Papers by Jing Xu

Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition (2023.acl-long)

Challenge:	Existing studies on how images are structured with texts to form coherent meanings in human cognition have not addressed the problem.
Approach:	They propose a concept of cross-modality discourse which defines how human readers couple image and text understandings.
Outcome:	The proposed model shows that trendy encoders based on multi-head attention are unable to understand cross-modality discourse and modeling texts at the output layer helps yield the-state-of-the-art results.

Copied to clipboard

Haodong Zhao, Ruifang He, Mengnan Xiao, Jing Xu

Structured Confidence–Guided Online Adaptation for LLM-based Multi-Label Classification (2026.findings-acl)

Challenge:	Multi-level implicit discourse relation recognition (MIDRR) aims at identifying hierarchical discourse relations among arguments.
Approach:	They propose a prompt-based multi-level implicit discourse relation recognition framework that leverages parameter-efficient prompt tuning to drive inputted arguments to match the pre-trained space.
Outcome:	The proposed framework achieves comparable results on PDTB 2.0 and 3.0 using about 0.1% trainable parameters compared with baselines.

Copied to clipboard

Pengyu Xu, JingRen Hou, Liping Jing, Jian Yu

Information Retrieval

Challenge:	Large language models (LLMs) enable zero-shot and few-shot multi-label text classification . but most approaches perform static inference and degrade under streaming test data .
Approach:	They propose a structured confidence-guided online adaptation framework for LLM-based multi-label generation without parameter updates.
Outcome:	The proposed framework improves Micro-F1 and Macro-F1, with the largest gains on long-tail labels.

P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completion (2021.findings-emnlp)

Copied to clipboard

Jingwen Xu, Jing Zhang, Xirui Ke, Yuxiao Dong, Hong Chen, Cuiping Li, Yongbin Liu

S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation (2022.aacl-main)

Challenge:	Existing methods to encode and match entity pairs have only a few observed reference entity pairs.
Approach:	They propose a model that infers and leverages paths that can expressively encode the relation of two entities.
Outcome:	The proposed model outperforms the state-of-the-art models by 11.2– 14.2% in terms of Hits@1.

Copied to clipboard

Chen Liang, Jing Xu, Yangkun Lin, Chong Yang, Yongliang Wang

VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels (2026.acl-long)

Challenge:	Emotion recognition in conversation (ERC) is a task arousing increasing interest in many fields.
Approach:	They propose a novel GNN-based ERC model that captures speaker and position information.
Outcome:	The proposed model captures speaker and position-aware conversation structure information.

Copied to clipboard

Yixiao He, Menghao Zhang, Haifeng Sun, Jing Wang, Kangheng Lin, Jinghan Wang, Chenye Xu, Pengfei Ren, Qi Qi, Jingyu Wang

Exploring Mode Connectivity for Pre-trained Language Models (2022.emnlp-main)

Challenge:	Recent advances in Video Large Language Models (Video-LLMs) enhance the ability of VAU models to describe and interpret anomalies.
Approach:	They propose a benchmark that explicitly defines anomalies across five semantic levels and provides detailed temporal boundaries and detailed textual descriptions for each.
Outcome:	The proposed benchmark defines anomalies across five semantic levels and provides detailed descriptions for each.

Copied to clipboard

Yujia Qin, Cheng Qian, Jing Yi, Weize Chen, Yankai Lin, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

Improving Hate Speech Detection by Fusing Textual and User Interaction Representations in Online Communities (2026.acl-industry)

Challenge:	Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found.
Approach:	They investigate the geometric connections of different minima through the lens of mode connectivity, which measures whether two minima can be connected with a low-loss path.
Outcome:	The proposed model can be used to find low-loss paths between two minima, and to understand how their mode connectivity affects their task knowledge.

Copied to clipboard

Xu Gao, Dong Jing, Kee-hung Lai

Representation Learning

Challenge:	Existing studies on toxic content in online communities are limited by the scarcity of data that align textual content with comprehensive social interactions.
Approach:	They propose a user-aware hate speech detection framework that effectively fuses textual semantics with social interaction representations to provide pragmatic context for disambiguation.
Outcome:	The proposed framework outperforms strong text-only baselines by over 3.6%, validating the critical role of social context in enhancing detection accuracy.

Knowledge Inheritance for Pre-trained Language Models (2022.naacl-main)

Copied to clipboard

Yujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Beyond Goldfish Memory: Long-Term Open-Domain Conversation (2022.acl-long)

Challenge:	Existing large-scale pre-trained language models are mainly trained from scratch individually, ignoring that many well-taught PLMs are available.
Approach:	They propose a pre-training framework called knowledge inheritance and propose auxiliary supervision to efficiently learn larger PLMs.
Outcome:	The proposed framework can be used to train large-scale language models with huge parameters and a large dataset can be adapted to domain adaptation and knowledge transfer.

Copied to clipboard

Jing Xu, Arthur Szlam, Jason Weston

Knowledge-augmented Self-training of A Question Rewriter for Conversational Knowledge Base Question Answering (2022.findings-emnlp)

Challenge:	Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context.
Approach:	They propose to use retrieval-augmented methods to summarize and recall past conversations to improve their models.
Outcome:	The proposed models outperform the current state-of-the-art models on human-human chat sessions in both automatic and human evaluations.

Copied to clipboard

Xirui Ke, Jing Zhang, Xin Lv, Yiqi Xu, Shulin Cao, Cuiping Li, Hong Chen, Juanzi Li

#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention (2021.emnlp-main)

Challenge:	Recent rise of conversational applications has promoted the development of conversation KBQA (ConvKBQA).
Approach:	They propose a framework to produce a full-fledged rewritten question based on conversation history and then reason the answer by existing single-turn KBQA models.
Outcome:	The proposed framework produces a full-fledged rewritten question based on the conversation history and reasoned the answer by existing single-turn KBQA models.

Copied to clipboard

Yuji Zhang, Yubo Zhang, Chunpu Xu, Jing Li, Ziyan Jiang, Baolin Peng

Tagging

Challenge:	Existing methods based on latent topics cannot capture user interests and thus can't be used to predict how likely a user will post with a hashtag.
Approach:	They propose a personalized topic attention model that captures salient contents to personalize hashtag contexts by predicting how likely a user will post with a hashtag.
Outcome:	The proposed model significantly outperforms the state-of-the-art recommendation approach without exploiting latent topics.

Noisy Multi-Label Text Classification via Instance-Label Pair Correction (2024.findings-naacl)

Copied to clipboard

Pengyu Xu, Mingyang Song, Linkaida Liu, Bing Liu, Hongjian Sun, Liping Jing, Jian Yu

Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models (2025.acl-long)

Challenge:	Noise is a significant challenge for machine learning models, especially deep learning models.
Approach:	They propose a holistic selection metric that identifies noisy pairs while considering global loss information and instance-specific ranking information.
Outcome:	The proposed approach significantly improves performance in noisy multi-label text classification tasks.

Copied to clipboard

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, Richard Yi Da Xu, Yunya Song, Xian Yang

Chain-of-Verification Reduces Hallucination in Large Language Models (2024.findings-acl)

Challenge:	Existing models struggle to balance predictive accuracy with human-understandable rationales.
Approach:	They propose to enhance LLMs by leveraging rationale distillation and domain knowledge injection for trustworthy multimodal rationale generation.
Outcome:	Experiments on real-world medical datasets show that ClinRaGen achieves state-of-the-art performance in disease diagnosis and rationale generation.

Copied to clipboard

Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston

KARL: Reinforcement Learning for LLM Agents on Multi-Turn Knowledge-Intensive Agentic Tasks (2026.acl-long)

Challenge:	Large language models can generate plausible but incorrect factual information, termed hallucinations, but they can still fail on lesser known facts.
Approach:	They develop a method that allows language models to deliberate on the responses they give in order to correct their errors.
Outcome:	The proposed method decreases hallucinations across a variety of tasks, including list-based questions, closed book MultiSpanQA and longform text generation.

Copied to clipboard

Xueqiao Sun, Xiao Liu, Bowen Lv, Hanchen Zhang, Bohao Jing, Zehan Qi, Yifan Xu, Yuxiao Dong, Jie Tang

An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4 (2025.findings-acl)

Challenge:	Large Language Models have shown remarkable potential as autonomous agents, but their effectiveness in knowledge-intensive tasks remains limited by passive knowledge utilization.
Approach:	They propose a framework that enables LLM agents to dynamically explore structured knowledge sources through multi-turn interactions.
Outcome:	The proposed framework outperforms existing retrieval-augmented approaches on knowledge graph and database tasks while maximizing tool-use behaviors end-to-end.

Copied to clipboard

Hui Huang, Xingyuan Bu, Hongli Zhou, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, Tiejun Zhao

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning (2025.emnlp-main)

Challenge:	Recent studies have fine-tuned judge models based on open-source LLMs to evaluate the quality of other LLM.
Approach:	They propose to use open-source LLMs to evaluate Large Language Models (LLMs) their empirical results show that the models underperform GPT-4 in several dimensions .
Outcome:	The proposed models outperform GPT-4 on several dimensions including generalizability, fairness and adaptability.

Copied to clipboard

Wenbin Hu, Haoran Li, Huihao Jing, Qi Hu, Ziqian Zeng, Sirui Han, Xu Heli, Tianshu Chu, Peizhao Hu, Yangqiu Song

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge (2025.emnlp-main)

Challenge:	Current mitigation strategies fail to preserve contextual reasoning capabilities in risky scenarios, leading to systemic risks for legal compliance.
Approach:	They propose to use reinforcement learning with a rule-based reward to incentivize contextual reasoning capabilities while enhancing compliance with safety and privacy norms.
Outcome:	The proposed model outperforms Qwen2.5-7B-Instruct model in safety and privacy benchmarks and achieves +8.58% accuracy improvement.

Copied to clipboard

Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason E Weston, Sainbayar Sukhbaatar

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)

Challenge:	Existing methods for improving large language models have focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training.
Approach:	They propose an iterative Meta-Rewarding step where the model judges its own judgements and uses that feedback to refine its judgment skills.
Outcome:	The proposed model improves Llama-3-8B-Instruct from 22.9% to 39.4% on AlpacaEval 2 and 20.6% to 29.1% on Arena-Hard.

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

Reasoning

Challenge:	Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases.
Approach:	They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases.
Outcome:	The proposed framework synthesizes more generalized training data to address these model weaknesses.

Mitigating Over-Generation for Unsupervised Keyphrase Extraction with Heterogeneous Centrality Detection (2023.emnlp-main)

Copied to clipboard

Mingyang Song, Pengyu Xu, Yi Feng, Huafeng Liu, Liping Jing

Recipes for Building an Open-Domain Chatbot (2021.eacl-main)

Challenge:	Existing keyphrase extraction models incorrectly determine a keyphrase as a phrase but output other candidates as keyphrases because they contain the same word.
Approach:	They propose a new approach that detects both implicit and explicit centrality within a heterogeneous graph as the importance score of each candidate keyphrase.
Outcome:	The proposed approach outperforms state-of-the-art keyphrase extraction models on three benchmark datasets.

Copied to clipboard

Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, Jason Weston

FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness (2026.findings-acl)

Challenge:	Existing work shows that scaling models in the number of parameters and the size of the data they are trained on gives improved results, but other factors are important.
Approach:	They propose to build open-domain chatbots that can be scaled to improve their performance . they use a blend of cognitive and cognitive skills to build a model that combines these skills .
Outcome:	The proposed models outperform existing approaches in multi-turn dialogue on engagingness and humanness measurements.

Copied to clipboard

Xiaoning Dong, Chengyan Wu, Yajie Wen, Yu Chen, Yun Xue, Zhang Jing, Wei Xu, Bolei Ma

Information Retrieval

Challenge:	Existing approaches to correct factually inaccurate outputs are lacking the semantic richness needed to properly understand its internal states of trustworthiness and honesty.
Approach:	They propose a framework for factuality alignment that integrates natural-language uncertainty signals with external knowledge and computes confidence scores and semantic entropy from LLM outputs.
Outcome:	Extensive experiments on four knowledge-intensive benchmarks show that FAITH improves the factual accuracy and truthfulness of Large Language Models (LLMs).

The CRINGE Loss: Learning what language not to model (2023.acl-long)

Copied to clipboard

Leonard Adolphs, Tianyu Gao, Jing Xu, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston

Challenge:	Standard language model training uses gold human documents or human-human interaction data and treats all training data as positive examples.
Approach:	They propose a procedure to train with negative examples using the "CRINGE" loss technique and use it to train models with such data.
Outcome:	The proposed procedure outperforms multiple strong baselines and is simple to train and implement.

Continual Dialogue State Tracking via Example-Guided Question Answering (2023.emnlp-main)

Copied to clipboard

Hyundong Cho, Andrea Madotto, Zhaojiang Lin, Khyathi Chandu, Satwik Kottur, Jing Xu, Jonathan May, Chinnadhurai Sankar

Enhancing Multi-Label Text Classification under Label-Dependent Noise: A Label-Specific Denoising Framework (2024.findings-emnlp)

Challenge:	Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services causes catastrophic forgetting.
Approach:	They propose to reformulate dialogue state tracking (DST) as a bundle of example-guided question answering tasks to minimize the task shift between services.
Outcome:	The proposed model achieves state-of-the-art performance on DST continual learning metrics without relying on any complex regularization or parameter expansion methods.

Copied to clipboard

Pengyu Xu, Liping Jing, Jian Yu

AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)

Challenge:	Existing noisy multi-label text classification methods rely on the class-conditional noise assumption, but in practice, noisy labels exhibit a certain degree of correlation with the true labels.
Approach:	They propose a label-specific denoising framework to counteract label-dependent noise by evaluating loss information, ranking information, and feature centroid.
Outcome:	The proposed framework significantly improves over existing state-of-the-art models under both synthetic and real-world noise conditions.

Copied to clipboard

Junjie Wang, Yicheng Chen, Wangshu Zhang, Sen Hu, Teng Xu, Jing Zheng

Modularized Interaction Network for Named Entity Recognition (2021.acl-long)

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.

Copied to clipboard

Fei Li, Zheng Wang, Siu Cheung Hui, Lejian Liao, Dandan Song, Jing Xu, Guoxiu He, Meihuizi Jia

Erxin Yu, Jing Li, Chunpu Xu

Challenge:	Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information.
Approach:	They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies.
Outcome:	The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets.

Copied to clipboard

MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Challenge:	Recent work focuses on generic human responses without considering popularity factors in the social contexts.
Approach:	They propose Popularity-Aligned Language Models to distinguish responses liked by a larger audience through reinforcement learning.
Outcome:	The proposed model can distinguish responses liked by a larger audience through reinforcement learning.

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

Boosting Text-to-SQL through Multi-grained Error Identification (2025.coling-main)

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 .

Copied to clipboard

Bo Xu, Shufei Li, Hongyu Jing, Ming Du, Hui Song, Hongya Wang, Yanghua Xiao

Programming Languages in NLP

Challenge:	Existing methods for error identification often overlook validation of generated results . text-to-SQL is a technology that converts natural language questions into executable SQL queries .
Approach:	They propose to integrate a multi-grained error identification method into existing methods to detect SQL errors.
Outcome:	The proposed method can be integrated as a plugin into various methods, providing effective error identification and correction capabilities.

AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Copied to clipboard

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang

Topic-Guided Self-Introduction Generation for Social Media Users (2023.findings-acl)

Challenge:	Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach:	They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome:	The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.

Copied to clipboard

Chunpu Xu, Jing Li, Piji Li, Min Yang

Following Length Constraints in Instructions (2025.emnlp-main)

Challenge:	Existing studies on social media use tags to profile users, but we have found that sentence-level self-introductions are more natural and engaging.
Approach:	They propose a novel topic-guided encoder-decoder framework that uses a user's tweeting history to generate a short sentence outlining their personal interests.
Outcome:	The proposed framework outperforms existing encoder-decoder models on a large-scale Twitter dataset and shows that it is more natural and engaging than previous approaches.

Copied to clipboard

Weizhe Yuan, Ilia Kulikov, Ping Yu, Kyunghyun Cho, Sainbayar Sukhbaatar, Jason E Weston, Jing Xu

Challenge:	Existing instruction following models fail to follow length constraints in their evaluations.
Approach:	They propose to train models that can be controlled at inference time with instructions containing desired length constraints.
Outcome:	The proposed models outperform standard instruction following models in length instructed evaluations.

Separation and Fusion: A Novel Multiple Token Linking Model for Event Argument Extraction (2024.naacl-long)

Copied to clipboard

Jing Xu, Dandan Song, Siu Hui, Zhijing Wu, Meihuizi Jia, Hao Wang, Yanru Zhou, Changzhi Zhou, Ziyi Yang

EDDA: An Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection (2024.lrec-main)

Challenge:	Existing methods for event argument extraction (EAE) lack cross-event information and require longer role sequences . et al. (2017): outperforms state-of-the-art methods for EE.
Approach:	They propose a separation-and-fusion paradigm to separate the acquisition of cross-event information and fuse it into the argument extraction of a target event.
Outcome:	The proposed model outperforms the state-of-the-art models on four widely used datasets.

Copied to clipboard

Daijun Ding, Li Dong, Zhichao Huang, Guangning Xu, Xu Huang, Bo Liu, Liwen Jing, Bowen Zhang

FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for enhancing text or data are limited by lack of logical connections between generated texts and training data.
Approach:	They propose an encoder-decoder data augmentation framework that combines large language models and chain-of-thought prompting to summarize texts into target-specific if-then rationales, establishing logical relationships.
Outcome:	The proposed framework significantly improves over state-of-the-art methods on benchmark datasets while enabling interpretable rationale-based learning.

Copied to clipboard

Yanling Wang, Haoyang Li, Hao Zou, Jing Zhang, Xinlei He, Qi Li, Ke Xu

DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)

Challenge:	Existing non-factuality detection methods require response generation, which incurs significant computational overhead.
Approach:	They propose a lightweight model called Factuality Lens which effectively probes hidden representations of fact-seeking questions for the NFP task.
Outcome:	The proposed model is able to probe hidden representations of fact-seeking questions and reduce development costs.

Copied to clipboard

Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang

CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models (2025.findings-naacl)

Challenge:	Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF).
Approach:	a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance.
Outcome:	a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models .

Copied to clipboard

Shangda Wu, Yashan Wang, Ruibin Yuan, Guo Zhancheng, Xu Tan, Ge Zhang, Monan Zhou, Jing Chen, Xuefeng Mu, Yuejie Gao, Yuanliang Dong, Jiafeng Liu, Xiaobing Li, Feng Yu, Maosong Sun

TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)

Challenge:	Current music information retrieval systems struggle to meet linguistic diversity challenges . current systems struggle with text queries in non-English languages .
Approach:	They propose a music information retrieval system that supports both ABC notation and MIDI . CLaMP 2 includes a multilingual text encoder and a multiple-modal music encoder .
Outcome:	The proposed system achieves state-of-the-art results in multilingual semantic search and music classification across modalities.

Copied to clipboard

Bei Li, Yi Jing, Xu Tan, Zhen Xing, Tong Xiao, Jingbo Zhu

A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection (2023.emnlp-main)

Challenge:	Prior work has focused on treating subwords as basic units in developing such systems.
Approach:	They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences.
Outcome:	The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks.

Copied to clipboard

Geng Tu, Ran Jing, Bin Liang, Min Yang, Kam-Fai Wong, Ruifeng Xu

PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)

Challenge:	Existing studies in Emotion Recognition in Conversations (ERC) focus on capturing context-sensitive and speaker-sensitive dependencies, ignoring the unintended dataset biases of data.
Approach:	They propose a training-free debiasing framework that extracts biases from the model by generating counterfactual utterances and contexts and mitigates them using simple yet empirically robust element-wise subtraction operations.
Outcome:	Experiments on three public datasets show that the proposed framework improves generalization ability and fairness across different ERC models.

Copied to clipboard

Bingbing Wang, Jingjie Lin, Zhixin Bai, Xintong Song, Qianlong Wang, Min Yang, Xi Zeng, Jing Li, Ruifeng Xu

Sentiment Analysis

Challenge:	Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction.
Approach:	They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise.
Outcome:	The proposed framework achieves state-of-the-art on three public datasets.

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation (2024.emnlp-main)

Copied to clipboard

Xiaoze Liu, Ting Sun, Tianyang Xu, Feijie Wu, Cunxiang Wang, Xiaoqian Wang, Jing Gao

Robustness in NLP

Challenge:	Large Language Models (LLMs) have transformed machine learning but have raised significant legal concerns due to their potential to produce text that infringes on copyrights.
Approach:	They propose a lightweight, real-time defense mechanism to prevent the generation of copyrighted text by evaluating methods and testing attack strategies.
Outcome:	The proposed defense significantly reduces the volume of copyrighted text generated by LLMs by effectively refusing malicious requests.

Copied to clipboard

Erxin Yu, Jing Li, Chunpu Xu

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (2024.emnlp-main)

Challenge:	Existing studies show that the wording of tweets can significantly impact popularity, reflected by user replies, retweets, and likes.
Approach:	They propose a novel approach to generate popular quote tweets by leveraging augmented auto-responses from readers to align language generation with popularity.
Outcome:	The proposed model outperforms existing models that do not incorporate response augmentation and can generate popular quote tweets with augmented auto-responses.

Copied to clipboard

Tianyang Xu, Shujin Wu, Shizhe Diao, Xiaoze Liu, Xingyao Wang, Yangyi Chen, Jing Gao

MIND Your Reasoning: A Meta-Cognitive Intuitive-Reflective Network for Dual-Reasoning in Multimodal Stance Detection (2026.acl-long)

Challenge:	Existing approaches to elicit confidence from large language models are limited to binary or inaccurate group-level confidence estimates.
Approach:	They propose a training framework that teaches LLMs to express more fine-grained confidence estimates.
Outcome:	The proposed training framework reduces the confidence calibration error and maintains the performance of the model.

Copied to clipboard

Bingbing Wang, Zhengda Jin, Bin Liang, Wenjie Li, Jing Li, Ruifeng Xu, Min Zhang

Sentiment Analysis

Challenge:	Existing methods operate by learning to fuse modalities, leading to frequent misjudgments.
Approach:	They propose a paradigm shift from learning to fuse to *learning the reason's process' inspired by the dual-process theory of human cognition, MIND operationalizes a self-improving loop.
Outcome:	The proposed model significantly outperforms baseline models and exhibits strong generalization.

AEQ-Bench: Measuring Empathy of Omni-Modal Large Models (2026.findings-acl)

Copied to clipboard

Xuan Luo, Lewei Yao, Lanqing Hong, Kai Chen, Dehua Tao, Daxin Tan, Yukun Deng, Ruifeng Xu, Jing Li

OSCaR: Object State Captioning and State Change Representation (2024.findings-naacl)

Challenge:	Existing benchmarks focus on cognitive abilities, such as knowledge retrieval, complex reasoning, and instruction following, largely overlooking empathy evaluation.
Approach:	They propose to benchmark two core empathetic capabilities of omnimodal large models (OLMs) generating empatries by comprehending affective cues from multi-modal inputs and judging empathy of audio responses without relying on text transcription.
Outcome:	The proposed benchmark outperforms existing models with audio output capabilities but is unreliable for evaluating fine-grained paralinguistic expressiveness.

Copied to clipboard

Nguyen Nguyen, Jing Bi, Ali Vosoughi, Yapeng Tian, Pooyan Fazli, Chenliang Xu

Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts (2023.acl-long)

Challenge:	Existing methods to extrapolate and comprehend changes in object states are limited . relying on a small set of symbolic words to represent changes has restricted expressiveness of language.
Approach:	They propose a dataset and benchmark to evaluate multimodal large language models . they investigate causal relations between a concrete action and the change .
Outcome:	The proposed method achieves near parity with GPT-4V ratings across helpfulness, accuracy, reasoning, and other key metrics.

Copied to clipboard

Mounica Maddela, Megan Ung, Jing Xu, Andrea Madotto, Heather Foran, Y-Lan Boureau

Challenge:	Existing models for cognitive behavioral therapy lack specific and diverse practice material.
Approach:	They propose to use a dataset to generate unhelpful thought patterns . they propose to train and evaluate existing models to generate an abundance of practice material .
Outcome:	The proposed model can generate unlimited quantity of practice material and generate suitable reframing proposals with no or minimal additional model training required.

Grammar-based Decoding for Improved Compositional Generalization in Semantic Parsing (2023.findings-acl)

Copied to clipboard

Jing Zheng, Jyh-Herng Chow, Zhongnan Shen, Peng Xu

MLeVLM: Improve Multi-level Progressive Capabilities based on Multimodal Large Language Model for Medical Visual Question Answering (2024.findings-acl)

Challenge:	Sequence-to-sequence (seq2sequ) models have been successful in semantic parsing tasks but struggle on out-of-distribution data.
Approach:	They propose to use a large-scale dialogue dataset to evaluate compositional generalization of semantic parsing.
Outcome:	The proposed model outperforms BART- and T5-based models on the SMCalflow-CS dataset on the zero-shot learning task.

Copied to clipboard

Dexuan Xu, Yanyuan Chen, Jieyi Wang, Yue Huang, Hanpin Wang, Zhi Jin, Hongxing Wang, Weihua Yue, Jing He, Hang Li, Yu Huang

S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency (2025.naacl-long)

Challenge:	Existing MVQA models ignore multi-level progressive capabilities due to unspecific data and plain architecture.
Approach:	They propose a multi-level visual language model for medical visual question answering (MVQA) which covers multi- level questions and answers as well as reasoning processes from visual clues to semantic cognition.
Outcome:	The proposed model outperforms existing medical multimodal large language models on a multi-level instruction dataset and a feature alignment module.

Copied to clipboard

Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, XiTai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu

Augmenting Reasoning Capabilities of LLMs with Graph Structures in Knowledge Base Question Answering (2024.findings-emnlp)

Challenge:	Large language models exhibit limitations when handling complex mathematical reasoning and logical inference tasks.
Approach:	They propose a sparsification strategy to reduce token costs within Multi-agent Debate (MAD) this strategy minimizes ineffective exchanges of information and unproductive discussions among agents .
Outcome:	The proposed approach reduces token costs by up to 94.5% while maintaining performance degradation below 2.0%.

Copied to clipboard

Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Hao Wang, Jun Yang, Jing Xu, Ruanmin Cao, HaoYu Wang

DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning (2026.findings-acl)

Challenge:	Recent work uses Large Language Models (LLMs) for semantic parsing to address Knowledge Base Question Answering tasks.
Approach:	They propose a framework that augments reasoning capabilities of LLMs with Graph Structures in Knowledge Base Question Answering to retrieve question-related graph structures.
Outcome:	The proposed framework outperforms existing methods on GrailQA and WebQSP under the few-shot setting.

Copied to clipboard

Pan Yang, Jing Yang, Ruan Xiao li, Yuling Chen, Yuankai Wu, Quan Zhou, Xu Wang

ECC: Synergizing Emotion, Cause and Commonsense for Empathetic Dialogue Generation (2025.coling-main)

Challenge:	Compositional Zero-Shot Learning (CZSL) is a new research paradigm that learns sub-concepts from seen compositions and recognizes unseen novel combinations.
Approach:	They propose a Dual-Modal Semantic Disentanglement framework that integrates visual and textual information to achieve effective sub-concept disentangling.
Outcome:	The proposed framework achieves state-of-the-art performance on three benchmark datasets . it integrates a class-centroid bridge module to guide class centroids toward the textual space .

Copied to clipboard

Xu Wang, Bo Wang, Yihong Tang, Dongming Zhao, Jing Liu, Ruifang He, Yuexian Hou

When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels (2024.naacl-long)

Challenge:	Empathy improves human-machine dialogue systems by enhancing the user's experience.
Approach:	They propose a framework that leverages specialized encoders to capture the key features of emotion, cause, and commonsense and collaboratively models these through a Conditional Variational Auto-Encoder.
Outcome:	Empirical results show that the framework outperforms baseline models and offers a robust solution for empathetic dialogue generation.

Copied to clipboard

Weiyan Shi, Emily Dinan, Kurt Shuster, Jason Weston, Jing Xu

Large Language Models as Reader for Bias Detection (2025.findings-emnlp)

Challenge:	Existing dialogue models are primarily trained on human-human conversations . thumb ups/downs and gold corrections are often sparse in real-life deployment settings .
Approach:	They propose a framework to make use of binary and free-form textual human feedback.
Outcome:	The proposed framework improves the final dialogue model by using model-corrected replies.

Copied to clipboard

Xuan Luo, Jing Li, Zhong Wenzhong, Geng Tu, Ruifeng Xu

MapNav: A Novel Memory Representation via Annotated Semantic Maps for VLM-based Vision-and-Language Navigation (2025.acl-long)

Challenge:	Traditional methods analyze text from the writer’s perspective, leaving the reader’s viewpoint underexplored.
Approach:	They investigate whether large language models can be leveraged as readers for bias detection by generating reader-perspective comments.
Outcome:	The proposed model performs comparable to GPT4's in detecting bias in media content.

Copied to clipboard

Lingfeng Zhang, Xiaoshuai Hao, Qinwen Xu, Qiang Zhang, Xinyao Zhang, Pengwei Wang, Jing Zhang, Zhongyuan Wang, Shanghang Zhang, Renjing Xu

RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems (2025.coling-main)

Challenge:	Vision-language navigation (VLN) is a key task in Embodied AI . traditional approaches rely on historical observations as spatio-temporal contexts for decision making .
Approach:	They propose a vision-language navigation model that leverages an annotation system to replace historical frames.
Outcome:	The proposed model can be used as a new memory representation method in vision-language navigation . it can be applied to simulated and real-world environments, and it is validated by experiments .

Copied to clipboard

Yihong Tang, Bo Wang, Xu Wang, Dongming Zhao, Jing Liu, Ruifang He, Yuexian Hou

SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures (2022.acl-long)

Challenge:	Existing approaches to combat character hallucination are vulnerable to attack . large language models (LLMs) are capable of generating responses inconsistent with intended personas .
Approach:	They propose a novel defence strategy that generates supplemental context through narration to mitigate role-query conflicts and improve query generalization.
Outcome:	The proposed defence strategy outperforms refusal-based strategies in character hallucinations and query generalization.

Copied to clipboard

Megan Ung, Jing Xu, Y-Lan Boureau

X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability (2025.findings-emnlp)

Challenge:	Existing open-domain conversational models can easily be made to talk in inadequate ways.
Approach:	They propose a task and dataset of graceful responses to safety feedback . they collect 8k dialogues demonstrating safety failures, feedback signaling them, and a response acknowledging feedback.
Outcome:	The proposed model improves on a dataset of 8k dialogues demonstrating safety failures, feedback signaling them, and a response acknowledging the feedback.

Copied to clipboard

Xiaoya Lu, Dongrui Liu, Yi Yu, Luxin Xu, Jing Shao

Muffin: Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback (2024.findings-acl)

Challenge:	Existing methods for enhancing LLM security compromise usability, study finds . boundary-safe representations close to harmful representations are disrupted, resulting in usability decline .
Approach:	They propose a method to push harmful representations away from boundary-safe representations and obtain an exact distinction boundary.
Outcome:	The proposed method reduces over-refusal rate and maintains general capability . it pushes harmful representations away from boundary-safe representations, thereby reducing usability.

Copied to clipboard

Jiashuo Wang, Chunpu Xu, Chak Tou Leong, Wenjie Li, Jing Li

Improving Knowledge Production Efficiency With Question Answering on Conversation (2023.acl-industry)

Challenge:	Existing studies have shown that emotional support conversation models generate unhelpful responses that can hinder their effectiveness.
Approach:	They propose a model-agnostic framework called Mitigating unhelpfulness with multifaceted AI feedback for emot io nal support (Muffin) it uses a multifaceted feedback module to assess helpfulness model responses across various facets of emotional support and contrasts helpful and unhelpful responses generated by the model.
Outcome:	The proposed framework reduces the likelihood of unhelpful responses by comparing helpful and unhelpfully responses generated by previous models to improve response fluency and relevance.

Copied to clipboard

Changlin Yang, Siye Liu, Sen Hu, Wangshu Zhang, Teng Xu, Jing Zheng

Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors (2025.acl-long)

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.

Copied to clipboard

Senqi Yang, Dongyu Zhang, Jing Ren, Ziqi Xu, Xiuzhen Zhang, Yiliao Song, Hongfei Lin, Feng Xia

Sentiment Analysis

Challenge:	Metaphors are pervasive in communication, making them crucial for natural language processing.
Approach:	They propose a multicultural multimodal metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English.
Outcome:	The proposed model improves metaphor comprehension across cultural backgrounds and cultural domains.

Bot-Adversarial Dialogue for Safe Conversational Agents (2021.naacl-main)

Copied to clipboard

Jing Xu, Da Ju, Margaret Li, Y-Lan Boureau, Jason Weston, Emily Dinan

Robustness in NLP

Challenge:	a new method for evaluating chatbot safety is proposed to mimic human-generated data . a bot-adversarial dialogue model learns undesirable features from this data, a study finds .
Approach:	They propose a human-and-model-in-the-loop framework for evaluating toxicity of chatbots . they propose two methods for safe conversational agents by either training on data or ”baking-in” safety to the generative model itself.
Outcome:	The proposed methods are safer than existing models while maintaining usability metrics, the authors say . they show that the proposed methods can be used to make safer models with human-model interactions .

Business as Rulesual: A Benchmark and Framework for Business Rule Flow Modeling with LLMs (2026.acl-long)

Copied to clipboard

Chen Yang, Ruping Xu, Ruizhe Li, Bin Cao, Jing Fan

Borrowing Human Senses: Comment-Aware Self-Training for Social Media Multimodal Classification (2022.emnlp-main)

Challenge:	Existing benchmarks for extracting structured procedural knowledge from unstructured business documents are limited by simplistic schemas and shallow logical dependencies.
Approach:	They propose a framework for extracting structured procedural knowledge from unstructured business documents . they propose BREX, a carefully curated benchmark comprising 409 real-world business documents and 2,855 expert-annotated rules .
Outcome:	The proposed framework outperforms standard prompts in rule extraction and execution.

Copied to clipboard

Chunpu Xu, Jing Li

Text Classification

Challenge:	Social media users are using images and text to voice opinions and share ideas.
Approach:	They propose to use user comments to extract hinting features from user comments and explore them via self-training.
Outcome:	The proposed framework improves on four social media benchmarks for image-text relation classification, sarcasm detection, sentiment classification, and hate speech detection.

On the Role of Discriminative Models in Generative Relation Extraction (2026.acl-long)

Copied to clipboard

Guozheng Li, Peng Wang, Zijie Xu, Jing Zhou, Jiajun Liu, Ziyu Shang

MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol (2025.emnlp-main)

Challenge:	Existing methods for relation extraction (RE) are discriminative and generative . previous studies show that discriminative models can support generative RE .
Approach:	They propose a framework that leverages discriminative models to produce a top-k set of candidate relations and integrates this knowledge into generative models via in-context or prompt learning.
Outcome:	The proposed framework achieves state-of-the-art on five widely used RE benchmarks.

Copied to clipboard

Huihao Jing, Haoran Li, Wenbin Hu, Qi Hu, Xu Heli, Tianshu Chu, Peizhao Hu, Yangqiu Song

HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection (2025.emnlp-main)

Challenge:	Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, but it also brings underexplored safety risks.
Approach:	They propose a framework that addresses the missing safety mechanisms in MCP and a taxonomy that captures diverse range of unsafe behaviors observed in MMP scenarios.
Outcome:	The proposed framework improves safety performance on state-of-the-art LLMs by capturing unsafe behaviors and analyzing the results.

Copied to clipboard

Yiheng Jing, Mingming Zhang, Yong Zhuang, Jiacheng Guo, Juan Wang, Xiaoyang Xu, Wenzhe Yi, Keyan Guo, Hongxin Hu

To Paraphrase or Not: Efficient Comment Detoxification with Unsupervised Detoxifiability Discrimination (2026.eacl-short)

Challenge:	Existing methods for hateful video detection rely on unimodal analysis or feature fusion . Existing tools struggle to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor .
Approach:	They propose a reasoning-based hateful video detection framework with multimodal large language models . they integrate Chain-of-Thought reasoning to enhance multimodal interaction modeling .
Outcome:	The proposed framework outperforms existing tools on two public datasets covering English and Chinese.

Copied to clipboard

Jing Ke, Zheyong Xie, Shaosheng Cao, Tong Xu, Enhong Chen

A Simple and Efficient Learning-Style Prompting for LLM Jailbreaking (2026.findings-eacl)

Challenge:	Existing methods for detoxification of toxic comments are limited by overcorrection and data scarcity . experimental results show that DID outperforms existing methods on academic data and an industrial platform .
Approach:	They propose a paradigm that adaptively conducts filtering or paraphrasing for each toxic comment based on its detoxifiability . they propose 'detoxifiabilities-aware detoxification' that can be trained to filter or paraphrase toxic comments based upon their detoxifikatability based only on detoxificable comments .
Outcome:	Experimental results show that DID outperforms existing methods on academic and industrial data.

Copied to clipboard

Xuan Luo, Yue Wang, Zefeng He, Geng Tu, Jing Li, Ruifeng Xu

MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding (2024.emnlp-main)

Challenge:	Learning-style queries can reliably elicit harmful responses, highlighting a critical safety blind spot in modern LLMs.
Approach:	They propose a new reframing paradigm that hides intention by learning from LLMs and uses 4 conceptual components to construct learning-style queries.
Outcome:	The proposed framework achieves top attack success rates on most models and across malicious categories while maintaining high efficiency with concise prompts.

Copied to clipboard

Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, Yangqiu Song

TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios (2025.findings-acl)

Challenge:	Existing methods for acquiring large-scale intentions generate product-centric intentions without product images and incur high costs for scalability.
Approach:	They propose a multimodal framework that allows Large Vision-Language Models to infer purchase intentions from multimodal product metadata and prioritize human-centric ones.
Outcome:	The proposed framework shows that it is robust to different prompts and superior to previous methods.

Copied to clipboard

Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, Daniel Zhang-Li, Jifan Yu, Shu Zhao, Juanzi Li, Jie Tang

Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation (2025.coling-main)

Challenge:	TableLLM is a robust large language model capable of handling tabular data manipulation tasks.
Approach:	They propose a distant supervision method for training which includes a reasoning process extension strategy and a cross-way validation strategy.
Outcome:	The proposed model has 8 billion parameters and is capable of handling tabular data tasks.

Copied to clipboard

Bo Xu, Haiqi Jiang, Jie Wei, Hongyu Jing, Ming Du, Hui Song, Hongya Wang, Yanghua Xiao

Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback (2023.acl-long)

Challenge:	Current named entity recognition methods struggle with text-image mismatch problem due to a lack of visual context.
Approach:	They propose an adaptive mixup image augmentation method that generates augmented images based on matching score between text and image .
Outcome:	The proposed method can be integrated into existing models and demonstrate consistent performance improvements.

Copied to clipboard

Jing Xu, Megan Ung, Mojtaba Komeili, Kushal Arora, Y-Lan Boureau, Jason Weston

Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation (2026.acl-long)

Challenge:	Frozen models trained to mimic static datasets can never improve their performance.
Approach:	They propose to use binary quality measurements and free-form text feedback to improve conversational skills in a conversational learning framework.
Outcome:	The proposed model improves on the DIRECTOR model, which is based on binary quality measurements and free-form text feedback, and shows that iterative retraining and redeployment can improve the model.

Copied to clipboard

Jiaju Chen, Yuxuan Lu, Xiaojie Wang, Huimin Zeng, Jing Huang, Jiri Gesi, Ying Xu, Bingsheng Yao, Dakuo Wang

Challenge:	Existing "LLM-as-a-judge" evaluation frameworks are limited by persona descriptions and are not generalizable to other tasks.
Approach:	They propose a framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents and instantiate LLM agents with the persona.
Outcome:	The proposed framework can believably simulate human evaluators . it extracts stakeholders' diverse perspectives from the provided research papers and constructs personas for the agents .

CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification (2024.eacl-long)

Copied to clipboard

Yang Li, Canran Xu, Guodong Long, Tao Shen, Chongyang Tao, Jing Jiang

DAMON: A Dialogue-Aware MCTS Framework for Jailbreaking Large Language Models (2025.emnlp-main)

Challenge:	Existing methods to improve pre-trained language models for many-class classification suffer from verbalizer ambiguity . a significant disparity exists between the pre-training and fine-tuning stages of the model .
Approach:	They propose a method to tune pre-trained language models to a broad spectrum of tasks . they use an instance-dependent soft prefix to complement language verbalizers in many-class classification .
Outcome:	The proposed method outperforms baselines on many-class datasets.

Copied to clipboard

Xu Zhang, Xunjian Yin, Dinghao Jing, Huixuan Zhang, Xinyu Hu, Xiaojun Wan

Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought (2026.findings-eacl)

Challenge:	Existing methods for multi-turn attacks mainly utilize a predefined dialogue pattern, limiting their effectiveness in realistic situations.
Approach:	They propose a multi-turn jailbreak attack method that leverages Monte Carlo Tree Search to explore multi-turned conversational spaces and identifies sub-instruction sequences that induce harmful responses.
Outcome:	The proposed method can induce undesired behaviors across five LLMs and three datasets.

Copied to clipboard

Bowen Li, Ziqi Xu, Jing Ren, Renqiang Luo, Xikun Zhang, Xiuzhen Zhang, Yongli Ren, Feng Xia

CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation (2025.acl-long)

Challenge:	Existing prompting methods for Large Language Models (LLMs) suffer from excessive token usage and limited generalisability across diverse reasoning tasks.
Approach:	They propose an Adaptive Causal Prompting with Sketch-of-Thought framework that leverages structural causal models to infer the causal effect of a query on its answer.
Outcome:	The proposed framework outperforms existing prompting baselines in terms of accuracy, robustness, and computational efficiency.

Copied to clipboard

Jingqian Zhao, Bingbing Wang, Geng Tu, Yice Zhang, Qianlong Wang, Bin Liang, Jing Li, Ruifeng Xu

Self-Evaluation of Large Language Model based on Glass-box Features (2024.findings-emnlp)

Challenge:	Publicly available datasets can be used to evaluate performance of large language models . however, contamination of test data can artificially inflate model performance .
Approach:	They propose a Contamination-resilient Evaluation strategy that updates data with real-world knowledge.
Outcome:	The proposed evaluation strategy can be used to update datasets with real-world knowledge.

Copied to clipboard

Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, Tiejun Zhao, Wenpeng Lu

An Alignment-Agnostic Model for Chinese Text Error Correction (2021.findings-emnlp)

Challenge:	Existing evaluation methods rely on external evaluators, focusing on training and prompting strategies, but model-aware glass-box features are overlooked.
Approach:	They propose to use model-aware glass-box features to evaluate an LLM's output.
Outcome:	The proposed model-aware features are reliable quality indicators for self-evaluation on public benchmarks.

Copied to clipboard

Liying Zheng, Yue Deng, Weishun Song, Liang Xu, Jing Xiao

Syntactic Text Processing

Challenge:	Existing models for Chinese text error correction can correct mistaken, missing and redundant characters, but they cannot handle missing or redundant characters.
Approach:	They propose an alignment-agnostic framework to correct Chinese text errors . framework detects missing and redundant characters and can be used as a cold start model .
Outcome:	The proposed framework can handle both text aligned and non-aligned situations and can serve as a cold start model when no annotation data are provided.

ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series (2025.findings-acl)

Copied to clipboard

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, V. W., Richard Yi Da Xu, Guo Li, Xian Yang

Sentiment Interpretable Logic Tensor Network for Aspect-Term Sentiment Analysis (2022.coling-1)

Challenge:	Large language models excel at processing unstructured data, but integrating time series data with text remains a challenge.
Approach:	They propose a self-supervised multimodal framework that uses prompt-guided learning to unify heterogeneous data types.
Outcome:	The proposed framework outperforms state-of-the-art approaches on disease diagnosis tasks using real-world datasets.

Copied to clipboard

Bowen Zhang, Xu Huang, Zhichao Huang, Hu Huang, Baoquan Zhang, Xianghua Fu, Liwen Jing

Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation (2024.findings-emnlp)

Challenge:	Aspect-term sentiment analysis (ATSA) is a fine-grained task that aims to infer the sentiment towards the given aspect-terms.
Approach:	They propose a novel ATSA method that is interpretable and has high accuracy . they propose SILTN, which is a neurosymbolic formalism, to improve the accuracy based on syntax knowledge distillation.
Outcome:	The proposed method is interpretable because it is a neurosymbolic formalism and a computational model that supports learning and reasoning about data with a differentiable first-order logic language.

Copied to clipboard

Yuhang Zhou, Jing Zhu, Paiheng Xu, Xiaoyu Liu, Xiyao Wang, Danai Koutra, Wei Ai, Furong Huang

Multi-Grained Knowledge Distillation for Named Entity Recognition (2021.naacl-main)

Challenge:	Knowledge distillation (KD) is a promising solution for large language models, but their deployment remains computationally expensive.
Approach:	They propose a framework which iteratively balances training data within a fixed computational budget and enables the transfer of knowledge from expensive teacher LLMs to smaller student models.
Outcome:	The proposed framework achieves state-of-the-art performance across diverse long-tailed datasets, enhancing both the efficiency and efficacy of the distilled models.

Copied to clipboard

Xuan Zhou, Xiao Zhang, Chenyang Tao, Junya Chen, Bing Xu, Wei Wang, Jing Xiao

Global and Local Hierarchical Prompt Tuning Framework for Multi-level Implicit Discourse Relation Recognition (2024.lrec-main)

Challenge:	Pre-trained big models have delivered top performance in Seq2seq modeling, but their deployments in real-world applications are often hindered by excessive computations and memory demands.
Approach:	They propose a distillation scheme to efficiently transfer knowledge from big models to their cheaper counterparts.
Outcome:	The proposed scheme maximizes the assimilation of knowledge from the teacher model to the student model.

Copied to clipboard

Lei Zeng, Ruifang He, Haowen Sun, Jing Xu, Chang Liu, Bo Wang

Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Parameter-Efficient Tuning (2022.findings-emnlp)

Challenge:	Recent methods to recognize hierarchical discourse relations without explicit connectives are inefficient and ignore the utilization of the output probability distribution information of the verbalizer.
Approach:	They propose a global and local hierarchical prompt tuning framework which leverages top-up propagated probability as the global hierarchy to inject it into multi-level verbalizer.
Outcome:	The proposed framework achieves competitive results on two benchmacks.

Copied to clipboard

Jing Yi, Weize Chen, Yujia Qin, Yankai Lin, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code (2025.acl-long)

Challenge:	Existing delta tuning algorithms freeze most of the parameters and only optimize minimal adaptive parameters.
Approach:	They propose to decompose DETs into a unified optimization subspace and conduct optimization within the subspace.
Outcome:	The proposed DETs achieve comparable performance to the original DET and can be transferred to another DET with non-trivial performance.

Copied to clipboard

Kechi Zhang, Ge Li, Yihong Dong, Jingjing Xu, Jun Zhang, Jing Su, Yongfei Liu, Zhi Jin

Programming Languages in NLP

Challenge:	Existing training methods for code generation do not improve code correctness and efficiency.
Approach:	They propose a framework that integrates preference learning into code generation to improve code correctness and efficiency.
Outcome:	The proposed framework improves code correctness and efficiency by integrating preference learning into code generation.

A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction (2022.coling-1)

Copied to clipboard

Changzhi Zhou, Dandan Song, Jing Xu, Zhijing Wu

Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification (2021.findings-emnlp)

Challenge:	Emotion-cause pair extraction (ECPE) is an emerging task in emotion cause analysis, which extracts potential emotion-caused pairs from an emotional document.
Approach:	They propose a document-level machine reading comprehension task to model complex relations between emotions and causes while avoiding generating the pairing matrix.
Outcome:	The proposed framework outperforms existing state-of-the-art methods on the emotion cause corpus and can model complex relations between emotions and causes while avoiding pairing matrix.

Copied to clipboard

Siyu Lai, Hui Huang, Dong Jing, Yufeng Chen, Jinan Xu, Jian Liu

Multilinguality

Challenge:	Recent multilingual pre-trained models have been demonstrated effective in many cross-lingual tasks.
Approach:	They propose a framework that leverages code-switched data with multi-view learning to fine-tune XLM-R.
Outcome:	The proposed model achieves state-of-the-art on zero-shot cross-lingual sentiment classification and dialogue state tracking tasks.

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing (2024.acl-long)

Copied to clipboard

Ziwei Chai, Guoyin Wang, Jing Su, Tianjie Zhang, Xuanwen Huang, Xuwu Wang, Jingjing Xu, Jianbo Yuan, Hongxia Yang, Fei Wu, Yang Yang

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities across a wide spectrum of tasks, but performance and reliability in certain specialized domains still fall short of expectations.
Approach:	They propose a unified generalist framework that facilitates seamless integration of multiple expert LLMs.
Outcome:	The proposed framework outperforms existing multi-LLM collaboration paradigms across six diverse expert domains.

The Promises and Pitfalls of Using Language Models to Measure Instruction Quality in Education (2024.naacl-long)

Copied to clipboard

Paiheng Xu, Jing Liu, Nathan Jones, Julie Cohen, Wei Ai

Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement (2025.acl-long)

Challenge:	Existing methods to assess instruction quality require trained raters to observe classrooms based on established criteria.
Approach:	They propose to use Natural Language Processing techniques to assess multiple high-inference instructional practices in in-person K-12 classrooms and simulated performance tasks for pre-service teachers.
Outcome:	The proposed method is able to assess multiple high-inference instructional practices in two educational settings: in-person K-12 classrooms and simulated performance tasks for pre-service teachers.

Copied to clipboard

Bingbing Xu, Jing Yao, Xiaoyuan Yi, Aishan Maoliniyazi, Xing Xie, Xiaofeng Meng

Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models (2025.naacl-long)

Challenge:	Large Language Models (LLMs) show remarkable performance across tasks . alignment with human values is critical for their responsible development.
Approach:	They propose a framework that evaluates value principles along three desirable properties . they propose supervised fine-tuning, reinforcement learning-based approaches .
Outcome:	The proposed framework improves value principles along the three desirable properties of LLMs.

Copied to clipboard

Tongxuan Liu, Wenjiang Xu, Weizhe Huang, Yuting Zeng, Jiaxing Wang, Xingyu Wang, Hailong Yang, Jing Li

A Cause-Effect Look at Alleviating Hallucination of Knowledge-grounded Dialogue Generation (2024.lrec-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks but their performance in complex logical reasoning tasks remains unsatisfactory.
Approach:	They propose a propositional logic prompting method which generates expanded logical information descriptions and utilizes them as an additional augmentation to original contexts.
Outcome:	Extensive experiments show that Logic-of-Thought boosts the performance of various prompting methods with a striking margin across five logical reasoning tasks.

Copied to clipboard

Jifan Yu, Xiaohan Zhang, Yifan Xu, Xuanyu Lei, Zijun Yao, Jing Zhang, Lei Hou, Juanzi Li

A Universal Discriminator for Zero-Shot Generalization (2023.acl-long)

Challenge:	Existing dialogue systems have demonstrated impressive performance conducting fluent and natural-sounding conversations, but they are plagued by the Knowledge Hallucination problem.
Approach:	They propose a method that exploits the dialogue-knowledge interaction to reduce hallucination by using external knowledge resources to generate more informative responses.
Outcome:	The proposed method reduces hallucination without disrupting other dialogue performance while keeping adaptive to different generation models.

Copied to clipboard

Haike Xu, Zongyu Lin, Jing Zhou, Yanan Zheng, Zhilin Yang