Kim, Wooseok Han, Jean Seo, Hyunkyung Lee, Jaehyo Yoo, Eunho Yang

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

Challenge:	Recent advances in Large Language Models have brought significant improvements to various service domains, including chatbots and medical pre-consultation applications.
Approach:	They propose a method that rebalances the turn-count distribution of training data to mitigate Format Inertia in medical pre-consultation tasks.
Outcome:	The proposed method significantly alleviates Format Inertia in medical pre-consultation tasks.

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

Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis (2024.findings-acl)

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

Wei Zhai, Hongzhi Qi, Qing Zhao, Jianqiang Li, Ziqi Wang, Han Wang, Bing Yang, Guanghui Fu

SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

Challenge:	Existing models for language analysis are inadequate for specialized domains like psychology.
Approach:	They have enriched a Chinese social media database with psychological lexicons to enhance its applicability to psychological text analysis.
Outcome:	The proposed model performed better on six public datasets and provided relevant predictions given the masked sentences.

Copied to clipboard

Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang

How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design Factors (2026.findings-acl)

Challenge:	Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach:	They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome:	The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.

Copied to clipboard

Kuai Yu, Naicheng Yu, Han Wang, Rui Yang, Huan Zhang

Entity Resolution in Open-domain Conversations (2021.naacl-industry)

Challenge:	Existing studies on the effect of environmental variation on web agents have focused on robustness to adversarial attacks with less attention to agents’ preferences in benign scenarios.
Approach:	They propose a controlled evaluation pipeline to quantify how visual attributes influence web-agent decision-making by comparing variants and browsing interactions.
Outcome:	Extensive experiments on 8 variant families, 5 real-world websites and 4 representative web agents show that background color contrast, item size, position, and card clarity have a strong influence on agents’ actions, whereas font styling, text color, and item image clarity exhibit minor effects.

Copied to clipboard

Mingyue Shang, Tong Wang, Mihail Eric, Jiangning Chen, Jiyang Wang, Matthew Welch, Tiantong Deng, Akshay Grewal, Han Wang, Yue Liu, Yang Liu, Dilek Hakkani-Tur

Natural Language Interfaces

Challenge:	Recent work on incorporating external knowledge into the response generation models has attracted great interest.
Approach:	They propose a neural entity linking approach to incorporate external knowledge into the response generation models to improve the relevancy of retrieved knowledge.
Outcome:	The proposed approach outperforms the baseline model by 62.8% relative to the baseline.

UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)

Copied to clipboard

Haoyu Wang, Shuo Wang, Yukun Yan, Xujia Wang, Zhiyu Yang, Yuzhuang Xu, Zhenghao Liu, Liner Yang, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun

Unsupervised Energy-based Adversarial Domain Adaptation for Cross-domain Text Classification (2021.findings-acl)

Challenge:	Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English.
Approach:	They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries.
Outcome:	The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation.

Copied to clipboard

Han Zou, Jianfei Yang, Xiaojian Wu

Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems (2021.naacl-industry)

Challenge:	Extensive experiments on multidomain sentiment classification and yes/no question-answering classification are conducted.
Approach:	They propose an unsupervised energy-based adversarial domain adaptation framework that maps the text sequences from both source and target domains to a feature space.
Outcome:	The proposed framework improves on multidomain sentiment classification and Yes/No question-answering classification.

Copied to clipboard

Tong Wang, Jiangning Chen, Mohsen Malmir, Shuyan Dong, Xin He, Han Wang, Chengwei Su, Yue Liu, Yang Liu

Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph (2020.coling-main)

Challenge:	In dialog systems, the Natural Language Understanding component makes the interpretation decision before the mentioned entities are resolved.
Approach:	They propose to leverage Entity Resolution (ER) features in NLU reranking to learn model weights . they propose a score distribution matching method to ensure the models are calibrated .
Outcome:	The proposed approach outperforms the baseline model on multiple domain evaluations.

Copied to clipboard

Xu Wang, Shuai Zhao, Jiale Han, Bo Cheng, Hao Yang, Jianchang Ao, Zhenzi Li

Structured Data in NLP

Challenge:	Existing studies rely on deep graph neural networks (GNNs) to capture rich structural information, but they lack the structural information needed for QA.
Approach:	They propose a framework which captures structural information from KBs and models long-distance node relations from two perspectives.
Outcome:	The proposed framework models long-distance node relations from two perspectives . it is based on two widely used multi-hop KBQA datasets .

SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)

Copied to clipboard

Chuxue Cao, Han Zhu, Jiaming Ji, Qichao Sun, Zhenghao Zhu, Wu Yinyu, Josef Dai, Yaodong Yang, Sirui Han, Yike Guo

TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models (2022.emnlp-main)

Challenge:	Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations.
Approach:	They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark.
Outcome:	The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks.

Copied to clipboard

Joel Jang, Seonghyeon Ye, Changho Lee, Sohee Yang, Joongbo Shin, Janghoon Han, Gyeonghun Kim, Minjoon Seo

When Slower Isn’t Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning (2026.findings-acl)

Challenge:	Language Models (LMs) become outdated as the world changes, a phenomenon called temporal misalignment.
Approach:	They propose a lifelong benchmark that utilizes the difference between consecutive snapshots of English Wikipedia and English Wikidata for training and evaluation.
Outcome:	The proposed benchmark can be trained on the difference between consecutive snapshots of English Wikipedia and English Wikidata for training and evaluation.

Copied to clipboard

Sitong Fang, Wenjing Cao, Jiahao Li, Xuyao Wang, Chi-Min Chan, Sirui Han, Juntao Dai, Yike Guo, Yaodong Yang, Jiaming Ji

QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning (2026.acl-long)

Challenge:	a study of slow reasoning models for multimodal reasoning finds that they are more prone to fabricating plausible yet false details when confronted with incomplete or misleading visual inputs.
Approach:	They conduct the first systematic study of the inverse scaling law in slow-thinking paradigms for multimodal reasoning.
Outcome:	The findings suggest that slower reasoning models are more prone to fabricating false details . the study analyzed 5,000-sample hierarchical prompt dataset by 50 participants .

Copied to clipboard

Songxin Qu, Tai-Ping Sun, Yun-Jie Wang, Huan-Yu Liu, Cheng Xue, Xiao-Fan Xu, Han Fang, Yang Yang, Yu-Chun Wu, Guo-Ping Guo, Zhao-Yun Chen

New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs (2026.acl-long)

Challenge:	Large language models lack reliability in scientific domains that require strict adherence to physical constraints.
Approach:	They propose a large-scale dataset constructed via a task-adaptive strategy and a hybrid verification protocol that combines deterministic solvers with semantic auditing to guarantee scientific rigor.
Outcome:	The proposed model outperforms baselines and general-purpose preference models and is competitive with proprietary models.

Copied to clipboard

Shiyao Cui, QingLin Zhang, Di Wang, Yida Lu, Zhexin Zhang, Jinhua Gao, Jinglin Yang, Min He, Han Qiu, Minlie Huang

Taxonomy of Comprehensive Safety for Clinical Agents (2025.emnlp-industry)

Challenge:	Neologisms can foster new linguistic consensus by stabilizing shared meanings and usage in common communicative norms.
Approach:	They propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms . they propose 'SeTox' framework that integrates real-time web context for naeologim detection .
Outcome:	The proposed framework outperforms large-scale models in detecting neologism toxicity.

Copied to clipboard

Jean Seo, Hyunkyung Lee, Gibaeg Kim, Wooseok Han, Jaehyo Yoo, Seungseop Lim, Kihun Shin, Eunho Yang

Challenge:	Existing methods for ensuring safety in clinical chatbot applications are not suitable for clinical applications.
Approach:	They propose a fine-grained taxonomy that integrates safety filtering and tool selection into a single user intent classification step.
Outcome:	The proposed taxonomy integrates safety filtering and tool selection into a single user intent classification step.

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction (2026.findings-acl)

Copied to clipboard

Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen

Learning to Link Grammar and Encyclopedic Information of Assist ESL Learners (P19-3)

Challenge:	Existing benchmarks focus on casual conversation or task-oriented dialogue, failing to capture “long-term project-oriented” interactions where agents must track evolving goals.
Approach:	They propose a benchmark that simulates the dynamic evolution of memory in real-world projects.
Outcome:	The proposed benchmarks simulate the dynamic evolution of memory in real-world projects.

Copied to clipboard

Jhih-Jie Chen, Chingyu Yang, Peichen Ho, Ming Chiao Tsai, Chia-Fang Ho, Kai-Wen Tuan, Chung-Ting Tsai, Wen-Bin Han, Jason Chang

Challenge:	Linggle Booster provides rich lexical information such as collocations and grammar patterns for target words.
Approach:	They propose a system that takes an article, identifies target vocabulary, provides lexical information, and generates a quiz on target words.
Outcome:	The proposed system has been evaluated on a set of target words and has a good performance.

Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models (2025.coling-main)

Copied to clipboard

Xinyu Pang, Ruixin Hong, Zhanke Zhou, Fangrui Lv, Xinwei Yang, Zhilong Liang, Bo Han, Changshui Zhang

CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translation (2022.findings-emnlp)

Challenge:	Existing large language models (LLMs) fail due to lack of knowledge or incorrect knowledge application.
Approach:	They propose a knowledge-augmented framework that constructs a formula set to provide explicit physics knowledge and utilizes checklists to guide effective knowledge application.
Outcome:	The proposed framework achieves state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.

Copied to clipboard

Han Zhang, Sheng Zhang, Yang Xiang, Bin Liang, Jinsong Su, Zhongjian Miao, Hui Wang, Ruifeng Xu

Multilinguality

Challenge:	Existing benchmarks for Continual Language Learning (CLL) are limited due to the complexity of the task and the lack of unified benchmarks.
Approach:	They propose a Continual Language Learning Evaluation benchmark CLLE in multilingual translation.
Outcome:	The proposed method is effective when compared with other strong benchmarks.

Finding the Pillars of Strength for Multi-Head Attention (2023.acl-long)

Copied to clipboard

Jinjie Ni, Rui Mao, Zonglin Yang, Han Lei, Erik Cambria

Chain of Attack: Hide Your Intention through Multi-Turn Interrogation (2025.findings-acl)

Challenge:	Recent studies have revealed some issues of Multi-Head Attention (MHA) e.g., redundancy and over-parameterization.
Approach:	They propose to train attention heads with a self-supervised group constraint to focus on an essential but distinctive feature subset.
Outcome:	The proposed method achieves significant performance gains on three well-established tasks while significantly compressing parameters.

Copied to clipboard

Xikang Yang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu

Unsupervised Multi-Granularity Summarization (2022.findings-emnlp)

Challenge:	Existing jailbreak attacks focus on single-turn dialogue scenarios, leaving vulnerabilities in multi-turn contexts inadequately explored.
Approach:	They propose an optimal interrogation principle to conceal the jailbreak intent and introduce a multi-turn attack chain generation strategy called CoA.
Outcome:	The proposed method shows that black-box LLMs exhibit insufficient resistance under multi-turn interrogation, with more advantages (ASR, 83% vs 64%)

Copied to clipboard

Ming Zhong, Yang Liu, Suyu Ge, Yuning Mao, Yizhu Jiao, Xingxing Zhang, Yichong Xu, Chenguang Zhu, Michael Zeng, Jiawei Han

Evaluating the Pre-Consultation Ability of LLMs using Diagnostic Guidelines (2026.eacl-industry)

Challenge:	Experimental results confirm the substantial superiority of GranuSum on multi-granularity summarization over strong baselines.
Approach:	They propose to rank events by their salience and annotate a benchmark for GranuSum that contains multiple summaries at different granularities for each document cluster.
Outcome:	The proposed framework is capable of producing multi-granular summaries in unsupervised manner over strong baselines.

Copied to clipboard

Jean Seo, Gibaeg Kim, Kihun Shin, Seungseop Lim, Hyunkyung Lee, Wooseok Han, Jongwon Lee, Eunho Yang

Challenge:	EPAG is a benchmark dataset and evaluation pipeline for pre-consultation of large language models.
Approach:	They propose a benchmark dataset and framework for evaluating pre-consultation ability of LLMs using diagnostic guidelines.
Outcome:	The proposed framework outperforms frontier LLMs in pre-consultation.

AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference (2024.findings-emnlp)

Copied to clipboard

Yang Han, Yiming Wang, Rui Wang, Lu Chen, Kai Yu

Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)

Challenge:	Text summarization tasks employ Pre-trained Language Models (PLMs) to fit diverse datasets.
Approach:	They propose a human summarization preference alignment framework to align PLMs with human preferences.
Outcome:	The proposed framework narrows the gap between automatic and human evaluations by integrating three components.

Copied to clipboard

Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin

Challenge:	e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features.
Approach:	They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent.
Outcome:	The proposed model outperforms baseline models and provides better recall and triage for specialized agents.

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks (2025.findings-naacl)

Copied to clipboard

Samuele Poppi, Zheng Xin Yong, Yifei He, Bobbie Chern, Han Zhao, Aobo Yang, Jianfeng Chi

Robustness in NLP

Challenge:	Recent advances in Large Language Models have sparked concerns about their safety.
Approach:	They propose a method to identify safety-related information in the model parameter space . they propose to use a few adversarially chosen examples to fine-tune LLMs .
Outcome:	The proposed method can break safety alignment in multilingual LLMs using a few examples . it also shows that the proposed method jailbreaks LLM models adapted to new languages .

Benchmarking Multi-National Value Alignment for Large Language Models (2025.findings-acl)

Copied to clipboard

Chengyi Ju, Weijie Shi, Chengzhong Liu, Jiaming Ji, Jipeng Zhang, Ruiyuan Zhang, Jiajie Xu, Yaodong Yang, Sirui Han, Yike Guo

RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model (2025.findings-naacl)

Challenge:	Existing studies on large language models focus on ethical reviews, failing to capture the diversity of national values.
Approach:	They propose a national value extraction pipeline to efficiently construct value assessment datasets and a model-based model with instruction tagging to process raw data sources.
Outcome:	The proposed benchmark evaluates the alignment of LLMs with the values of five major nations: China, the United States, the UK, France, and Germany.

Copied to clipboard

Changhai Zhou, Shijie Han, Lining Yang, Yuhua Zhou, Xu Cheng, Yibin Wang, Hongguang Li

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)

Challenge:	Current compression techniques entail structural pruning and a recovery phase that leverages the Low-Rank Adaptation algorithm.
Approach:	They propose a hierarchical rank allocation method that enables efficient fine-tuning of pruned LLMs according to layerwise specific recovery requirements.
Outcome:	The proposed algorithm outperforms state-of-the-art methods across pruning settings and LLM architectures with improvements ranging from 0.7% to 5.5%.

Copied to clipboard

Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang

DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences.
Approach:	They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks.
Outcome:	Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks.

Copied to clipboard

Xiaojun Bi, Shuo Li, Junyao Xing, Ziyue Wang, Fuwen Luo, Weizheng Qiao, Lu Han, Ziwei Sun, Peng Li, Yang Liu

InterIDEAS: Philosophical Intertextuality via LLMs (2025.emnlp-main)

Challenge:	Dongba pictographic is the only pictograph script still in use in the world.
Approach:	DongbaMIE is the first dataset focusing on multimodal information extraction of Dongbe pictographs.
Outcome:	The dataset contains 23,530 sentence-level and 2,539 paragraph-level high-quality text-image pairs.

Copied to clipboard

Yue Yang, Yinzhi Xu, Chenghao Huang, JohnMichael Jurgensen, Han Hu, Hao Wang

Challenge:	a new dataset aims to bridge philosophy, literary studies, and natural language processing (NLP) by integrating theories of intertextuality with bibliometric techniques.
Approach:	They propose a dataset that bridges philosophy, literary studies, and natural language processing (NLP) it combines theories of intertextuality from literary studies with bibliometric techniques and recent LLMs .
Outcome:	a new dataset bridges philosophy, literary studies, and natural language processing (NLP) to analyze intertextuality . the proposed method helps scholars understand the intellectual, social, and historical relations embedded in texts . it also contributes to the development of language models, authors say .

More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning (2025.emnlp-industry)

Copied to clipboard

Yike Zhao, Simin Guo, Ziqing Yang, Shifan Han, Dahua Lin, Fei Tan

SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026.findings-acl)

Challenge:	Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored.
Approach:	They conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning under a unified pipeline designed to mirror training and deployment scenarios.
Outcome:	The proposed pipelines mirror training and deployment scenarios and are suitable for industrial applications.

Copied to clipboard

Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Lintao Ma, Xingyu Lu, Jun Zhou, Pengfei Liu, Jiancan Wu, Xiang Wang

FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation (2025.acl-long)

Challenge:	Existing large-scale large-context models suffer from performance degradation when processing long numerical sequences.
Approach:	They propose a framework to mitigate attention dispersion by strategically inserting separator tokens into the model to recalibrat attention to local segments while preserving global context.
Outcome:	The proposed framework improves accuracy and reduces inference token consumption by 16.4% on 9 widely-adopted LLMs.

Copied to clipboard

Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo

Ambiguous Learning from Retrieval: Towards Zero-shot Semantic Parsing (2023.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years, but there is a notable lack of effective and specialized multimodal evaluation datasets in the financial domain.
Approach:	They introduce FinMME, a multimodal large language model with 11,000 financial research samples and 20 annotators.
Outcome:	The proposed model performs better than state-of-the-art models, highlighting its challenging nature.

Copied to clipboard

Shan Wu, Chunlei Xin, Hongyu Lin, Xianpei Han, Cao Liu, Jiansong Chen, Fan Yang, Guanglu Wan, Le Sun

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)

Challenge:	Existing neural semantic parsers require a large amount of training data which is expensive and difficult to obtain.
Approach:	They propose a framework for a supervised retrieval system based on pretrained language models . they propose ambiguous supervision to improve the precision and coverage of the task .
Outcome:	The proposed approach outperforms state-of-the-art zero-shot parsing methods in ambiguous supervision.

Copied to clipboard

Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong

Reward Generalization in RLHF: A Topological Perspective (2025.findings-acl)

Challenge:	Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency.
Approach:	They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs.
Outcome:	The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks.

Copied to clipboard

Tianyi Alex Qiu, Fanzhi Zeng, Jiaming Ji, Dong Yan, Kaile Wang, Jiayi Zhou, Yang Han, Josef Dai, Xuehai Pan, Yaodong Yang

Challenge:	Existing alignment methods share a common topology of information flow, but their alternatives have not been thoroughly explored.
Approach:	They propose a theory of reward generalization in reinforcement learning from human feedback . they propose induced Bayesian networks to model the impact of dataset topologies on reward generalisation .
Outcome:	The proposed method achieves an average win rate of 65% on three NLP tasks.

ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web (2026.acl-long)

Copied to clipboard

Zhiyuan Yao, Zishan Xu, Yifu Guo, Zhiguang Han, Cheng Yang, Shuo Zhang, Weinan Zhang, Xingshan Zeng, Weiwen Liu

Challenge:	Existing routers that use hardcoded tools are limited by scalability and generality bottlenecks.
Approach:	They propose a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems.
Outcome:	The proposed pipeline can train routers with dynamic context understanding to create the plug-and-play Light Routing Agent.

ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)

Copied to clipboard

Chenyang Song, Xu Han, Zhengyan Zhang, Shengding Hu, Xiyu Shi, Kuai Li, Chen Chen, Zhiyuan Liu, Guangli Li, Tao Yang, Maosong Sun