Papers by Yifan Wang

TellWhisper: Tell Whisper Who Speaks When (2026.acl-long)

Challenge:	Extensive experiments on seven semantic textual similarity tasks show our method achieves consistent improvement over the contrastive learning baseline and sets new states of the art.
Approach:	They propose a whitening-based contrastive learning method for sentence embedding learning which combines contrastive and shuffled group whitening.
Outcome:	The proposed method achieves better alignment and uniformity on seven semantic textual similarity tasks.

Copied to clipboard

Yifan Hu, Peiji Yang, Zhisheng Wang, Yicheng Zhong, Rui Liu

RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework (2025.acl-long)

Challenge:	Existing approaches decouple temporal modeling and speaker modeling when addressing 'when' and 'who' . a new framework that couples temporal structure with speaker dynamics is proposed to address these limitations .
Approach:	They propose a framework that couples temporal and speaker identity within the speech encoder . they propose TS-RoPE, a time-speaker rotary positional encoding that partitions Query/Key channels into temporal, speaker subspaces and applies region-specific rotations to align "when" and "who" cues in selfattention.
Outcome:	The proposed framework couples temporal structure with speaker dynamics in speech encoder . it uses frame-level speaker activity to estimate speaker-activity estimates .

Copied to clipboard

Kunlun Zhu, Yifan Luo, Dingling Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Ruobing Wang, Shuo Wang, Yishan Li, Nan Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Text Generation

Challenge:	Existing evaluation metrics for RAG systems are lacking due to high costs of data construction and lack of factual accuracy.
Approach:	They propose a framework to evaluate RAG systems in specialized scenarios . they propose three new metrics to evaluate LLM-generated responses .
Outcome:	The proposed framework outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.

Reflection on Knowledge Graph for Large Language Models Reasoning (2025.findings-acl)

Copied to clipboard

Yigeng Zhou, Wu Li, Yifan Lu, Jing Li, Fangming Liu, Meishan Zhang, Yequan Wang, Daojing He, Honghai Liu, Min Zhang

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (2024.findings-emnlp)

Challenge:	Existing methods for supplementing Large Language Models (LLMs) with knowledge graphs often introduce noise in the retrieval and reasoning pipeline, hindering their ability to integrate external knowledge for complex multi-hop question answering.
Approach:	They propose a framework to enhance LLMs' reasoning capabilities through reflective engagement with knowledge graphs by Query Decoupling, LLM-Driven Knowledge Graph Exploration, and Inference with Knowledge Reconstruction.
Outcome:	The proposed framework integrates external knowledge into LLMs and trains them to leverage this knowledge for answering questions.

Copied to clipboard

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li

Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)

Challenge:	Existing studies focus on specialized agents designed for particular tasks.
Approach:	They propose to scale annotated interaction trajectories and fine-tune LLMs on AgentBank to get a series of agent models, Samoyed.
Outcome:	The proposed model can scale to get generalized agent capabilities.

Copied to clipboard

Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang

SGG: Learning to Select, Guide, and Generate for Keyphrase Generation (2021.naacl-main)

Challenge:	Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale.
Approach:	They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data.
Outcome:	The proposed framework transforms user-generated content into user queries and generates responses from the policy model.

Copied to clipboard

Jing Zhao, Junwei Bao, Yifan Wang, Youzheng Wu, Xiaodong He, Bowen Zhou

Text Generation

Challenge:	Existing keyphrase generation approaches synchronously generate present and absent keyphrases without explicitly distinguishing these two categories.
Approach:	They propose to deal with present and absent keyphrases separately with different mechanisms by using a hierarchical neural network with a pointing-based selector and a selection-guided generator.
Outcome:	The proposed model outperforms baselines on four keyphrase generation tasks and shows extensibility in natural language generation tasks.

A Thorough Examination of Decoding Methods in the Era of LLMs (2024.emnlp-main)

Copied to clipboard

Chufan Shi, Haoran Yang, Deng Cai, Zhisong Zhang, Yifan Wang, Yujiu Yang, Wai Lam

A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025.acl-long)

Challenge:	Decoding methods are essential for converting language models from next-token predictors into practical task solvers.
Approach:	They propose to evaluate decoding methods in general-purpose large language models . they find that decoding method performance is notably task-dependent .
Outcome:	The proposed methods perform task-dependently and are influenced by alignment, model size, and quantization.

Copied to clipboard

Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang

ProQA: Structural Prompt-based Pre-training for Unified Question Answering (2022.naacl-main)

Challenge:	achieving data-efficient post-training of Large Language Models is a key research question.
Approach:	They propose a taxonomy of data-efficient LLM post-training methods from a data-centric perspective.
Outcome:	The proposed methods cover data selection, data quality enhancement, synthetic data generation, data distillation and compression, and self-evolving data ecosystems.

Copied to clipboard

Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations (2025.naacl-long)

Challenge:	Existing QA research on question answering is focused on specific question types, knowledge domains, or reasoning skills.
Approach:	They propose a unified QA paradigm that solves various tasks through a single model.
Outcome:	The proposed model improves QA-centric ability on 11 QA benchmarks.

Copied to clipboard

Yichuan Li, Xinyang Zhang, Chenwei Zhang, Mao Li, Tianyi Liu, Pei Chen, Yifan Gao, Kyumin Lee, Kaize Ding, Zhengyang Wang, Zhihan Zhang, Jingbo Shang, Xian Li, Trishul Chilimbi

Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments (2024.acl-long)

Challenge:	Existing benchmarks for recommendation explanation evaluation lack item diversity and user preferences data.
Approach:	They propose a model-agnostic recommendation explanation evaluation benchmark based on Amazon e-commerce categories with implicit preferences . they propose two novel automatic evaluators that enable scalable and human-preference aligned evaluation of explanations .
Outcome:	The proposed model-agnostic evaluation benchmark outperforms existing methods in a variety of domains.

Copied to clipboard

Zhenrui Yue, Huimin Zeng, Lanyu Shang, Yifan Liu, Yang Zhang, Dong Wang

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)

Challenge:	Existing methods to verify claim credibility rely on embedded knowledge or unreliable context.
Approach:	They propose retrieval augmented fact verification through the synthesis of contrasting arguments (RAFTS) they use an embedding model to identify informative demonstrations and in-context prompts to generate the prediction and explanation.
Outcome:	The proposed method outperforms existing methods with smaller LLMs or unreliable contexts.

Copied to clipboard

Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang

Evaluating Object Hallucination in Large Vision-Language Models (2023.emnlp-main)

Challenge:	Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability.
Approach:	They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs .
Outcome:	The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks.

Copied to clipboard

Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Xin Zhao, Ji-Rong Wen

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

Challenge:	Large vision-language models (LVLMs) suffer from object hallucinations, i.e., they tend to generate objects inconsistent with the target images in the descriptions.
Approach:	They propose to integrate powerful large vision-language models (LVLMs) they propose a polling-based query method to evaluate object hallucination .
Outcome:	The proposed model can evaluate object hallucination in a more stable and flexible way.

Copied to clipboard

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

Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)

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

Copied to clipboard

Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, Xiaodan Zhu

Explore the Reasoning Capability of LLMs in the Chess Testbed (2025.naacl-short)

Challenge:	Existing methods for AVE are limited on rare attributes due to poor generalization ability.
Approach:	They propose to leverage pretraining and transfer learning to address weaknesses in existing methods.
Outcome:	The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources.

Copied to clipboard

Shu Wang, Lei Ji, Renxi Wang, Wenxiao Zhao, Haokun Liu, Yifan Hou, Ying Nian Wu

IHEval: Evaluating Language Models on Following the Instruction Hierarchy (2025.naacl-long)

Challenge:	a recent study shows that large language models struggle with long-term, complex reasoning tasks.
Approach:	They propose to integrate annotated strategy and tactic into large language models to improve reasoning capability.
Outcome:	The proposed model performs better than GPT, Claude, and Gemini models . it integrates annotated strategy and tactic into the model .

Copied to clipboard

Zhihan Zhang, Shiyang Li, Zixuan Zhang, Xin Liu, Haoming Jiang, Xianfeng Tang, Yifan Gao, Zheng Li, Haodong Wang, Zhaoxuan Tan, Yichuan Li, Qingyu Yin, Bing Yin, Meng Jiang

Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation (2022.emnlp-main)

Challenge:	Instruction-tuned language models (LMs) are increasingly deployed as interactive services across various applications.
Approach:	They propose a benchmark to evaluate models' ability to follow the instruction hierarchy by comparing their models to a set of benchmarks.
Outcome:	The proposed benchmark covers 3,538 examples across nine tasks covering cases where instructions in different priorities either align or conflict.

Copied to clipboard

Peiyi Wang, Yifan Song, Tianyu Liu, Binghuai Lin, Yunbo Cao, Sujian Li, Zhifang Sui

UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations (2025.acl-long)

Challenge:	Existing studies attribute catastrophic forgetting to the corruption of the learned representations as new relations come . Continual relation extraction models suffer from catastrophic forgetting when learning new relations .
Approach:	They propose to use adversarial class augmentation mechanism to learn more precise representations . they propose to train the model on a sequence of tasks where two new relations are discovered .
Outcome:	The proposed model improves on two popular benchmarks.

Copied to clipboard

Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang

MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models (2025.emnlp-main)

Challenge:	Existing conversational search systems are usually built with two different models . this separation restricts the system from leveraging the model's intrinsic knowledge simultaneously . Existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses.
Approach:	They propose to unify dense retrieval and response generation for large language models in conversation by fine-tuning and mitigating data discrepancy.
Outcome:	The proposed model can outperform existing models on five conversational search datasets and reduce inconsistency risks while mitigating data discrepancy.

Copied to clipboard

Zhengyi Zhao, Shubo Zhang, Yuxi Zhang, Yanxi Zhao, Yifan Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu

CESRec: Constructing Pseudo Interactions for Sequential Recommendation via Conversational Feedback (2025.findings-emnlp)

Challenge:	Current approaches focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overlooking a fundamental challenge: the same meme can express different intents depending on its conversational context.
Approach:	They propose a benchmark to evaluate how large vision language models understand memes in their original context.
Outcome:	The proposed benchmark evaluates how large vision language models understand meme intent in their original context.

Copied to clipboard

Yifan Wang, Shen Gao, Jiabao Fang, Rui Yan, Billy Chiu, Shuo Shang

LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition (2025.emnlp-main)

Challenge:	Existing Sequential Recommendation Systems (SRS) rely on collaborative filtering signals and fail to capture real-time user preferences.
Approach:	They propose a framework that integrates the long-term preference modeling of SRS with the real-time preference elicitation of CRS.
Outcome:	The proposed framework integrates the long-term preference modeling of SRS with the real-time preference elicitation of CRS.

Copied to clipboard

Qianrui Zhou, Hua Xu, Yifan Wang, Xinzhi Dong, Hanlei Zhang

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction (2021.acl-long)

Challenge:	Existing methods for understanding intents from multimodal signals exhibit limitations in their modality-level reliance, constraining relational reasoning over fine-grained semantics for complex intent understanding.
Approach:	They propose a method that harnesses the expansive knowledge of large language models to establish semantic foundations that boost smaller models’ relational reasoning performance.
Outcome:	The proposed method outperforms state-of-the-art methods on multimodal intent and dialogue act recognition tasks and shows consistent performance gains across diverse semantic understanding scenarios.

Copied to clipboard

Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos Santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments (2026.acl-long)

Challenge:	Open-domain question answering is a task to answer questions using passages with diverse topics.
Approach:	They propose a model that aggregates evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions.
Outcome:	The proposed model achieves state-of-the-art performance on AmbigQA dataset and shows competitive performance on NQ-Open and TriviaQA.

Copied to clipboard

Hao Mi, Qiang Sheng, Shaofei Wang, Beizhe Hu, Yifan Sun, Zhengjia Wang, Hengqi Zeng, Yang Li, Danding Wang, Juan Cao

NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

Challenge:	Existing methods for hallucination detection focus on implicit neural uncertainty or explicit symbolic reasoning, ignoring factual hallucinosities.
Approach:	They propose a framework that bridges neural features and symbolic judgments for hallucination detection by leveraging a "meta-judgment" process to map symbolic labels back into the feature space.
Outcome:	Extensive experiments on 4 public datasets, across 4 LLMs, against 8 baselines demonstrate the superiority of LaaB.

Copied to clipboard

Changyu Zeng, Yifan Wang, Zimu Wang, Wei Wang, Zhengni Yang, Muyi Bao, Jimin Xiao, Anh Nguyen, Yutao Yue

EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification (2024.findings-acl)

Challenge:	Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach:	They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome:	The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.

Copied to clipboard

Huanhuan Ma, Weizhi Xu, Yifan Wei, Liuji Chen, Liang Wang, Qiang Liu, Shu Wu, Liang Wang

From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations (2025.emnlp-main)

Challenge:	Existing studies on fact verification lack a high-quality dataset for explainability . existing systems lack evidence retrieval and veracity prediction, limiting the ability to verify a claim .
Approach:	They propose a dataset for multi-hop explainable fact verification that summarises and modifies Wikipedia documents.
Outcome:	The proposed dataset aims to improve the accuracy of multi-hop explainable fact verification systems.

Copied to clipboard

Benlu Wang, Iris Xia, Yifan Zhang, Junda Wang, null Feiyun Ouyang, Shuo Han, Arman Cohan, Hong Yu, Zonghai Yao

Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? (2025.findings-emnlp)

Challenge:	Existing benchmarks assess only the final answer with a wide numerical tolerance, overlooking systematic reasoning failures and potentially causing serious clinical misjudgments.
Approach:	They propose a new step-by-step evaluation pipeline that assesses formula selection, entity extraction, and arithmetic computation.
Outcome:	The proposed method improves the accuracy of large language models on medical benchmarks from 16.35% to 53.19%.

Copied to clipboard

Xiaochen Wang, Heming Xia, Jialin Song, Longyu Guan, Qingxiu Dong, Rui Li, Yixin Yang, Yifan Pu, Weiyao Luo, Yiru Wang, Xiangdi Meng, Wenjie Li, Zhifang Sui

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

Challenge:	Large Multimodal Models have demonstrated strong performance on vision-language benchmarks, yet current evaluations focus on single-image reasoning.
Approach:	STRIPCIPHER is a benchmark designed to evaluate model ability on understanding implicit narratives in silent comics.
Outcome:	STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels.

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

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

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

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

Fine- and Coarse-Granularity Hybrid Self-Attention for Efficient BERT (2022.acl-long)

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

Copied to clipboard

Jing Zhao, Yifan Wang, Junwei Bao, Youzheng Wu, Xiaodong He

TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making (2025.emnlp-main)

Challenge:	Transformer-based pre-trained models achieve state-of-the-art results, but they can be prohibitively costly.
Approach:	They propose a fine- and coarse-granularity hybrid self-attention that shortens the computational sequence length in self- attention by progressively shortening the computational time.
Outcome:	The proposed model reduces computation cost by shortening the computational sequence length in self-attention.

Copied to clipboard

Kechen Jiao, Zhirui Fang, Jiahao Liu, Bei Li, Qifan Wang, Xinyu Liu, Junhao Ruan, Zhongjian Qiao, Yifan Zhu, Yaxin Xu, Jingang Wang, Xiu Li

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)

Challenge:	Existing post-SFT methods for embodied AI are constrained by sparse rewards and action-only optimization, resulting in low sample efficiency, poor consistency, and model degradation.
Approach:	They propose to integrate Thought-Centric Preference Optimization (TCPO) into embodied decision-making by transforming sparse reward signals into richer step sample pairs.
Outcome:	The proposed approach achieves an average success rate of 26.67% in the ALFWorld environment, and a 6% improvement over RL4VLM.

Copied to clipboard

Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang

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

Challenge:	Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed .
Approach:	They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision.
Outcome:	The proposed framework reduces token usage while improving accuracy on math benchmarks.

Copied to clipboard

Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Gong Yifan, Sheng Zhang

ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning (2025.emnlp-main)

Challenge:	Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting.
Approach:	They propose a representation-aware model merging framework for continual learning without access to historical data.
Outcome:	The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios.

Copied to clipboard

Rui Wang, Bohao Li, Xiyang Dai, Jianwei Yang, Yi-Ling Chen, Zhen Xing, Yifan Yang, Dongdong Chen, Xipeng Qiu, Zuxuan Wu, Yu-Gang Jiang

InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective (2023.findings-emnlp)

Challenge:	Existing approaches to adapt image-focused models for video understanding have not been successful in analyzing long video sequences.
Approach:	They propose a video instruction dataset that outperforms existing video instruction data for fine-tuning MLLMs by incrementally increasing input context length.
Outcome:	The proposed model outperforms existing models on video benchmarks and outperformed proprietary models on VideoMME even with a compact 7B model.

Copied to clipboard

Yifan Song, Peiyi Wang, Weimin Xiong, Dawei Zhu, Tianyu Liu, Zhifang Sui, Sujian Li

Information Extraction & Text Mining

Challenge:	Recent studies have identified the severe performance decrease on analogous classes as a key factor for catastrophic forgetting.
Approach:	They propose a replay-based continual text classification method that uses fast-slow and current-past contrastive learning to perform mutual information maximization and better recover previously learned representations.
Outcome:	The proposed method achieves state-of-the-art on three text classification tasks.

Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference (2020.emnlp-main)

Copied to clipboard

Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu, Changyou Chen

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Challenge:	Existing studies show that multi-head attention is an effective module in deep neural networks, but there are no explicit mechanisms guaranteeing this property.
Approach:	They propose a non-parametric approach that explicitly improves the repulsiveness in multi-head attention and consequently strengthens model’s expressiveness.
Outcome:	The proposed approach improves the repulsiveness in multi-head attention and strengthens model’s expressiveness.

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey (2025.findings-naacl)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Xiaoyu Liu, Paiheng Xu, Junda Wu, Jiaxin Yuan, Yifan Yang, Yuhang Zhou, Fuxiao Liu, Tianrui Guan, Haoliang Wang, Tong Yu, Julian McAuley, Wei Ai, Furong Huang

Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization (2023.acl-long)

Challenge:	Large Language Models (LLMs) have shown great potential to enhance Natural Language Processing (NLP) models in areas such as predictive accuracy, fairness, robustness, and explainability.
Approach:	They evaluate or improve generative Large Language Models from a causal perspective in areas such as reasoning capacity, fairness and safety issues, explainability, and handling multimodality.
Outcome:	The proposed models can be used to perform causal relationship discovery and causal effect estimation tasks.

Copied to clipboard

Dongqi Pu, Yifan Wang, Vera Demberg

Summarization

Challenge:	Contemporary leading-edge systems for abstractive (long) text summarization employ Transformer encoderdecoder architectures that only consider the nuclearity annotation .
Approach:	They propose to incorporate Rhetorical Structure Theory into a novel summarization model that incorporates both the types and uncertainty of rhetorical relations.
Outcome:	The proposed model outperforms state-of-the-art models on automatic metrics and human evaluation.

MultiSQL: A Schema-Integrated Context-Dependent Text2SQL Dataset with Diverse SQL Operations (2024.findings-acl)

Copied to clipboard

Chunhui Li, Yifan Wang, Zhen Wu, Zhen Yu, Fei Zhao, Shujian Huang, Xinyu Dai

Improving Consistency for Text Summarization with Energy Functions (2023.findings-emnlp)

Challenge:	Text2SQL is a task that translates natural language into SQL statements.
Approach:	They propose a task that translates natural language into SQL statements.
Outcome:	The proposed task enables users to convert natural language into SQL statements.

Copied to clipboard

Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang

Summarization

Challenge:	Current abstractive summarization models generate inconsistent content due to the inherently noisy dataset and the discrepancy between maximum likelihood estimation based training objectives and consistency measurements.
Approach:	They propose a new consistency taxonomy that categorizes inconsistent content into faithfulness, factuality, and self-supportiveness.
Outcome:	Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency.

Can LLMs Hear the Dogwhistle? (2026.findings-acl)

Copied to clipboard

Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline (2024.findings-emnlp)

Challenge:	Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach:	They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome:	The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.

Copied to clipboard

Yifan Xu, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Zhao Wenyi, Jie Tang, Yuxiao Dong

Numerical Reasoning

Challenge:	Large language models (LLMs) have shown excellent mastering of human language but struggle in real-world applications that require mathematical problem-solving.
Approach:	They propose a pipeline to train a general Math-Critique model from the LLM itself to provide feedback signals and employ rejective fine-tuning and direct preference optimization over the Llm's own generations for data collection.
Outcome:	The proposed pipeline outperforms existing LLMs that could be two times larger.

Rethinking Token Reduction for State Space Models (2024.emnlp-main)

Copied to clipboard

Zheng Zhan, Yushu Wu, Zhenglun Kong, Changdi Yang, Yifan Gong, Xuan Shen, Xue Lin, Pu Zhao, Yanzhi Wang

Challenge:	Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% .
Approach:	They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging.
Outcome:	The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements.

Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing (2025.findings-acl)

Copied to clipboard

Yifan Lu, Jing Li, Yigeng Zhou, Yihui Zhang, Wenya Wang, Xiucheng Li, Meishan Zhang, Fangming Liu, Jun Yu, Min Zhang

Challenge:	Existing knowledge editing methods for large language models (LLMs) suffer from over-editing, where detoxified models reject legitimate queries, compromising overall performance.
Approach:	They propose a toxicity-aware knowledge editing approach that dynamically detects toxic activation patterns during forward propagation and then routes computations through adaptive inter-layer pathways to mitigate toxicity effectively.
Outcome:	The proposed method outperforms existing methods on large language models and enhances the SafeEdit benchmark.

SciNews: From Scholarly Complexities to Public Narratives – a Dataset for Scientific News Report Generation (2024.lrec-main)

Copied to clipboard

Dongqi Pu, Yifan Wang, Jia E. Loy, Vera Demberg

Text Generation

Challenge:	Scientific news reports are a bridge between academic and scientific publications . however, the pursuit of automated news reports faces challenges due to the insufficient availability of parallel corpora.
Approach:	They propose to use a corpus of scientific news reports to facilitate this paradigm development . they highlight the divergences in readability and brevity between scientific news narratives and academic manuscripts .
Outcome:	The proposed corpus includes academic publications and scientific news reports across nine disciplines.

FAER: Benchmarking VLMs for Failure-Aware Embodied Reasoning (2026.findings-acl)

Copied to clipboard

Hao Song, Kaifeng Liu, Yuanxing Liu, Xiang Tian, Xuesong Wang, Chen Yifan, Weinan Zhang, Ting Liu

From Mimesis to Metamorphosis: Evolving VLM Judges via In-Context Comparing and Knowledge Internalization (2026.findings-acl)

Challenge:	Visual-language models (VLMs) are the core component of embodied agents in perceiving the environment and making decisions.
Approach:	They propose a failure-aware benchmark to evaluate the performance of visual language models (VLMs) in long-horizon tasks.
Outcome:	The proposed benchmark evaluates the performance of 16 widely utilized VLMs and 4 LLMs for FAER tasks.

Copied to clipboard

Juntuo Wang, Yuming Qiao, Yifan Yang, Lunxi Yuan, Liang Luo, Dan Meng

Information Retrieval

Challenge:	Existing approaches to subjective assessment are inconsistent and inconsistent due to inconsistent scales and inherent preference biases.
Approach:	They propose a framework that operationalizes subjective assessment as comparative analysis and internalizes it via Language Buttons.
Outcome:	The proposed framework achieves state-of-the-art performance across multiple benchmarks and is scale-steerable.

Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)

Copied to clipboard

Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li

Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Value (2024.naacl-long)

Challenge:	Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions.
Approach:	They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations.
Outcome:	The proposed framework measures the agent's higher-order social cognition in multi-turn conversations.

Copied to clipboard

Jing Yao, Xiaoyuan Yi, Yifan Gong, Xiting Wang, Xing Xie

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Challenge:	Existing work specifies values as risk criteria formulated in the AI community, e.g., fairness and privacy protection, suffering from poor clarity, adaptability and transparency.
Approach:	They propose a value alignment paradigm based on Schwartz's Theory of Basic Values as an instantiation and propose 'BaseAlign' to support this paradigm.
Outcome:	The proposed model covers existing risks and anticipates unidentified ones with a low-data set.

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Hao Zhang, Zhenjia Li, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, null Xiaoxincc, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation (2026.acl-long)

Challenge:	Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers.
Approach:	They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters .
Outcome:	The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork.

Copied to clipboard

Shanwen Tan, Ziyang Dong, Wei Ju, Yiwei Fu, Hao Wu, Kun Wang, Yifan Wang, Ziyue Qiao

Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced Framework (2026.eacl-industry)

Challenge:	Existing approaches to decode large language models (LLMs) often over-reject benign information, limiting their generalizability in real-world scenarios where harmful and benign information coexist.
Approach:	They propose a framework to regulate decoding alignments for Large Language Models (LLMs) they employ a reward-guided branch decoding paradigm to incorporate safety awareness during generation.
Outcome:	The proposed framework achieves superior performance on four attack benchmarks and two neutral datasets.

Copied to clipboard

Xinle Pang, Danding Wang, Qiang Sheng, Yifan Sun, Beizhe Hu, Juan Cao

The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters (2025.acl-long)

Challenge:	Existing methods for fact-checking lack coherence and context, whereas abstractive methods lack cohesion and context.
Approach:	They propose a framework that generates Chinese user-specific debunking passages . they propose to use a generative AI framework to generate context-sensitive responses .
Outcome:	The proposed framework generates Chinese user-specific debunking passages by iteratively refining outputs based on simulated user feedback.

Copied to clipboard

Chulun Zhou, Qiujing Wang, Mo Yu, Xiaoqian Yue, Rui Lu, Jiangnan Li, Yifan Zhou, Shunchi Zhang, Jie Zhou, Wai Lam

Controlling Styles in Neural Machine Translation with Activation Prompt (2023.findings-acl)

Challenge:	Theory-of-Mind (ToM) is a psychological capability that allows humans to understand and interpret the mental states of others.
Approach:	They propose a CharToM-QA benchmark to assess the importance of comprehensive contextual understanding about personal backgrounds in ToM.
Outcome:	The proposed model outperforms existing models on 1,035 ToM questions based on classic novels and shows that educated participants perform better when they have read the novels than non-educated participants.

Copied to clipboard

Yifan Wang, Zewei Sun, Shanbo Cheng, Weiguo Zheng, Mingxuan Wang

Machine Translation

Challenge:	Earlier studies on controlling styles in neural machine translation (NMT) have focused on regulating the level of formality, but they still encounter two major challenges.
Approach:	They propose a method to control the style of neural machine translation by retrieving prompts from stylized monolingual corpus.
Outcome:	The proposed method can control the style of translation and achieve remarkable performance.

UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning (2026.findings-acl)

Copied to clipboard

Yifan Wang, Yun Fu

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas (2025.emnlp-main)

Challenge:	Recent large multimodal models (LMMs) have demonstrated impressive capabilities in image understanding, yet they struggle to perform complex reasoning on multimodal problems.
Approach:	They propose a multimodal prompting method that strengthens reasoning for multimodal tasks in large multimodal models.
Outcome:	The proposed method improves reasoning on three public benchmarks and shows that it can be used to extract key information from images.

Copied to clipboard

Ya Wu, Qiang Sheng, Danding Wang, Guang Yang, Yifan Sun, Zhengjia Wang, Yuyan Bu, Juan Cao

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)

Challenge:	Existing evaluations of LLMs' moral reasoning capabilities rely on single-step evaluations, ignoring how models adapt to evolving ethical challenges.
Approach:	They propose a framework to evaluate evolving moral judgments of large language models (LLMs) using multi-step moral dilemma questionnaires.
Outcome:	The proposed framework enables a fine-grained analysis of how LLMs adjust their moral reasoning across escalating dilemmas.

Copied to clipboard

Fengran Mo, Yifan Gao, Sha Li, Hansi Zeng, Xin Liu, Zhaoxuan Tan, Xian Li, Jianshu Chen, Dakuo Wang, Meng Jiang

TiKMiX: Efficient Semi-Dynamic Data Mixture via Data Influence for LLM Pre-training (2026.acl-long)

Challenge:	Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions.
Approach:	They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals.
Outcome:	The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals.

Copied to clipboard

Yifan Wang, null Binbinliu, Fengze Liu, Yuanfan Guo, Jiyao Deng, Xuecheng Wu, Weidong Zhou, Xiaohuan Zhou, Taifeng Wang

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation (2025.acl-industry)

Challenge:	Static data mixing strategies in large language models are often suboptimal as they fail to adapt to the model’s evolving learning states.
Approach:	They propose a semi-dynamic data mixing framework that uses a key observation of influence ranking invariance to reduce computational overhead by 80% .
Outcome:	The proposed method reduces computational overhead by 80% and achieves an average performance gain of 2% across nine downstream benchmarks, effectively mitigating data under-digestion.

Copied to clipboard

Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong

Information Extraction & Text Mining

Challenge:	Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards.
Approach:	They propose a method to transform a generative MLLM into a multimodal classifier using minimal discriminative training data.
Outcome:	The proposed method improves F1 score by 66.50% over traditional classifiers while requiring only 2% of the fine-tuning data.

Glue pizza and eat rocks - Exploiting Vulnerabilities in Retrieval-Augmented Generative Models (2024.emnlp-main)

Copied to clipboard

Zhen Tan, Chengshuai Zhao, Raha Moraffah, Yifan Li, Song Wang, Jundong Li, Tianlong Chen, Huan Liu

RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework (2024.emnlp-main)

Challenge:	Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases.
Approach:	They propose to exploit openness of RAG models by injecting deceptive content into the retrieval database, intentionally changing the model’s behavior.
Outcome:	The proposed model can be exploited through crafted content uploads with access to the retriever.

Copied to clipboard

Yifan Wang, Vera Demberg

TopoSHIELD: Reshaping the Flow of Malice via Spatio-Temporal Risk-Aware Topological Evolution in Multi-Agent Systems (2026.findings-acl)

Challenge:	RSA-Control is a training-free controllable text generation framework . existing studies rely on fine-tuning pre-trained language models . external components could hurt coherence and accuracy of the model .
Approach:	They propose a training-free controllable text generation framework grounded in pragmatics that directs the generation process by recursively reasoning between imaginary speakers and listeners.
Outcome:	The proposed framework achieves strong attribute control while maintaining fluency and content consistency.

Copied to clipboard

Ruiyang Huang, Chenxi Wang, Tinghe Zhang, Fengrui Liu, Jiayan Sun, Haocheng Wang, Yifan Wu

Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (2024.emnlp-main)

Challenge:	Multi-agent systems (MAS) inherit general task-solving and instruction-following capabilities, but their interconnectivity introduces significant security risks.
Approach:	They propose a framework that reshapes the flow of malice via risk-aware topological evolution.
Outcome:	Empirically, TopoSHIELD reduces toxicity by 58% on GPT-4o while preserving high utility (>90% success rate).

Copied to clipboard

Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)

Challenge:	Recent approaches to enhance agent performance focus on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals.
Approach:	They propose a step-level framework that provides detailed step-by-step guidance to enhance agent training by using Monte Carlo methods.
Outcome:	The proposed framework outperforms strong baselines on three tasks and shows that it is effective in augmenting efficiency and its applicability to diverse models.

Copied to clipboard

Zhensheng Jin, Xinze Li, Yifan Ji, Chunyi Peng, Zhenghao Liu, Qi Shi, Yukun Yan, Shuo Wang, Furong Peng, Ge Yu

DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual Systems (2026.acl-long)

Challenge:	Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem .
Approach:	They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths .
Outcome:	The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines .

Copied to clipboard

Shuyu Zhang, Yifan Wei, Jialuo Yuan, Xinru Wang, Yanmin Zhu, Yujie Liu, Bin Li

LEAF: Large Language Diffusion Model for Time Series Forecasting (2025.findings-emnlp)

Challenge:	Task oriented dialog systems often rely on static exploration strategies that do not adapt to dynamic dialog contexts.
Approach:	They propose a dialog policy learning framework that formalizes the exploration challenge through a structured cognitive state space C.
Outcome:	The proposed framework achieves SOTA performance in success rate, efficiency, and generalization.

Copied to clipboard

Yuhang Pei, Tao Ren, Yifan Wang, Zhipeng Sun, Wei Ju, Chong Chen, Xian-Sheng Hua, Xiao Luo

User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems (2025.acl-industry)

Challenge:	Recent work has applied large language models (LLMs) into time series forecasting, but they lack an understanding of holistic temporal patterns with potential error accumulation.
Approach:	They propose a framework that marries Larg e Langu age Diffusion Model with time series forecasting (LEAF) they propose converting time series into tokens and adopting language diffusion models to capture temporal dependencies.
Outcome:	The proposed framework generates future predictions with a diffusion model from a holistic view.

Copied to clipboard

Jianling Wang, Yifan Liu, Yinghao Sun, Xuejian Ma, Yueqi Wang, He Ma, Zhengyang Su, Minmin Chen, Mingyan Gao, Onkar Dalal, Ed H. Chi, Lichan Hong, Ningren Han, Haokai Lu

Influence-based Online Experience Selection for Effective RLHF (2026.acl-long)

Challenge:	Large Language Models (LLMs) can be used to broaden user experiences beyond established preferences and reinforce feedback loops.
Approach:	They propose a hierarchical approach that combines hierarchic planning with LLM inference-time scaling to improve recommendation relevancy without compromising novelty.
Outcome:	The proposed approach shows significant gains in both user satisfaction and exploration diversity.

Copied to clipboard

Yifan Gong, Jing Yao, Xiting Wang, Xunlong Wang, Xiaoyuan Yi, Xing Xie

The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking (2025.emnlp-main)

Challenge:	Existing methods for RL fail to establish an interpretable connection between data and optimization objectives.
Approach:	They propose a data selection method that dynamically estimates the influence of individual training samples on policy optimization.
Outcome:	The proposed method significantly improves training effectiveness with fewer optimization steps.

Copied to clipboard

Yaoyao Qian, Yifan Zeng, Yuchao Jiang, Chelsi Jain, Huazheng Wang

HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have demonstrated strong performance in information retrieval tasks like passage ranking.
Approach:	They propose two attacks that aim to force the LLM ranker to prefer a specific passage and rank it at the top.
Outcome:	The proposed attacks aim to force the LLM ranker to prefer a specific passage and rank it at the top.

Copied to clipboard

Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, Deyi Xiong

LoRaDA: Low-Rank Direct Attention Adaptation for Efficient LLM Fine-tuning (2025.findings-emnlp)

Challenge:	a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models .
Approach:	They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams .
Outcome:	The proposed model is based on o1-like models and a high-level model.

Copied to clipboard

Zhangming Li, Qinghao Hu, Yiqun Chen, Peisong Wang, Yifan Zhang, Jian Cheng

SPO: Self Preference Optimization with Self Regularization (2025.findings-emnlp)

Challenge:	Recent advances in parameter-efficient fine-tuning techniques allow for adjustments to only a minor fraction of the parameters of language models.
Approach:	They propose a low-rank direct attention adapted method for efficient LLM fine-tuning . they propose LMAM, which can bring negative attention to self-attention modules .
Outcome:	The proposed method outperforms the full fine-tuning method by 2.1% on GLUE benchmark.

Copied to clipboard

Yuhao Sun, Yifan Zhang, Quandong Wang, Qinzhuo Wu, Wei Liu, Jian Luan

Machine Translation

Challenge:	Existing reference-free preference optimization methods exhibit higher training efficiency but are prone to overoptimization, leading to performance degradation.
Approach:	They propose a reference-free preference optimization method that replaces the logsigmoid loss function with a SiLU function to improve the model's performance.
Outcome:	The proposed method achieves 7% improvement over SimPO on AlpacaEval 2 and MT-Bench.

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)

Copied to clipboard

Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song

Rationale-Enhanced Language Models are Better Continual Relation Learners (2023.emnlp-main)

Challenge:	Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges .
Approach:	They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Outcome:	The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset .

Copied to clipboard

Weimin Xiong, Yifan Song, Peiyi Wang, Sujian Li

ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering (2024.findings-emnlp)

Challenge:	Recent studies have found that catastrophic forgetting arises from the model’s lack of robustness against future analogous relations.
Approach:	They propose a multi-task rationale tuning strategy to help the model learn current relations robustly and conduct contrastive rationale replay to further distinguish analogous relations.
Outcome:	The proposed method outperforms the state-of-the-art models on two benchmarks.

Copied to clipboard

Yifan Wu, Lutao Yan, Leixian Shen, Yunhai Wang, Nan Tang, Yuyu Luo

Divide, Optimize, Merge: Scalable Fine-Grained Generative Optimization for LLM Agents (2025.findings-emnlp)

Challenge:	Chart question answering (ChartQA) tasks are a critical part of visualization charts.
Approach:	They propose a chart question answering task that uses MLLMs to analyze charts . they propose 'Chain-of-Charts' textual prompt strategy that directs attention to visual elements .
Outcome:	The proposed model improves performance by 14.41% and 80% in low-level ChartQA tasks.

Copied to clipboard

Jiale Liu, Yifan Zeng, Shaokun Zhang, Chi Zhang, Malte Højmark-Bertelsen, Marie Normann Gadeberg, Huazheng Wang, Qingyun Wu

The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism (2025.naacl-long)

Challenge:	LLM-based generative optimization has shown remarkable potential in improving agentic systems, but the current approach of prompting with the trajectories on the whole training dataset becomes untenable as datasets grow.
Approach:	They propose a scalable framework that divides large optimization tasks into manageable subsets and performs targeted optimizations.
Outcome:	The proposed framework outperforms conventional approach by 1.6-8.6% while reducing average prompt token consumption by 56.3%.

Copied to clipboard

Yifan Song, Guoyin Wang, Sujian Li, Bill Yuchen Lin

Challenge:	Current evaluations of large language models (LLMs) focus on a single output per example, which limits our understanding of LLM performance variability in real-world applications.
Approach:	They explore the performance differences between greedy decoding and sampling and identify benchmarks’ consistency regarding non-determinism and examine unique model behaviors.
Outcome:	The proposed model outperforms sampling methods and greedy decoding outperformed other models.

Exploring Fine-Grained Human Motion Video Captioning (2025.coling-main)

Copied to clipboard

Bingchan Zhao, Xinyi Liu, Zhuocheng Yu, Tongchen Yang, Yifan Song, Mingyu Jin, Sujian Li, Yizhou Wang

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

Challenge:	Existing video captioning models fail to capture nuanced semantics of videos . existing models generate coarse descriptions of human motions, resulting in poor quality .
Approach:	They construct a fine-grained human motion video captioning dataset named BoFiT and a model that generates fine-grain descriptions of human motions via prompting.
Outcome:	The proposed model outperforms existing models on comprehensive metrics.

Copied to clipboard

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

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

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

Copied to clipboard

Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

Won’t Get Fooled Again: Answering Questions with False Premises (2023.acl-long)

Challenge:	Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach:	They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome:	The proposed framework outperforms baseline methods in real-time and in real applications.

Copied to clipboard

Shengding Hu, Yifan Luo, Huadong Wang, Xingyi Cheng, Zhiyuan Liu, Maosong Sun

Question Answering

Challenge:	Pre-trained language models (PLMs) are often easily deceived by tricky questions such as “How many eyes does the sun have?” .
Approach:	They annotate a FalseQA dataset containing 2365 human-written FPQs and find that PLMs are capable of discriminating FPqs by fine-tuning on moderate numbers.
Outcome:	The proposed model can discriminate on FPQs by fine-tuning on moderate numbers of examples and generate reasonable explanations for false premise questions.

Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning (2026.acl-long)

Copied to clipboard

Yifan Wang, Shiyu Li, Peiming Li, Xiaochen Yang, Zheng Wei, Yang Tang

Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Challenge:	Recent work on Chain-of-Thought prompting imposes substantial computational overhead . lack of supervision obscures the analyzability of the latent reasoning chain.
Approach:	They propose a framework to render latent reasoning chain into images, making latent rationale explicit and traceable.
Outcome:	The proposed framework achieves 3-4 token compression and substantial inference acceleration compared to explicit CoT prompting.

Copied to clipboard

Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang

Speech & Audio in NLP

Challenge:	Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach:	They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome:	The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.

InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions (2024.naacl-long)

Copied to clipboard

Yifan Wang, Yafei Liu, Chufan Shi, Haoling Li, Chen Chen, Haonan Lu, Yujiu Yang

RoR: Read-over-Read for Long Document Machine Reading Comprehension (2021.findings-emnlp)

Challenge:	In order to perform downstream tasks, Large Language Models (LLMs) need continual adaptation without catastrophic forgetting.
Approach:	They propose a new paradigm that allows for continual adaptation without catastrophic forgetting . they propose to replay previous data based on task similarity with instructions .
Outcome:	The proposed method improves performance over 16 tasks with different training orders.

Copied to clipboard

Jing Zhao, Junwei Bao, Yifan Wang, Yongwei Zhou, Youzheng Wu, Xiaodong He, Bowen Zhou

Machine Reading Comprehension

Challenge:	Existing models for machine reading comprehension are limited to individual chunks due to encoding length constraint.
Approach:	They propose a read-over-read method that expands the reading field from chunk to document by predicting regional answers for each chunk.
Outcome:	Extensive experiments on QuAC and TriviaQA show that the proposed model performs well for long document reading.

Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework (2025.emnlp-main)

Copied to clipboard

Cai Ke, Yiming Du, Bin Liang, Yifan Xiang, Lin Gui, Zhongyang Li, Baojun Wang, Yue Yu, Hui Wang, Kam-Fai Wong, Ruifeng Xu

OPERA: Operation-Pivoted Discrete Reasoning over Text (2022.naacl-main)

Challenge:	Large language models extract useful information from conversation history to enhance the response in long-term conversations.
Approach:	They propose a Fragment-then-Compose framework to optimize memory utilization for long-term open-domain conversation.
Outcome:	The proposed framework can be used to extract useful information from conversation history . it can be adapted to different situations and improve response generation .

Copied to clipboard

Yongwei Zhou, Junwei Bao, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He, Tiejun Zhao

WebSynthesis: World Model-Guided Monte Carlo Tree Search for Efficient WebAgent Trajectory Synthesis (2026.acl-long)

Challenge:	Existing methods to predict logical forms ignore the utilization of symbolic operations and lack reasoning ability and interpretability.
Approach:	They propose an operation-pivoted discrete reasoning framework that uses symbolic operations as neural modules to facilitate reasoning ability and interpretability.
Outcome:	Extensive experiments on DROP and RACENum datasets show the reasoning ability of OPERA.

Copied to clipboard

Yifei Gao, Junhong Ye, Yifan Yang, Jiaqi Wang, Yi Zhang, Zhang Ruichen, Jitao Sang

Green & Sustainable NLP

Challenge:	Recent advances in large language models have enabled increasingly capable web agents . however, training such agents at scale still relies on high-quality interaction trajectories that are difficult to obtain at scale.
Approach:	They propose a framework for scalable trajectory synthesis that simulates state transitions without network dependencies and integrates Monte Carlo Tree Search to enable reversible exploration over the simulated state space.
Outcome:	Experiments on WebArena, WebVoyager, and Mind2Web-Online show that agents trained exclusively on synthesized trajectories outperform those trained on real-world data.

Less Likely Brainstorming: Using Language Models to Generate Alternative Hypotheses (2023.findings-acl)

Copied to clipboard

Liyan Tang, Yifan Peng, Yanshan Wang, Ying Ding, Greg Durrett, Justin Rousseau

Can Vision-Language Models Solve Visual Math Equations? (2025.emnlp-main)

Challenge:	Existing methods to reduce cognitive errors in MRI interpretations do not work for generating less likely outputs.
Approach:	They propose a task that asks a model to generate outputs that humans think are relevant but less likely to happen.
Outcome:	The proposed method compares with several state-of-the-art controlled text generation models via automatic and human evaluations and shows that it reduces cognitive errors in interpreting MRI findings.

Copied to clipboard

Monjoy Narayan Choudhury, Junling Wang, Yifan Hou, Mrinmaya Sachan

Visual Data in NLP

Challenge:	Vision-Language Models (VLMs) perform well on textual equations, but fail on visually grounded counterparts.
Approach:	They propose to decompose visual equation solving into symbolic equation solving and visual recognition into two core components to understand this gap.
Outcome:	The proposed models perform well on textual equations, but fail on visual grounded ones.

TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks (2026.findings-acl)

Copied to clipboard

Yuanze Hu, Xinyu Wang, Zhichao Yang, Gen Li, Ye Qiu, Zhaoxin Fan, Yifan Sun, Wenjun wu, Jin Dong, Xiaotie Deng

P3LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training (2022.findings-emnlp)

Challenge:	Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications.
Approach:	They propose a framework that retrieves context from a memory bank to enhance alignment . they propose EMI-based approach to align vision and language models .
Outcome:	The proposed framework reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead.

Copied to clipboard

Junwei Bao, Yifan Wang, Ying Jiangyong, Yeyun Gong, Jing Zhao, Youzheng Wu, Xiaodong He

Improving LLM Reasoning through Interpretable Role-Playing Steering (2025.findings-emnlp)

Challenge:	Existing autoregressive left-to-right (L2R) models are limited to unidirectional information and constrained on strong local dependencies.
Approach:	They propose a probabilistically permuted prophet language model which strengthens the modeling of bidirectional information and long token dependencies for sequence generation.
Outcome:	Experiments on GLGE dataset show that P3LM improves on natural language generation tasks.

Copied to clipboard

Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du

LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking (2022.naacl-main)

Challenge:	Existing methods for role-playing rely on prompt engineering, which lacks stability and interpretability.
Approach:	They propose a framework that extracts latent representations from role-play prompts and constructs a steering vector that can be injected into the model's residual stream with controllable intensity.
Outcome:	The proposed framework extracts latent representations from role-play prompts, selects the most relevant features based on activation patterns, and constructs a steering vector that can be injected into the model’s residual stream with controllable intensity.

Copied to clipboard

Yifan Wang, Jing Zhao, Junwei Bao, Chaoqun Duan, Youzheng Wu, Xiaodong He

Can MLLMs Reason Beyond Language? VisReason: A Comprehensive Benchmark for Vision-Centric Reasoning (2026.findings-acl)

Challenge:	Existing methods exploit the utterances of all dialogue turns to assign value to slots . this can lead to suboptimal results due to information introduced from irrelevant utterrances .
Approach:	They propose a SLot-TUrN Alignment enhanced approach to assign slot value . they explicitly align each slot with its most relevant utterance and then predict the corresponding value based on this aligned utteration.
Outcome:	The proposed approach achieves state-of-the-art on three multi-domain task-oriented dialogue datasets.

Copied to clipboard

Longteng Guo, Yifan Wang, Pengkang Huo, Tailai Chen, Yuze Wu, Jing Liu, Xinxin Zhu

SCOTT: Self-Consistent Chain-of-Thought Distillation (2023.acl-long)

Challenge:	Recent advances in multimodal large language models demonstrate strong performance on visual reasoning benchmarks.
Approach:	They propose a benchmark for vision-centric reasoning that integrates visual and textual information for non-trivial reasoning.
Outcome:	The proposed benchmark exposes gaps between humans and current MLLMs and reveals limited benefits from test-time reasoning strategies.

Copied to clipboard

Peifeng Wang, Zhengyang Wang, Zheng Li, Yifan Gao, Bing Yin, Xiang Ren

LongEmbed: Extending Embedding Models for Long Context Retrieval (2024.emnlp-main)

Challenge:	Large language models (LMs) generate free-text rationales for their predictions via chain-of-thought prompting, but there is little guarantee that the generated rationale is consistent with LM’s predictions or faithfully justify the decisions.
Approach:	They propose a faithful knowledge distillation method to learn a small, self-consistent CoT model from a larger teacher model by contrastive decoding.
Outcome:	The proposed method yields comparable performance but is less faithful than baselines.

Copied to clipboard

Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li

Representation Learning

Challenge:	Existing embedding models support only 512 input tokens, hindering their application in scenarios requiring long inputs.
Approach:	They evaluate the performance of existing embedding models by using a new benchmark and a training-free context window extension strategy.
Outcome:	The proposed model extends the input window of existing models by several folds.

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning (2025.coling-main)

Copied to clipboard

Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen

Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)

Challenge:	Experimental results show that visual instruction tuning improves performance of Multi-modal Large Language Models (MLLMs) to extend the application scope of Large Language Modells, a surge of work augments LLMs with vision encoders to endow the ability of multi-modal cognition and reasoning.
Approach:	They propose a systematic approach to create high-quality visual reasoning instructions using a synthesize-complicate-reformulate paradigm.
Outcome:	The proposed method improves performance of MLLMs by 27.86% and 27.60% on MME-Perception and MME Cognition.

Copied to clipboard

Yuntao Wen, Ruixiang Feng, Feng Guo, Yifan Wang, Ran Le, Yang Song, Shen Gao, Shuo Shang

Challenge:	Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities.
Approach:	They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction.
Outcome:	Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities.

Training LLMs for Optimization Modeling via Iterative Data Synthesis and Structured Validation (2025.findings-emnlp)

Copied to clipboard

Yang Wu, Yifan Zhang, Yurong Wu, Yuran Wang, Junkai Zhang, Jian Cheng

Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are a promising tool for OR, but they face challenges when dealing with complex problems.
Approach:	They propose a framework that augments existing datasets and generates high-quality fine-tuning data tailored to OR.
Outcome:	The proposed framework augments existing datasets and generates high-quality fine-tuning data . it prevents error propagation and ensures the quality of the generated dataset .

Copied to clipboard

Yifan Sun, Danding Wang, Qiang Sheng, Juan Cao, Jintao Li

Memory or Reasoning? Explore How LLMs Compute Mixed Arithmetic Expressions (2025.findings-acl)

Challenge:	Existing concepts-based explainable approaches do not discover unseen concepts . a recent approach to solve this problem is concept-based explanations .
Approach:	They propose a framework that extracts comprehensible concepts automatically with no annotations . ECO-Concept uses an object-centric architecture to extract task-specific semantic concepts .
Outcome:	a new framework extracts comprehensible concepts with no concept annotations . the proposed framework outperforms existing methods in computability tests on diverse tasks .

Copied to clipboard

Chengzhi Li, Heyan Huang, Ping Jian, Zhen Yang, Chenxu Wang, Yifan Wang

Using Perspectival Words Is Harder Than Vocabulary Words for Humans —and Even More So for Multimodal Language Models (2026.acl-long)

Challenge:	Large language models (LLMs) can solve complex multi-step math reasoning problems, but their internal implementation is limited.
Approach:	They propose to use a "Causal Effect Driven F**ine-tuning method" to improve LLMs' reasoning ability.
Outcome:	The proposed method improves the model's reasoning ability by enhancing key components that are used to execute mixed arithmetic calculations.

Copied to clipboard

Dota Tianai Dong, Yifan Luo, Po-Ya Angela Wang, Asli Ozyurek, Paula Rubio-Fernandez

SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (2026.findings-acl)

Challenge:	Existing evaluations of multimodal language models focus on vocabulary words with relatively stable, context-independent meanings in conversation, such as object names, colors, and verbs.
Approach:	They compare human and multimodal language models in their use of three word types: vocabulary, possessives, and demonstratives.
Outcome:	The models approach human-level performance on using vocabulary, but exhibit clear deficits with possessives and even greater difficulties with demonstratives.

Copied to clipboard

Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin, Yangqiu Song

FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery (2023.findings-acl)

Challenge:	Existing models fail to capture and model customer intention effectively because of insufficient information exploitation and only apparent information like descriptions and titles are used.
Approach:	They propose to exploit existing session data to capture and model intention in E-commerce product purchase sessions using a multimodal benchmark.
Outcome:	The proposed framework can bridge the gap between intention understanding in simplified research cases like co-buy intention and more complex yet practical scenarios like session history.

Copied to clipboard

Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin

Commonsense Reasoning

Challenge:	Existing intention-based studies on recommendation tasks are limited and use models to implicitly model the intention memberships.
Approach:	They propose a framework that leverages the generation power of large language models and human-in-the-loop annotation to semi-automatically construct the intention knowledge graph.
Outcome:	The proposed framework can model e-commerce knowledge and have many potential applications.

Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context (2025.emnlp-main)

Copied to clipboard

Rushi Wang, Jiateng Liu, Cheng Qian, Yifan Shen, Yanzhou Pan, Zhaozhuo Xu, Ahmed Abbasi, Heng Ji, Denghui Zhang

SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)

Challenge:	Incorporating external context can enhance the response quality of Large Language Models (LLMs). however, real-world contexts often mix relevant information with disproportionate inappropriate content.
Approach:	They propose a Poisoned Context Testbed to pair queries with real-world contexts . they propose 'rw-Steering' to internalize inappropriate signals .
Outcome:	The proposed model improves response quality by 39.8% and reverses undesirable behavior curve.

Copied to clipboard

Hui Wang, Jinghua Zhao, Yifan Yang, Shujie Liu, Junyang Chen, Yanzhe Zhang, Shiwan Zhao, Jinyu Li, Jiaming Zhou, Haoqin Sun, Yan Lu, Yong Qin

SimpleDoc: Multi‐Modal Document Understanding with Dual‐Cue Page Retrieval and Iterative Refinement (2025.emnlp-main)

Challenge:	Existing methods for evaluating the perceptual quality of synthetic speech are limited due to the complexity of perceptual quality factors and the diversity of speech generation tasks.
Approach:	They propose a new paradigm for enabling large language models to conduct structured speech quality evaluation using a large-scale dataset.
Outcome:	The proposed model performs well across tasks and languages.

Copied to clipboard

Chelsi Jain, Yiran Wu, Yifan Zeng, Jiale Liu, Shengyu Dai, Zhenwen Shao, Qingyun Wu, Huazheng Wang