Papers by Zheng Hu
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that rule-based evaluation methods are ineffective for open-ended natural language generation. |
| Approach: | They propose a pointwise generative reward model with a dedicated two-stage rollout method and unified query-based criteria that can be trained with 5.7K high-quality data. |
| Outcome: | The proposed model achieves superior performance on diverse reward model benchmarks, especially in Best-of-N scenarios, and delivers more effective improvements in downstream RL practice. |
VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)
Copied to clipboard
Shuliang Liu, Zheng Qi, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu
| Challenge: | Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable. |
| Approach: | They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns . |
| Outcome: | The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC). |
FISTAPruner: Layer-wise Post-training Pruning for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing pruning methods require inefficient retraining for billion-scale LLMs or rely on heuristicically designed metrics to determine pruning masks, leading to performance degradation. |
| Approach: | They propose a convex optimization model that induces sparsity in large language models by leveraging FISTA. |
| Outcome: | The proposed method can remove 50% of model parameters while retaining 98.6% and 95.6% of the zero-shot performance. |
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)
Copied to clipboard
Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap . |
| Approach: | They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models. |
| Outcome: | The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting . |
Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a promising approach for cross-cultural recipe adaptation, but it fails to generate diverse results even when provided with varied contextual inputs. |
| Approach: | They propose a plug-and-play RAG framework that enhances diversity in both retrieval and context organization to generate diverse outputs to accommodate multiple user preferences. |
| Outcome: | The proposed framework achieves Pareto efficiency in terms of diversity and quality of recipe adaptation compared to closed-book LLMs. |
Unified Thinker: A General Reasoning Core for Image Generation (2026.acl-long)
Copied to clipboard
Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao
| Challenge: | generative models struggle with logic-intensive instruction following, exposing a persistent reasoning–execution gap. |
| Approach: | They propose a task-agnostic reasoning architecture for general image generation . they propose pixel-level feedback to ground the Thinker's policy in pixel feedback . |
| Outcome: | The proposed system significantly improves image reasoning and generation quality. |
An AMR-based Link Prediction Approach for Document-level Event Argument Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work has introduced Abstract Meaning Representation (AMR) for Document-level Event Argument Extraction (Doc-level EAE) however, in these works AMR is used only implicitly, for instance, as additional features or training signals. |
| Approach: | They propose a novel AMR-based graph structure which uses graph neural networks to find event arguments from unstructured text. |
| Outcome: | The proposed graph structure outperforms the state-of-the-art models by 3.63pt and 2.33pt F1 and reduces inference time by 56%. |
Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to cross-document event coreference resolution are prone to learning simple co-occurrences due to the complexity of contexts. |
| Approach: | They propose a collaborative approach to cross-document event coreference resolution that leverages both a universally capable LLM and a task-specific SLM. |
| Outcome: | The proposed approach surpasses the performance of both large and small language models individually, underscoring its effectiveness in diverse scenarios. |
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)
Copied to clipboard
Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang
| Challenge: | PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks. |
| Approach: | They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks. |
| Outcome: | The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods. |
OpenPrompt: An Open-source Framework for Prompt-learning (2022.acl-demo)
Copied to clipboard
| Challenge: | Prompt-learning is a new paradigm in natural language processing, adapting pre-trained language models to cloze-style prediction, autoregressive modeling, or sequence to sequence generation. |
| Approach: | They propose a framework for prompt-learning that integrates pre-trained language models with a unified framework. |
| Outcome: | The proposed framework is easy to use and flexible enough to integrate with other frameworks. |
A Bayesian Approach to Harnessing the Power of LLMs in Authorship Attribution (2024.emnlp-main)
Copied to clipboard
| Challenge: | Authorship attribution relies on manual features and fails to capture long-range correlations, limiting their effectiveness. |
| Approach: | They propose to use Bayesian methods to calculate the probability that a text entails previous writings of an author. |
| Outcome: | The proposed model can achieve 85% accuracy on the IMDb and blog datasets. |
Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)
Copied to clipboard
Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu
| Challenge: | Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole . |
| Approach: | They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task. |
| Outcome: | The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices. |
CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space (2025.emnlp-main)
Copied to clipboard
Yong Zhao, Kai Xu, Zhengqiu Zhu, Yue Hu, Zhiheng Zheng, Yingfeng Chen, Yatai Ji, Chen Gao, Yong Li, Jincai Huang
| Challenge: | Embodied Question Answering (EQA) tasks are primarily focused on indoor environments, leaving the complexities of urban settings unexplored. |
| Approach: | They propose a task where an embodied agent answers open-vocabulary questions in dynamic city spaces. |
| Outcome: | The proposed agent achieves 60.7% of human-level answering accuracy compared to baselines . the proposed agent outperforms existing agents in open-ended city spaces . |
RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing structured reasoning frameworks lack internal decision probability and cannot model the tree as a whole. |
| Approach: | They propose a Reinforcement Learning based Entailment Tree generation framework that is trained using the cumulative signals across the whole tree. |
| Outcome: | The proposed framework offers explicit deductions with entailment steps in a tree structure. |
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Chia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh, Menghai Pan, Chin-Chia Michael Yeh, Guanchu Wang, Mingzhi Hu, Zhichao Xu, Yan Zheng, Mahashweta Das, Na Zou
| Challenge: | Existing RAG systems struggle with the quality of retrieval documents, causing performance degradation and reducing performance. |
| Approach: | They propose a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents. |
| Outcome: | The proposed framework outperforms existing RAG frameworks in QA benchmarks and shows superior answer consistency and answer accuracy over baseline methods. |
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)
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
| 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. |
MAssistant: A Personal Knowledge Assistant for MOOC Learners (D19-3)
Copied to clipboard
| Challenge: | Massive Open Online Courses (MOOCs) have experienced a rapid development since 2012 . many MOOC platforms have been launched, including Coursera1 , edX2 , and Udacity3 etc. |
| Approach: | They present a personal knowledge assistant system called MAssistant for MOOC learners . MAsistants has a large-scale concept graph built from open data . it also provides a browser extension which interacts with users during video lectures . |
| Outcome: | The proposed system helps users trace the concepts they have learned in MOOCs, and to build their own concept graphs. |
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)
Copied to clipboard
Runxuan Liu, Xianhao Ou, Xinyan Ma, Jiyuan Wang, Jiafeng Liang, Jiaqi Li, Tao He, Zheng Chu, Rongchuan Mu, Zekun Wang, Baoxin Wang, Dayong Wu, Ming Liu, Shijin Wang, Guoping Hu, Bing Qin
| Challenge: | Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization. |
| Approach: | They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach. |
| Outcome: | The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks. |
KCAT: A Knowledge-Constraint Typing Annotation Tool (P19-3)
Copied to clipboard
Sheng Lin, Luye Zheng, Bo Chen, Siliang Tang, Zhigang Chen, Guoping Hu, Yueting Zhuang, Fei Wu, Xiang Ren
| Challenge: | Recent years Natural Language Processing community has seen a surge of interest in fine-grained entity typing (FET) given an entity mention (i.e. a sequence of token spans representing an entity), FET aims at uncovering its contextdependent type. |
| Approach: | They propose an efficient Knowledge Constraint Fine-grained Entity Typing Annotation Tool which further improves the entity typing process through entity linking together with some practical functions. |
| Outcome: | The proposed tool improves the entity typing process by linking the candidate types with some practical functions. |
Exploring Lottery Prompts for Pre-trained Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize pre-trained language models are expensive and slow to scale. |
| Approach: | They propose to search for instance-level lottery prompts and generalize them to unseen data . they validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM . |
| Outcome: | The proposed method can achieve comparable results with other gradient-free and optimization-free baselines. |
Self-Ensemble: Mitigating Confidence Distortion for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models exhibit a confidence distortion problem on multichoice question-answering . Self-Ensemble solves this problem by splitting the choices into several groups . |
| Approach: | They propose a method that splits LLM choices into several groups and ensembles them to reach a final decision. |
| Outcome: | The proposed method outperforms standard inference and baseline methods on MCQA. |
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models with stacked layers do not explicitly model hierarchical structure of language understanding. |
| Approach: | They propose a recursive Transformer model based on differentiable CKY style binary trees to emulate hierarchical composition process. |
| Outcome: | The proposed model can predict words given their left and right abstraction nodes. |
StructuThink: Reasoning with Task Transition Knowledge for Autonomous LLM-Based Agents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | StructuThink framework enhances LLMs' ability to ground decisions in domain-specific scenarios. |
| Approach: | They propose a knowledge-structured reasoning framework that enhances LLM-based agents with explicit decision constraints. |
| Outcome: | The proposed framework achieves higher task success rates and more efficient action sequences than baseline methods. |
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)
Copied to clipboard
Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng
| Challenge: | Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity. |
| Approach: | They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. |
| Outcome: | The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging. |
AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Recent work on learning from multiple tasks has shown that adding an extra fusion layer to implement knowledge composition is non-scalable for some applications. |
| Approach: | They propose a two-stage knowledge distillation algorithm to extract task specific knowledge by using local data to train a student adapter. |
| Outcome: | Experiments on frequently asked question retrieval in task-oriented dialog systems validate the efficiency of AdapterDistillation. |
Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction (2025.emnlp-main)
Copied to clipboard
Junkai Liu, Yujie Tong, Hui Huang, Bowen Zheng, Yiran Hu, Peicheng Wu, Chuan Xiao, Makoto Onizuka, Muyun Yang, Shuyuan Zheng
| Challenge: | Existing studies use legal facts to predict judgments, but legal facts are difficult to obtain in early stages of litigation. |
| Approach: | They propose a legal fact prediction task that takes evidence from trial as input to make predictions in the absence of ground-truth legal facts. |
| Outcome: | The proposed task can predict court rulings without ground-truth legal facts . the first benchmark dataset, LFPBench, is used to evaluate the task . |
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)
Copied to clipboard
Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen
| Challenge: | Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed . |
| Approach: | They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities. |
| Outcome: | The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech . |
Token-level Inference-Time Alignment for Vision-Language Models (2026.findings-acl)
Copied to clipboard
Kejia Chen, Junjun Zheng, Jiawen Zhang, Manxi Lin, Xiao Pan, Jiacong Hu, Jian Lou, Zunlei Feng, Mingli Song
| Challenge: | Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity . despite widespread adoption, VLMs often exhibit a critical failure mode: hallucination . |
| Approach: | They propose a framework for Token-level Inference-Time Alignment that steers the decoding process without updating the base model parameters. |
| Outcome: | The proposed framework improves performance on 13 benchmarks across architectures . it boosts LLaVA-1.5-7B by 8.6% on MMVet and achieves a 74.0 MMStar score . |
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)
Copied to clipboard
Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu
| Challenge: | Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression. |
| Approach: | They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks. |
| Outcome: | The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks. |
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)
Copied to clipboard
Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang
| Challenge: | Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. |
| Approach: | AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks. |
| Outcome: | Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% . |
All That Glitters is Not Gold: Improving Robust Retrieval-Augmented Language Models with Fact-Centric Preference Alignment (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to learn adaptive retrieval for noisy documents lack prior filtering and may lead to the loss of crucial information. |
| Approach: | They propose a method to improve retrieval performance without prior filtering . they use LLMs self-generated synthetic data as training data without manual annotation . |
| Outcome: | The proposed method performs positive document mining based on factual consistency and uses LLMs self-generated synthetic data as training data without manual annotation. |
SAFER: A Controllable Safeguard for LLMs against Backdoor Attacks (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing inference-time defenses lack explicit control over false acceptance rate (FAR) existing inference time defenses aim to mitigate poisoned inputs but lack explicit FAR control . |
| Approach: | They propose a framework that provides explicit control over false acceptance rate without prior knowledge of backdoor samples. |
| Outcome: | The proposed framework outperforms existing inference-time defenses on three benchmark datasets . it provides explicit and provable control over false acceptance rate without prior knowledge of backdoor samples . |
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)
Copied to clipboard
Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu
| Challenge: | Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves. |
| Approach: | They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop. |
| Outcome: | The proposed framework yields more stable training and higher long-horizon task success across open-world environments. |
Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences (2025.findings-emnlp)
Copied to clipboard
Mingqian Zheng, Wenjia Hu, Patrick Zhao, Motahhare Eslami, Jena D. Hwang, Faeze Brahman, Carolyn Rose, Maarten Sap
| Challenge: | Current LLMs are trained to refuse potentially harmful input queries regardless of intent . a study of 480 participants evaluating 3,840 query-response pairs reveals that response strategy largely shapes user experience . |
| Approach: | They examine how different refusal strategies affect user perceptions across varying motivations . they find partial compliance reduces negative user perception by over 50% to flat-out refusals a 480 participants study . |
| Outcome: | The study examines the perceptions of LLMs on user intents and their response strategies . it shows that partial compliance reduces negative user perceptions by over 50% to flat refusals . |
Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction (2025.acl-industry)
Copied to clipboard
Yinghui Li, Shang Qin, Jingheng Ye, Haojing Huang, Yangning Li, Shu-Yu Guo, Libo Qin, Xuming Hu, Wenhao Jiang, Hai-Tao Zheng, Philip S. Yu
| Challenge: | Recent studies have shown that Large Language Models’ performance as correctors on Chinese Grammatical Error Correction (CGEC) remains unsatisfactory due to the challenging nature of the task. |
| Approach: | They propose a training framework EXAM that uses LLMs as explainers to enhance CGEC small models and a novel evaluation method SEE that utilizes LLM as evaluators to bring more reasonable evaluations. |
| Outcome: | The proposed methods improve the performance of LLMs on Chinese Grammatical Error Correction (CGEC) task. |
DSCD: Large Language Model Detoxification with Self-Constrained Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for decoding large language models (LLMs) are based on external constraints and require additional resource overhead and loss of generation fluency. |
| Approach: | They propose a method for LLMs detoxification without parameter fine-tuning that strengthens the inner token distribution while weakening that of hallucination and toxic layer during output generation. |
| Outcome: | Extensive experiments on open-source LLMs and public datasets demonstrate DSCD's state-of-the-art (SOTA) performance in detoxification and generation fluency, with superior efficiency compared to existing methods. |
Exploiting Abstract Meaning Representation for Open-Domain Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work attempts to address these challenges using Pretrained Language Models (PLMs) but the diversity of surface form expressions can hinder the model’s ability to capture accurate correlations, especially when the context is lengthy and complex. |
| Approach: | They propose a method known as Graph-as-Token (GST) to incorporate AMRs into PLMs to assist the model in understanding complex semantic information. |
| Outcome: | The proposed method outperforms existing methods and significantly improves performance on both Natural Questions and TriviaQA. |
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) with web search capabilities show significant potential for deep research. |
| Approach: | They introduce a framework for end-to-end training of LLM-based deep research agents . they implement a specialized multi-agent architecture where browsing agents extract relevant information from various webpage structures. |
| Outcome: | The proposed framework improves on open-domain research tasks by 28.9 points over prompt engineering and 7.2 points over RAG-based RL agents. |
Multimodal Dialogue Response Generation (2022.acl-long)
Copied to clipboard
Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang
| Challenge: | Existing studies focus on multimodal dialogue models but neglect generation methods. |
| Approach: | They propose a multimodal dialogue response generation task which requires multimodal dialogs containing both texts and images which are difficult to obtain. |
| Outcome: | Experiments show that the proposed model can generate informative text and high-resolution image responses. |
STARD: A Chinese Statute Retrieval Dataset Derived from Real-life Queries by Non-professionals (2024.findings-emnlp)
Copied to clipboard
Weihang Su, Yiran Hu, Anzhe Xie, Qingyao Ai, Quezi Bing, Ning Zheng, Yun Liu, Weixing Shen, Yiqun Liu
| Challenge: | Existing statute retrieval benchmarks emphasize formal and professional queries from sources like bar exams and legal case documents . existing retrieval approaches that lack domain-specific knowledge may struggle to capture the meanings of specialized terms accurately. |
| Approach: | They propose a dataset that captures the complexity and diversity of real queries from the general public. |
| Outcome: | The proposed dataset captures the complexity and diversity of real queries from the general public. |
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning (2026.acl-long)
Copied to clipboard
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Binbin Zheng, Chaowen Hu, Zekai Shao, Cong Qin, Lu Pan, Ke Zeng, Xunliang Cai
| Challenge: | Existing RLVR algorithms rely on rigid, uniform, and symmetric trust region mechanisms . current algorithms lack robustness, asymmetric signal reliability and inefficient gradient utilization . |
| Approach: | They propose a framework to harmonize three dimensions of RLVR algorithms, a paper argues . a binary cutoff is used to discard valuable reinforcement signals, they argue . |
| Outcome: | The proposed framework outperforms baselines in evaluating a robust RLVR solution. |
From log 𝜋 to 𝜋: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight (2026.acl-long)
Copied to clipboard
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu, Cong Qin, Zekai Shao, Binbin Zheng, Lu Pan, Ke Zeng
| Challenge: | Standard algorithms for Large Language Models (LLMs) enforce stability via "hard clipping" but relying on log-probability gradient yields divergent weights as probabilities vanish, destabilizing LLM training. |
| Approach: | They propose a decoupled gradient policy optimization that uses a decay mechanism to decouple the probability of a boundary token. |
| Outcome: | The proposed algorithm outperforms baselines on various mathematical benchmarks. |
Training-Free Test-Time Contrastive Learning for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training-free alternatives to training-based models are static or depend on external guidance. |
| Approach: | They propose a training-free adaptation framework that enables a frozen LLM to improve online by distilling supervision from its own inference experiences. |
| Outcome: | The proposed framework outperforms existing test-time adaptation methods under online evaluation. |
Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)
Copied to clipboard
Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao
| Challenge: | Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs . |
| Approach: | They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained . |
| Outcome: | The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency. |
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)
Copied to clipboard
Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song
| Challenge: | Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage. |
| Approach: | They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality. |
G-Cap: A Game Character Caption Generator (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on Large Vision-Language Models (LVLMs) primarily focus on real-world scenarios, leaving surreal, highly stylized, and semantically hybrid virtual-world situations significantly underexplored. |
| Approach: | They propose to use a manually annotated benchmark to evaluate LVLMs' ability to perceive and describe game character from the virtual-world. |
| Outcome: | The proposed task evaluates LVLMs’ ability to perceive and describe game character from the virtual-world. |
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)
Copied to clipboard
Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li
| Challenge: | Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). |
| Approach: | They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning. |
| Outcome: | The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks. |
Knowledge-Centric Hallucination Detection (2024.emnlp-main)
Copied to clipboard
Xiangkun Hu, Dongyu Ru, Lin Qiu, Qipeng Guo, Tianhang Zhang, Yang Xu, Yun Luo, Pengfei Liu, Yue Zhang, Zheng Zhang
| Challenge: | Large Language Models (LLMs) have shown impressive capabilities but a tendency to hallucinate. |
| Approach: | They propose a framework that introduces claim-triplets to represent claims in LLM responses and evaluates them against a reference. |
| Outcome: | The proposed framework outperforms prior methods by 18.2 to 27.2 points on a benchmark spanning various NLP tasks and annotated 11k claim-triplets from 2.1k responses by seven LLMs. |
AIR: Complex Instruction Generation via Automatic Iterative Refinement (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for generating complex instructions are resource-intensive and lack diversity. |
| Approach: | They propose a framework to generate complex instructions with constraints using a document-generated initial instruction and an iterative refinement framework to incorporate LLM-as-judge guidance. |
| Outcome: | The proposed framework significantly outperforms existing methods for generating complex instructions, and outperformed existing methods. |
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents (2025.findings-emnlp)
Copied to clipboard
Pengzhou Cheng, Haowen Hu, Zheng Wu, Zongru Wu, Tianjie Ju, Daizong Ding, Zhuosheng Zhang, Gongshen Liu
| Challenge: | MLLM-powered GUI agents expose multiple interaction-level triggers, causing backdoor attacks . backdoor injection maximizes feature difference across sample classes, improving flexibility . |
| Approach: | They propose a framework for red-teaming backdoor attacks using MLLMs . they construct composite triggers by combining goal and interaction levels . |
| Outcome: | The proposed framework is effective and stealthy for red-teaming backdoor attacks. |
ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, legal claims are not being used by non-professionals. |
| Approach: | They construct a dataset for Chinese legal claim generation task and then use it to evaluate the generated claims. |
| Outcome: | The proposed dataset is the first for the Chinese legal claim generation task and will be made publicly available. |
Joint Document-Level Event Extraction via Token-Token Bidirectional Event Completed Graph (2023.acl-long)
Copied to clipboard
| Challenge: | a joint exaction method can be used to extract document-level event records . it avoids inefficiency and error propagation issues in traditional pipeline methods . |
| Approach: | They propose a joint exaction method that can avoid inefficiency and error propagation issues . they propose eType-Role1-Roul2 as the edge type to reveal which tokens play argument roles . |
| Outcome: | The proposed method can avoid inefficiency and error propagation issues in traditional pipeline methods. |
Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches involve models iterating and improving their previous responses based on internal reflection ability or external feedback. |
| Approach: | They propose a reflection framework that leverages meta-thoughts and self-consistency to enhance the iterative reflection capability of Large LanguageModels. |
| Outcome: | The proposed framework achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability. |
E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models (2024.findings-acl)
Copied to clipboard
Jinchang Hou, Chang Ao, Haihong Wu, Xiangtao Kong, Zhigang Zheng, Daijia Tang, Chengming Li, Xiping Hu, Ruifeng Xu, Shiwen Ni, Min Yang
| Challenge: | despite the rapid development of Large Language Models, there is no dedicated benchmark for evaluating LLMs in Chinese K-12 education. |
| Approach: | They propose to develop a benchmark specifically tailored for Chinese K-12 education. |
| Outcome: | EVAL is the first evaluation benchmark specifically tailored for Chinese K-12 education. |
Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly deployed as agents that invoke external tools through structured function calls. |
| Approach: | They introduce a diagnostic benchmark and conduct a systematic evaluation of multilingual tool calling across Chinese, Hindi, and the low-resource language Igbo. |
| Outcome: | The proposed benchmarks show that multilingual tool calling fails despite correct intent understanding and tool selection. |
CycleOIE: A Low-Resource Training Framework For Open Information Extraction (2025.coling-main)
Copied to clipboard
Zhihong Jin, Chunhong Zhang, Zheng Hu, Jibin Yu, Ruiqi Ma, Qingyun Chen, Xiaohao Liao, Yanxing Zhang
| Challenge: | Open Information Extraction (OpenIE) models rely heavily on large amounts of annotated data. |
| Approach: | They propose a training framework that maximizes data efficiency through a cycle-consistency mechanism. |
| Outcome: | The proposed approach improves the quality of training data by curating low-quality datasets annotated by a large language model. |
Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to short text clustering are prone to degenerate solutions and noisy data. |
| Approach: | They propose a model to improve robustness against imbalanced and noisy data . they propose self-adaptive optimal transport and class-wise contrastive learning . |
| Outcome: | The proposed model outperforms the state-of-the-art models on eight short text clustering datasets. |
Dual Cache for Long Document Neural Coreference Resolution (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies show the effectiveness of cache-based neural coreference resolution models on long documents. |
| Approach: | They propose a hybrid cache that integrates two eviction policies to capture global and local entities separately and improves F1 score of coreference by 0.7 5.7pt. |
| Outcome: | The proposed model outperforms existing models on four benchmarks while saving up to 83% of inference time. |
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)
Copied to clipboard
Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song
| Challenge: | a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks. |
| Approach: | They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains . |
| Outcome: | a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively . |
Dialogue Meaning Representation for Task-Oriented Dialogue Systems (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on dialogue meaning representations is limited in scalability for complex expressions. |
| Approach: | They propose a pliable and easily extendable representation for task-oriented dialogue . they propose an inheritance hierarchy mechanism focusing on domain extensibility . |
| Outcome: | The proposed representation can be easily extended to a task-oriented dialogue dataset. |
FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis (2025.findings-acl)
Copied to clipboard
Yilun Zheng, Sha Li, Fangkun Wu, Yang Ziyi, Lin Hongchao, Zhichao Hu, Cai Xinjun, Ziming Wang, Jinxuan Chen, Sitao Luan, Jiahao Xu, Lihui Chen
| Challenge: | Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own . limited available data and deficient diversity in current datasets hinder study of parody . |
| Approach: | They build a dataset of parody users and annotated comments from both English and Chinese corpora to test parody detection and comment sentiment analysis. |
| Outcome: | The proposed datasets provide richer contextual information, which is lacking in existing datasets. |
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multi-role dialogue summarization favor surface-level imitation of references rather than genuine gains in faithfulness or alignment with human preferences. |
| Approach: | They propose a framework that couples explicit cognitive-style reasoning with reward-based optimization for multi-role dialogue summarization. |
| Outcome: | The proposed framework matches strong baselines on ROUGE and BERTScore, while in-depth analysis on SAMSum shows clear gains in factual faithfulness and model-based preference alignment. |
GRAG: Graph Retrieval-Augmented Generation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and is not suitable for networked documents. |
| Approach: | They propose a novel divide-and-conquer strategy that retrieves optimal subgraph structure in linear time. |
| Outcome: | The proposed approach outperforms current state-of-the-art methods on graph reasoning benchmarks. |
Improving Knowledge Production Efficiency With Question Answering on Conversation (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing researches on conversation-based QA focus on document-based tasks . current researche focuses on document based tasks, but there is a lack of researche on conversation based qa . |
| Approach: | They propose a multi-span extraction model on conversation-based QA and introduce continual pre-training and multi-task learning schemes to further improve model performance. |
| Outcome: | The proposed model outperforms baseline on two Chinese datasets and will be released for research purposes. |
Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)
Copied to clipboard
Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang
| Challenge: | characterization imaging data is fundamental to acquiring materials information. |
| Approach: | a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise. |
| Outcome: | a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions . |
A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum, Evidence and Experiences (2025.findings-acl)
Copied to clipboard
Jiaxin Shen, Jinan Xu, Huiqi Hu, Luyi Lin, Guoyang Ma, Fei Zheng, Fandong Meng, Jie Zhou, Wenjuan Han
| Challenge: | a recent study focuses on generating impartial and interpretable judicial judgments based on established criminal fact. |
| Approach: | They propose a law reasoning schema enriched with hierarchical factum probandum, evidence, and implicit experience that enables public scrutiny and preventing bias. |
| Outcome: | The proposed schema enables public scrutiny and prevents bias in the "Intelligent Court" it employs a suite of legal analysis tools to address the challenge task. |
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods neglect stylistic modeling and rely on static thresholds, which greatly limits the detection performance. |
| Approach: | They propose a framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation. |
| Outcome: | The proposed framework achieves an average improvement 11.34% in detection performance compared to baselines. |
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models (2025.findings-acl)
Copied to clipboard
Shuliang Liu, Hongyi Liu, Aiwei Liu, Duan Bingchen, Zheng Qi, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu
| Challenge: | Existing methods for detection of misinformation generated by large language models fail to mitigate societal risks . authors propose a paradigm shift from passive detection to anticipatory mitigation strategies . existing defenses remain reactionary in an era demanding proactive defense, authors say . |
| Approach: | They propose a three-pillar approach to prevent misinformation by fortifying integrity of training data and inference reliability by embedding self-corrective mechanisms during reasoning. |
| Outcome: | The proposed framework improves existing methods in misinformation prevention by 63% . it demonstrates that existing methods exhibit false negative rates against misinformation . |
Refiner: Restructure Retrieved Content Efficiently to Advance Question-Answering Capabilities (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. |
| Approach: | They propose an end-to-end extract-and-restructure paradigm that leverages a single decoder-only LLM to adaptively extract query-relevant contents verbatim along with the necessary context. |
| Outcome: | Experiments show that a trained Refiner outperforms state-of-the-art RAG and compressing approaches in multiple tasks. |
A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges (2025.findings-acl)
Copied to clipboard
Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, Xuming Hu
| Challenge: | This survey provides **the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models** . integrating large language model with mathematical reasoning tasks is becoming significant as AI advances . |
| Approach: | They review over 200 studies published since 2021 and examine the state-of-the-art developments in Math-LLMs . they identify five major challenges hindering the realization of AGI in this domain . |
| Outcome: | The authors examine the state-of-the-art developments in Math-LLMs with a focus on multimodal settings. |
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens (2025.findings-acl)
Copied to clipboard
Shaoshen Chen, Yangning Li, Zishan Xu, Yongqin Zeng, Shunlong Wu, Xinshuo Hu, Zifei Shan, Xin Su, Jiwei Tang, Yinghui Li, Hai-Tao Zheng
| Challenge: | Existing semantic vector-based compression methods do not account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunk. |
| Approach: | They propose a method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression. |
| Outcome: | The proposed method surpasses state-of-the-art methods on long context tasks. |
CoLAKE: Contextualized Language and Knowledge Embedding (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models for integrating factual knowledge into pre-trained language models are shallow, static, and separately pre-train entities. |
| Approach: | They propose a method which integrates knowledge contexts from large-scale knowledge bases into a unified data structure. |
| Outcome: | The proposed model outperforms existing models on knowledge-driven tasks and knowledge probing tasks. |
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning (2025.findings-acl)
Copied to clipboard
Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu
| Challenge: | Existing methods for MU forget quality and model utility are not fully explored for safety in MLLMs. |
| Approach: | They propose a safety unlearning benchmark for MLLMs to measure over-forgetting . they propose MU methods to forget quality and model utility . |
| Outcome: | The proposed method reduces over-forgetting by 79.5% while maintaining forget quality and model utility. |
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)
Copied to clipboard
Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang
| Challenge: | Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data . |
| Approach: | They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation. |
| Outcome: | The proposed framework outperforms open-source baselines and is competitive with GPT-5. |
LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding (2026.acl-long)
Copied to clipboard
Zhivar Sourati, Zheng Wang, Marianne Menglin Liu, Yazhe Hu, Mengqing Guo, Sujeeth Bharadwaj, Kyu J. Han, Tao Sheng, Sujith Ravi, Morteza Dehghani, Dan Roth
| Challenge: | Conventional retrieval-augmented generation (RAG) methods encode content in isolated chunks during ingestion, losing structural and cross-page dependencies, and retrieve a fixed number of pages at inference. |
| Approach: | They propose a Layout-Aware Dynamic RAG framework that encodes content in isolated chunks during ingestion and retrieves a fixed number of pages at inference. |
| Outcome: | Experiments on MMLongBench-Doc, LongDocURL, DUDE, and MP-DoxVQA show that LAD-RAG improves retrieval, achieving over 90% perfect recall on average without any top-k tuning, and outperforming baseline retrievers by up to 20% in recall at comparable noise levels. |
More than Text: Multi-modal Chinese Word Segmentation (2021.acl-short)
Copied to clipboard
| Challenge: | Currently, word segmentation is performed in many languages without word delimiters. |
| Approach: | They propose to combine the multi-modality to perform Chinese word segmentation . they propose a time-dependent multi-module interactive model to integrate multi-modality information . |
| Outcome: | The proposed model integrates multi-modal information for word sequence labeling with Chinese language as target . the proposed model performs well on three training sets on Chinese and other languages without word delimiters. |
MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in machine learning (MU) have enabled the selective removal of private or sensitive information encoded within deep neural networks. |
| Approach: | They propose to "reformulate" the task of multimodal MU in the era of MLLMs by preserving only the visual patterns associated with a given entity while preserving the corresponding textual knowledge. |
| Outcome: | The proposed method surpasses baselines that finetuned MLLMs with VQA data directly through Gradient Ascent (GA) or Negative Preference Optimization (NPO), across all evaluation dimensions. |
Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing research focuses on object-level or attribute-level hallucinations, neglecting the more complex relation hallucinosities. |
| Approach: | They propose a comprehensive benchmark targeting relation hallucinations comprising over 20,000 real-world samples and a confidence-based mitigation strategy which reduces the halluciation rate by an average of 9.75% across three datasets. |
| Outcome: | The proposed approach reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot. |
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) evolve into agentic systems capable of autonomous tool invocation and complex reasoning. |
| Approach: | They propose a trajectory-level preference benchmark to evaluate judges' ability to distinguish preferred versus distractor agent trajectories in tool-integrated environments. |
| Outcome: | The proposed benchmark evaluates how well judges distinguish preferred versus distractor agent trajectories in complex tool-using scenarios. |
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)
Copied to clipboard
Yancheng He, Shilong Li, Jiaheng Liu, Yingshui Tan, Weixun Wang, Hui Huang, Xingyuan Bu, Hangyu Guo, Chengwei Hu, Boren Zheng, Zhuoran Lin, Dekai Sun, Zhicheng Zheng, Wenbo Su, Bo Zheng
| Challenge: | Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence. |
| Approach: | They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics . |
| Outcome: | The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate . |
LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)
Copied to clipboard
Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen
| Challenge: | a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented. |
| Approach: | They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs). |
| Outcome: | The proposed library is based on extensive experiments in a variety of evaluation settings. |
EventRelBench: A Comprehensive Benchmark for Evaluating Event Relation Understanding in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLMs fail to capture event relationships, despite advances in NLP . a new benchmark is being developed to assess LLM's ability to extract event relationships . |
| Approach: | They propose a benchmark to assess LLMs' ability to extract event relations . EventRelBench comprises 35K diverse event relation questions . |
| Outcome: | The benchmark EventRelBench measures the performance of large language models on event relation extraction tasks. |
OSCR-Attack: One-Shot Character Level Attacks through Self-Optimizing Continuous Relaxation (2026.findings-acl)
Copied to clipboard
Lingyi Kong, Zhuo Liu, Zhanghao Hu, Qilong Qiu, Yutao Yang, Jingjing Xue, Zheng Wang, Lin Gui, Feiping Nie
| Challenge: | Character-level adversarial attacks preserve semantics but are costly and inefficient . generative LLMs are gaining popularity due to their uncertainty and vulnerability to textual adversarials . |
| Approach: | They propose an end-to-end framework that transforms discrete choices into continuous representations and a conflict resolution strategy that maps them back into discrete insertion operations. |
| Outcome: | The proposed framework improves ASR by 21.45% points and accelerates the attack by 3.66 times compared to baselines. |
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)
Copied to clipboard
Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao
| Challenge: | Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL). |
| Approach: | They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
| Outcome: | The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
Toward Fully Exploiting Heterogeneous Corpus:A Decoupled Named Entity Recognition Model with Two-stage Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a fundamental and widely used task in natural language processing. |
| Approach: | They propose a decoupled NER model with two-stage training to take advantage of heterogeneous corpus, including dictionaries, distantly supervised instances, and human-annotated instances. |
| Outcome: | Empirical results show that the proposed model improves against baselines and can be scaled to a large extent. |
Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for large language models (LLMs) have been used to prompt different reasoning thoughts, such as Chain of Thought and Program of Though. |
| Approach: | They propose a framework that prompts large language models with diverse reasoning thoughts by iterating between different prompting methods. |
| Outcome: | The proposed framework is able to generate multiple reasoning thoughts in 10 popular math reasoning datasets and is orthogonal to recent work that makes improvements on single reasoning methods and can generalise to logical reasoning domain. |
Multi-Document Event Extraction Using Large and Small Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to multi-document event extraction have limited attention . despite its practical significance, this task has inherent challenges . |
| Approach: | They propose a collaborative framework that integrates large language models for multi-step reasoning and fine-tuned small language models to handle key subtasks. |
| Outcome: | The proposed framework outperforms existing methods and provides new insights into collaborative reasoning to tackle the complexities of multi-document event extraction. |
Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries. |
| Approach: | They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios. |
| Outcome: | The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities. |
PerSphere: A Comprehensive Framework for Multi-Faceted Perspective Retrieval and Summarization (2025.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that the main challenge lies in long context and perspective extraction. |
| Approach: | They propose a benchmark to facilitate multi-faceted perspective retrieval and summarization . they propose measurable metrics to evaluate the comprehensiveness of the retrieval pipeline . |
| Outcome: | The proposed system breaks free from information silos by combining two opposing claims . it can be used to extract multiple perspectives and improve performance on the platform . |
Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations of multi-hop question answering systems focus on comparing final answers of reasoning method and given ground-truths. |
| Approach: | They propose a "Planner-Executor-Reasoner" architecture that evaluates reasoning . they propose PER-DP and PER QA architectures that provide ground-truths . |
| Outcome: | The proposed model improves the performance of multi-hop question answering systems. |
GraphNarrator: Generating Textual Explanations for Graph Neural Networks (2025.acl-long)
Copied to clipboard
| Challenge: | Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis. |
| Approach: | They propose to use a generative language model to map input-output pairs to explanations reflecting the model’s decision-making process to generate a model that generates pseudo-labels that capture the model's decisions from saliency-based explanations. |
| Outcome: | Extensive experiments show that GraphNarrator produces human-preferred explanations that are faithful, concise, and human-like. |
Value of Information: A Framework for Human–Agent Communication (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to large language model (LLM) agents fail to account for stakes of different decisions. |
| Approach: | They propose a framework that balances task risk, query ambiguity, user effort . they use a value-of-information framework to dynamically weigh the expected utility gain . |
| Outcome: | The proposed model matches or exceeds the best manually-tuned baselines in four domains . it explicitly balances task risk, query ambiguity, and user effort . |
OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)
Copied to clipboard
Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou
| Challenge: | Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs. |
| Approach: | They propose a framework that integrates dialogue, reasoning, and personalized recommendation. |
| Outcome: | Experiments across public benchmarks show state-of-the-art performance. |
Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest (2022.coling-1)
Copied to clipboard
| Challenge: | Medical relation extraction (MRE) tasks aims to extract relations between entities in medical literature. |
| Approach: | They propose to combine semantic and syntactic information from medical texts by using causal explanation theory. |
| Outcome: | Empirically, the proposed model outperforms existing methods on benchmark medical datasets. |
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)
Copied to clipboard
Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang
| Challenge: | Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction. |
| Approach: | They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack. |
| Outcome: | The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses. |
AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods treat three modal features equally, without distinguishing the importance of different modalities. Existing models split the video into frames, leading to missing the global acoustic information. |
| Approach: | They propose a global Acoustic feature enhanced Modal-Order-Aware network to address these problems. |
| Outcome: | The proposed model outperforms state-of-the-art models on two public datasets. |
CLEVA: Chinese Language Models EVAluation Platform (2023.emnlp-demo)
Copied to clipboard
Yanyang Li, Jianqiao Zhao, Duo Zheng, Zi-Yuan Hu, Zhi Chen, Xiaohui Su, Yongfeng Huang, Shijia Huang, Dahua Lin, Michael Lyu, Liwei Wang
| Challenge: | Large language models (LLMs) have revolutionized natural language processing. |
| Approach: | They propose a Chinese-based platform that assesses Chinese LLMs using a standardized workflow and a unique sampling strategy. |
| Outcome: | CLEVA evaluates Chinese LLMs on a standardized workflow and a competitive leaderboard with minimal coding. |
UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models (2024.emnlp-main)
Copied to clipboard
Xinyu Pi, Mingyuan Wu, Jize Jiang, Haozhen Zheng, Beitong Tian, ChengXiang Zhai, Klara Nahrstedt, Zhiting Hu
| Challenge: | Vision-Language Models (VLMs) perform on par with larger models in general domain visual grounding and question-answering benchmarks. |
| Approach: | They propose a "Uncontextualized Uncommon Objects" benchmark to evaluate their performance on common datasets. |
| Outcome: | The proposed benchmark focuses on systematically testing VLMs with both large and small parameter counts on rare and specialized objects. |