Papers by Yang Feng

Static Models, Dynamic World: A Unified Perspective on Temporal Perception in Large Language Models (2026.findings-acl)

Challenge:	Unsupervised neural machine translation (NMT) is a new approach for machine translation . the model uses only one shared encoder to map pairs of sentences from different languages to a shared-latent space .
Approach:	They propose an unsupervised approach which trains the model without labeling data . they propose two independent encoders but share some partial weights to extract high-level representations of input sentences.
Outcome:	The proposed approach achieves significant improvements on English-German, English-French and Chinese-to-English translation tasks.

Copied to clipboard

Chenhao Li, Dandan Song, Changzhi Zhou, Jun Yang, Yuhang Tian, Huipeng Ma, Guangyuan Feng, Luan Zhang, Xudong Li, Ke Duan

Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions (2022.emnlp-main)

Challenge:	Large language models are trained on static corpora but deployed in a dynamic world . a foundational tension remains between time and the ability to understand it .
Approach:	They formalize temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers.
Outcome:	The proposed framework formalizes temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers . the framework induces four temporal information regimes corresponding to internal reasoning, answer recency, premise anchoring, and genuine world indeterminacy .

Copied to clipboard

Shuhao Gu, Bojie Hu, Yang Feng

DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)

Challenge:	Currently, continuous learning methods suffer from catastrophic forgetting problem, causing model to forget previous knowledge while learning new knowledge.
Approach:	They propose a two-stage continuous learning method based on local features of the real loss to avoid catastrophic forgetting problem.
Outcome:	The proposed method achieves significant improvements on domain adaptation and more challenging language adaptation tasks.

Copied to clipboard

Zhenyang Cai, Jiaming Zhang, Junjie Zhao, Ziyi Zeng, Yanchao Li, Liang Jingyi, Junying Chen, Yunjin Yang, Jiajun You, Shuzhi Deng, null Xieruiqiii, Yuanting Chen, Xiangyi Feng, Jianquan Li, Liangyi Chen, Junwen Wang, Shan Jiang, Benyou Wang

Composable Text Controls in Latent Space with ODEs (2023.emnlp-main)

Challenge:	Current multimodal large language models (MLLMs) show limited understanding of dental images.
Approach:	They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning.
Outcome:	The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks.

Copied to clipboard

Guangyi Liu, Zeyu Feng, Yuan Gao, Zichao Yang, Xiaodan Liang, Junwei Bao, Xiaodong He, Shuguang Cui, Zhen Li, Zhiting Hu

Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization (2026.findings-acl)

Challenge:	Existing approaches to composable text operations often require plug-and-play . a single LM can perform arbitrary text operation composition in the latent space .
Approach:	They propose an efficient approach for composable text operations in the latent space of text . they connect pretrained LMs to the laten space and adapt them to the space .
Outcome:	The proposed approach improves on existing methods in the latent space of text.

Copied to clipboard

Jiantong Jiang, Peiyu Yang, Rui Zhang, Feng Liu

A Learnable Skill Combination Strategy for Multi-task Learning in Natural Language Understanding (2026.findings-acl)

Challenge:	Large language models (LLMs) are a powerful tool for high-performance inference serving.
Approach:	They focus on system-aware KV infrastructure for serving LLMs . they analyze cross-behavior co-design affinity and behavior-objective links .
Outcome:	The proposed key-value (KV) cache is crucial for low-latency, high-throughput LLM inference serving.

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, Mengfei Guo, Xiaoting Wu, Junlan Feng

Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models (2025.emnlp-main)

Challenge:	a novel multi-task learning framework for domain-specific natural language understanding tasks addresses these limitations by combing multiple tasks into a single framework.
Approach:	They propose a multi-task learning framework that decomposes the language model into modular skill components and employs a dynamic, learnable skill-combination mechanism to adaptively handle diverse tasks.
Outcome:	The proposed framework surpasses conventional multi-task learning approaches in performance.

Copied to clipboard

Qihang Ma, Shengyu Li, Jie Tang, Dingkang Yang, null Chenshaodong, Yingyi Zhang, Chao Feng, Ran Jiao

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Challenge:	Multi-modal keyphrase prediction (MMKP) aims to produce concise, informative phrases that capture the essence of cross-modal inputs.
Approach:	They propose to use vision-language models to generate conclusive phrases using multiple modalities of input information.
Outcome:	The proposed methods outperform existing methods on absence and unseen scenarios and overestimate model capability due to overlap in training tests.

Copied to clipboard

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

LLM-based Translation Inference with Iterative Bilingual Understanding (2025.findings-acl)

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

Copied to clipboard

Andong Chen, Kehai Chen, Yang Xiang, Xuefeng Bai, Muyun Yang, Yang Feng, Tiejun Zhao, Min Zhang

Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation (2023.emnlp-main)

Challenge:	Existing studies show that the ability of large language models to generate contextual understanding of the sentence can degrade translation quality.
Approach:	They propose a method that generates contextual understanding for both source and target languages separately.
Outcome:	The proposed method outperforms strong comparison methods in multiple domains.

Copied to clipboard

Wenyu Guo, Qingkai Fang, Dong Yu, Yang Feng

Neural Machine Translation with Phrase-Level Universal Visual Representations (2022.acl-long)

Challenge:	Existing models require associated image with input sentence, which is difficult to satisfy at inference.
Approach:	They propose to use synthetic and authentic images to generate translations using text-to-image generation models.
Outcome:	The proposed model achieves state-of-the-art performance on En-De and En-Fr datasets while remaining independent of authentic images during inference.

Copied to clipboard

Qingkai Fang, Yang Feng

SwiftPrune: Hessian-Free Weight Pruning for Large Language Models (2025.findings-emnlp)

Challenge:	Existing multimodal machine translation methods require paired input of source sentence and image, which makes them suffer from shortage of sentence-image pairs.
Approach:	They propose a phrase-level retrieval-based method to get visual information from existing sentence-image data sets.
Outcome:	The proposed method significantly outperforms strong baselines on multiple MMT datasets, especially when the textual context is limited.

Copied to clipboard

Yuhan Kang, Yang Shi, Mei Wen, Jun He, Jianchao Yang, Zeyu Xue, Jing Feng, Xinwang Liu

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty (2025.findings-emnlp)

Challenge:	a novel post-training pruning method relies on the Hessian matrix to perform pruning . current pruning methods are computationally intensive and lack performance due to second-order derivative calculations.
Approach:	They propose a Hessian-free weight pruning method that reduces computational burden . they use an Exponentially Weighted Moving Average technique to bypass weight sorting .
Outcome:	The proposed method achieves hardware-efficient model compression by eliminating computational intensive calculations.

Copied to clipboard

Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao, Manuel Mager, Nikolaos Pappas, Kishaloy Halder, Yang Li, Yassine Benajiba, Dan Roth

Challenge:	Existing methods to gauge model’s uncertainty through self-consistency in responses to the target query are misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same query when answering a knowledge-preserving perturbation of the query.
Approach:	They propose a method that uses multi-agent interaction to estimate black-box LLMs' uncertainty.
Outcome:	The proposed method outperforms existing self-consistency based methods and improves hallucination detection.

Rethinking Diverse Human Preference Learning through Principal Component Analysis (2025.findings-acl)

Copied to clipboard

Feng Luo, Rui Yang, Hao Sun, Chunyuan Deng, Jiarui Yao, Jingyan Shen, Huan Zhang, Hanjie Chen

Explainability & Interpretability in NLP

Challenge:	Decomposed Reward Models extract diverse human preferences from binary comparisons without fine-grained annotations.
Approach:	They propose a decomposed reward model that extracts diverse human preferences from binary comparisons without fine-grained annotations.
Outcome:	The proposed approach extracts diverse human preferences from binary comparisons without fine-grained annotations.

LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis (2025.acl-long)

Copied to clipboard

Qingkai Fang, Yan Zhou, Shoutao Guo, Shaolei Zhang, Yang Feng

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation (2026.findings-acl)

Challenge:	LLaMA-Omni 2 is a series of speech language models (SpeechLMs) based on large language models.
Approach:	They introduce a series of speech language models capable of real-time speech interaction . LLaMA-Omni 2 trains on 200K multi-turn speech dialogue samples .
Outcome:	The proposed speech language models surpass state-of-the-art models on spoken question answering and speech instruction.

Copied to clipboard

Haonan Shangguan, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Feiliang Ren, Ge Yu

CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)

Challenge:	Current approaches for Multimodal Sentiment Analysis (MSA) rely on parameter-heavy LLMs for classification, overlooking multimodal sentiment reasoning generation in resource-limited environments.
Approach:	They propose a multimodal sentiment reasoning distillation model that employs a teacher-assistant-student paradigm to address deployment constraints in resource-limited environments.
Outcome:	The proposed model performs well on a resource-limited JMSRC task with only 3B parameters and shows generalization and interpretability.

Copied to clipboard

Feiteng Fang, Liang Zhu, Xi Feng, Jinchang Hou, Qixuan Zhao, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles (2025.acl-long)

Challenge:	Large language models (LLMs) have attracted considerable attention from academic and industrial communities due to their outstanding performance in various natural language processing tasks.
Approach:	They propose a Contrastive Learning Framework for Human Alignment to evaluate the noise within the data and dynamically adjust the training process.
Outcome:	The proposed framework surpasses other algorithms in terms of reward model scores, automatic evaluations, and human assessments on the widely used dataset "Helpful and Harmless"

Copied to clipboard

Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li

How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026.acl-industry)

Challenge:	Existing user simulators lack authenticity and user-level diversity in interactions with large language models.
Approach:	They propose a user simulator with implicit user profiles that infers user profiles from human-machine interactions to simulate personalized and realistic dialogues.
Outcome:	The proposed framework outperforms baselines in authenticity and diversity while maintaining comparable consistency.

Copied to clipboard

Yongqi Tong, Xiaoyun Feng, Lyuxin Xue, Jianshe Li, Xin Zhang, Jiang-Ming Yang

Challenge:	Traditional industrial agents rely on modular workflows that fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency.
Approach:	They propose a paradigm shift from external workflows to internalized knowledge representation that consolidates complex business logic and SOPs directly into the model’s parameters.
Outcome:	The proposed model breaks the impossible triangle of latency, accuracy, and complexity.

MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production (2024.findings-acl)

Copied to clipboard

Jian Ma, Wenguan Wang, Yi Yang, Feng Zheng

GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News Summarization (2024.emnlp-main)

Challenge:	Existing solutions for sign language production are limited due to phonological differences and data scarcity.
Approach:	They propose a unified framework for continuous sign language production that generates sign predictions step by step from text or speech embeddings.
Outcome:	The proposed model achieves competitive performance on how2sign and PHOENIX14T datasets.

Copied to clipboard

Yangfan Ye, Xiachong Feng, Xiaocheng Feng, Weitao Ma, Libo Qin, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models (2026.findings-acl)

Challenge:	Current studies focus on single-language or single-document tasks for news summarization . lack of a benchmark inhibits researchers from adequately studying this invaluable problem.
Approach:	They propose a novel task that unifies Multi-lingual, Cross-lingual and Multi-document Summarization into one task.
Outcome:	The proposed task encapsulates the real-world requirements all-in-one and is validated by extensive analysis.

Copied to clipboard

Zhen Yang, Xinyue Zhang, Ping Jian, Chengzhi Li, Zhongbin Guo, Jiaping Feng, Wenpeng Lu

Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation (2022.findings-emnlp)

Challenge:	Large Language Models (LLMs) exhibit notable deficiencies in temporal reasoning . phrasing changes can lead LLMs to produce inconsistent outputs .
Approach:	They investigate the mechanistic interpretability of temporal ordering within event temporal reasoning . they identify a sparse subset of attention heads that are causally responsible for reasoning outcomes .
Outcome:	The proposed model outperforms other models in a variety of tasks and is validated by intervention-based experiments.

Copied to clipboard

Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)

Challenge:	Existing methods to perform adaptive and fixed translations lack evaluation before taking actions.
Approach:	They propose a method to perform adaptive translation policy via post-evaluation into fixed policy . their method evaluates rationality of next action by measuring change in source content .
Outcome:	The proposed method exceeds strong baselines under all latency.

Copied to clipboard

Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu

Prediction Difference Regularization against Perturbation for Neural Machine Translation (2022.acl-long)

Challenge:	Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models.
Approach:	They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness.
Outcome:	The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models.

Copied to clipboard

Dengji Guo, Zhengrui Ma, Min Zhang, Yang Feng

ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive Framework (2025.acl-long)

Challenge:	Existing methods for regularizing input perturbation are limited by under-fitting of training data.
Approach:	They propose a method that can reduce over-fitting and under-fitting at the same time.
Outcome:	The proposed method can reduce over-fitting and under-fitturing while making the model less sensitive to small input changes and more robust to under-perturbed training data.

Copied to clipboard

Hengyuan Zhang, Chenming Shang, Sizhe Wang, Dongdong Zhang, Yiyao Yu, Feng Yao, Renliang Sun, Yujiu Yang, Furu Wei

Refining Source Representations with Relation Networks for Neural Machine Translation (C18-1)

Challenge:	Experiments show that ShifCon significantly enhances the performance of non-dominant languages due to the imbalance in training data across languages.
Approach:	They propose a Shift-based multilingual Contrastive framework that aligns the internal forward process of other languages toward that of the dominant one.
Outcome:	The proposed framework significantly improves performance of non-dominant languages, particularly for low-resource ones.

Copied to clipboard

Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)

Challenge:	Existing neural machine translation frameworks that forget distant information and disregard relationship between source and target words are not effective.
Approach:	They propose to use relation networks to learn better representations of the source . they propose to associate source words with each other to help retain their relationships .
Outcome:	Experiments show that the proposed approach outperforms the encoder-decoder framework on several datasets.

Copied to clipboard

Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu

Structured Data in NLP

Challenge:	Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.
Approach:	They propose a framework that compresses web agent trajectories via graph-based pruning.
Outcome:	The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models.

TexSmart: A System for Enhanced Natural Language Understanding (2021.acl-demo)

Copied to clipboard

Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, ZhanHui Kang, Shuming Shi

PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction (2021.acl-long)

Challenge:	TexSmart supports fine-grained named entity recognition (NER) Large-scale fine-granular entity types are expected to provide richer semantic information for downstream NLP applications.
Approach:	They introduce TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Outcome:	The proposed system supports fine-grained named entity recognition (NER) and enhanced semantic analysis functions.

Copied to clipboard

Shulin Liu, Tao Yang, Tianchi Yue, Feng Zhang, Di Wang

TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning (2025.findings-acl)

Challenge:	Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts.
Approach:	They propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) which jointly learns how to understand language and correct spelling errors.
Outcome:	The proposed model outperforms state-of-the-art methods on widely used benchmarks and achieves superior performance against existing models.

Copied to clipboard

Mingyu Zheng, Zhifan Feng, Jia Wang, Lanrui Wang, Zheng Lin, Hao Yang, Weiping Wang

Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation (2022.acl-long)

Challenge:	Existing methods for table instruction tuning are limited due to limited data diversity and lack of data quality.
Approach:	They propose a weakness-guided data synthesis framework for table instruction tuning that explores the vast input space of table understanding tasks and then iterates through the input space.
Outcome:	The proposed framework boosts the average accuracy of Llama3.1-8B-instruct by 11.62% with 27K GPT-4o synthetic data and outperforms state-of-the-art data synthesis baselines which use more training data.

Copied to clipboard

Chenze Shao, Yang Feng

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)

Challenge:	Neural networks tend to gradually forget the previously learned knowledge when learning multiple tasks sequentially from dynamic data distributions.
Approach:	They propose a method that iteratively provides complementary knowledge to student models by dynamically updating teacher models trained on specific data orders.
Outcome:	The proposed method improves on multiple machine translation tasks and improves performance over baseline systems.

Copied to clipboard

Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana

MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)

Challenge:	Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100.
Approach:	They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth.
Outcome:	The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth.

Copied to clipboard

Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

Attack Prompt Generation for Red Teaming and Defending Large Language Models (2023.findings-emnlp)

Challenge:	Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs.
Approach:	They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints.
Outcome:	The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks.

Copied to clipboard

Boyi Deng, Wenjie Wang, Fuli Feng, Yang Deng, Qifan Wang, Xiangnan He

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models (2026.acl-long)

Challenge:	Existing studies construct attack prompts via manual or automatic methods, but these methods have limitations on cost and quality.
Approach:	They propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning and a defense framework that fine-tunes victim LLM's through iterative interactions with the attack framework.
Outcome:	The proposed approach is based on experiments on different LLMs to evaluate their effectiveness against red teaming attacks.

Copied to clipboard

Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang

Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models (2024.emnlp-main)

Challenge:	Structured pruning is a practical approach to deploying large language models (LLMs) but it fails to capitalize on modest task-specific calibration signals, causing limited downstream gains.
Approach:	They propose a method that removes attention heads and MLP channels using loss-based important scores . they use perplexity for language modeling and a margin-based objective for decision-style tasks .
Outcome:	The proposed method lowers perplexity and improves accuracy at higher sparsity . it also stabilizes accuracy and mitigates perxity collapse without fine-tuning .

Copied to clipboard

Keqin Bao, Jizhi Zhang, Yang Zhang, Xinyue Huo, Chong Chen, Fuli Feng

EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding (2025.findings-acl)

Challenge:	Existing approaches to adapt Large Language Models (LLMs) for recommendation encounter significant challenges such as amplification bias and homogeneity.
Approach:	They propose a new decoding approach called Debiasing-Diversifying Decoding (D3) that disables length normalization for ghost tokens to alleviate amplification bias and incorporates a text-free assistant model to encourage tokens less frequently generated by LLMs for counteracting recommendation homogeneity.
Outcome:	Extensive experiments on real-world datasets demonstrate the proposed approach’s effectiveness in enhancing accuracy and diversity.

Copied to clipboard

Mingxu Tao, Jie Hu, Mingchuan Yang, Yunhuai Liu, Dongyan Zhao, Yansong Feng

Dual-Phase Accelerated Prompt Optimization (2024.findings-emnlp)

Challenge:	Existing methods to enhance performance of Large language models are limited due to the cost of training data and privacy concerns.
Approach:	They propose a method that enhances a finetuned model with its inferior version and adopts contrastive decoding to reduce predicted errors.
Outcome:	The proposed method outperforms existing methods in data-scarcity scenarios across three domains and shows that it is more robust and robust.

Copied to clipboard

Muchen Yang, Moxin Li, Yongle Li, Zijun Chen, Chongming Gao, Junqi Zhang, Yangyang Li, Fuli Feng

Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mapping (2022.findings-emnlp)

Challenge:	Existing methods for prompt optimization make light of the importance of high-quality initialization and the identification of effective directions.
Approach:	They propose a method which uses a meta-instruction to generate high-quality initial prompts and iteratively optimize them at the sentence level.
Outcome:	The proposed method achieves consistent accuracy gain over baselines with less than five optimization steps.

Copied to clipboard

Shuhao Gu, Yang Feng

Latent Inter-User Difference Modeling for LLM Personalization (2025.emnlp-main)

Challenge:	Existing model structure and training scheme cannot ensure universal representations and cross-mappings because of lacking explicit constraints.
Approach:	They propose a state mover’s distance model to model the difference of the representations output by the encoder and a agreement-based training scheme to minimize the proposed distance to learn universal representations.
Outcome:	The proposed model can translate between languages unseen during training, i.e., zero-shot translation.

Copied to clipboard

Yilun Qiu, Tianhao Shi, Xiaoyan Zhao, Fengbin Zhu, Yang Zhang, Fuli Feng

CPL: Counterfactual Prompt Learning for Vision and Language Models (2022.emnlp-main)

Challenge:	Large language models (LLMs) are increasingly integrated into users’ daily lives, leading to a growing demand for personalized outputs.
Approach:	They propose a framework that models inter-user differences in the latent space instead of relying on language-based prompts.
Outcome:	The proposed framework outperforms baseline methods on personalized review generation.

Copied to clipboard

Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Wang

HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition (2024.acl-long)

Challenge:	Existing prompt tuning methods tend to learn spurious or entangled representations, leading to poor generalization to unseen concepts.
Approach:	They propose a prompt tuning technique that tunes the learnable prompt for pre-trained vision and language models.
Outcome:	The proposed method improves few-shot performance on vision and language tasks over existing prompt tuning methods.

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation (P19-1)

Challenge:	Large language models (LLMs) are a promising alternative to expensive human evaluations.
Approach:	They propose a framework that iteratively aligns LLM-based evaluators with human preference . they decompose a given evaluation task into finer-grained criteria .
Outcome:	The proposed framework iteratively aligns LLM-based evaluators with human preference . it decomposes a given evaluation task into finer-grained criteria . the framework is efficient to train and more explainable than relying solely on prompts .

Copied to clipboard

Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen, Jie Zhou

Knowledge Distillation based Contextual Relevance Matching for E-commerce Product Search (2022.emnlp-industry)

Challenge:	Experimental results show that the Reinforce-NAT system surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed.
Approach:	They propose a sequence-level training method and a Transformer decoder to fuse the target sequential information into the top layer of the decoded Transformer.
Outcome:	The proposed model surpasses the baseline NAT system on BLEU without decelerating the decoding speed and achieves comparable translation performance to the autoregressive Transformer model with considerable speedup.

Copied to clipboard

Ziyang Liu, Chaokun Wang, Hao Feng, Lingfei Wu, Liqun Yang

Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model (2021.findings-emnlp)

Challenge:	Existing approaches to e-commerce relevance matching ignore bipartite graphs in logs . experimental results show that proposed method improves human relevance judgment .
Approach:	They propose an efficient knowledge distillation framework for e-commerce relevance matching to exploit the advantages of Transformer-style and classical relevance matching models.
Outcome:	The proposed method significantly improves human relevance judgment on large-scale real-world data.

Copied to clipboard

PsyChain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling Dialogues (2026.findings-acl)

Challenge:	Dot-product attention only considers the pair-wise correlation between words, resulting in dispersion when dealing with long sentences and neglecting source neighboring relationships.
Approach:	They propose to model concentrated attention in cross-attention using a Gaussian Mixture Model to model cross- attention in a language model.
Outcome:	Experiments on three datasets show that the proposed method outperforms the baseline and has significant improvement on alignment quality, N-gram accuracy, and long sentence translation.

Copied to clipboard

Yi Feng, Zijie Yang, Chen Zhang, Wenxuan Zhang, Dongming Zhang, Liping Jing, Jian Yu

A Sequence-to-Sequence Approach to Dialogue State Tracking (2021.acl-long)

Challenge:	Existing psychological counseling datasets suffer from monolithic client personas, insufficient therapeutic depth, and a lack of process controllability.
Approach:	They propose a framework that evolves static counseling corpora into high-fidelity dialogues . they use a Client Profiler that pairs life scenarios with psychological personality archetypes based on client personality and stage progression .
Outcome:	The proposed framework achieves 61-91% win rates against domain-specific baselines in pairwise evaluation and the highest average score in human evaluation, indicating potential for real-world counseling.

Copied to clipboard

Yue Feng, Yang Wang, Hang Li

PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)

Challenge:	Existing methods for dialogue state tracking are still challenging, but they are improving . a new approach to dialogue state monitoring is proposed, called Seq2Seq-DU .
Approach:	They propose a new dialogue state tracking module that formalizes DST as a sequence-to-sequence problem.
Outcome:	The proposed method outperforms existing methods on benchmark datasets in different settings.

Copied to clipboard

Chengbing Wang, Wuqiang Zheng, Yang Zhang, Fengbin Zhu, Junyi Cheng, Yi Xie, Wenjie Wang, Fuli Feng

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

Challenge:	Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy.
Approach:	They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality .
Outcome:	a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset.

Copied to clipboard

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

Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (2026.acl-long)

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

Copied to clipboard

Zizhen Wang, Bo Feng, Zhengfeng Lai, Shiyu Li, Yang Lu, Meng Cao, Ping Huang, Xiaoming Simon Wang

AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation (2025.findings-acl)

Challenge:	Existing metrics for video captioning are based on text-based comparisons with ground-truth references.
Approach:	They propose a reference-free benchmark that assesses video captions based on their utility . they will release the benchmark to facilitate reproducible research .
Outcome:	The proposed benchmark improves on human-verified, fine-grained questions . it correlates significantly better with human judgments than existing metrics .

Copied to clipboard

Ming Wang, Peidong Wang, Lin Wu, Xiaocui Yang, Daling Wang, Shi Feng, Yuxin Chen, Bixuan Wang, Yifei Zhang

Interpretable Math Word Problem Solution Generation via Step-by-step Planning (2023.acl-long)

Challenge:	Existing models of seeker simulations are limited by the cost and ethical concerns of involving real seekers in mental health research.
Approach:	They propose an emotional and cognitive dynamic agent system equipped with tertiary memory to enable dynamic control of the simulator's configurations.
Outcome:	The proposed system achieves more realistic seeker simulation compared to baselines.

Copied to clipboard

Mengxue Zhang, Zichao Wang, Zhichao Yang, Weiqi Feng, Andrew Lan

TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement (2025.findings-naacl)

Challenge:	Existing approaches to solving math word problems focus on obtaining the correct answer.
Approach:	They propose a step-by-step planning approach for intermediate solution generation that strategically plans the generation of the next solution step based on the MWP and the previous solution steps.
Outcome:	The proposed approach improves the accuracy and interpretability of the solution on automatic metrics and human evaluation.

Copied to clipboard

Zhaopeng Feng, Yan Zhang, Hao Li, Bei Wu, Jiayu Liao, Wenqiang Liu, Jun Lang, Yang Feng, Jian Wu, Zuozhu Liu

CTC-based Non-autoregressive Textless Speech-to-Speech Translation (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). human evaluations reveal that LLM-generated translations still contain various errors.
Approach:	They propose a LLM-based self-refinement framework that feeds error information back into LLMs to facilitate self-finement, leading to enhanced translation quality.
Outcome:	The proposed framework outperforms internal refinement and feedback methods while ensuring a robust translation quality baseline.

Copied to clipboard

Qingkai Fang, Zhengrui Ma, Yan Zhou, Min Zhang, Yang Feng

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration (2026.findings-acl)

Challenge:	Existing direct speech-to-speech translation models require text supervision during training, which is not feasible for numerous unwritten languages.
Approach:	They propose a non-autoregressive (NAR) model that generates discrete units from the source speech and employs a unit-based vocoder to synthesize the target.
Outcome:	The proposed model achieves translation quality comparable to the autoregressive model while preserving up to 26.81 decoding speedup.

Copied to clipboard

Zhuofan Wen, Yang Feng

Efficient Training for Cross-lingual Speech Language Models (2026.findings-acl)

Challenge:	Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models.
Approach:	They propose a self-draft framework that suppresses spurious confidence via layer-wise temperature annealing in early-exit decision and adaptively bounds speculation length based on token-wise decoding difficulty.
Outcome:	The proposed framework suppresses spurious confidence and bounds speculation length based on token-wise decoding difficulty.

Copied to clipboard

Yan Zhou, Qingkai Fang, Yun Hong, Yang Feng

DeepMed: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference (2026.findings-acl)

Challenge:	Currently, large language models (LLMs) focus on the text modality, making speech modeling difficult.
Approach:	They propose a cross-lingual speech language model that trains on discrete speech tokens to achieve cross-modal and cross-linguistic alignment through continual pre-training.
Outcome:	The proposed method achieves cross-modal and cross-lingual alignment through continual pre-training.

Copied to clipboard

Zihan Wang, Hao Wang, Shi Feng, Xiaocui Yang, Daling Wang, Yiqun Zhang, Jinghao Lin, Xiaozhong Ji, Haihua Yang

Incremental Transformer with Deliberation Decoder for Document Grounded Conversations (P19-1)

Challenge:	Medical reasoning models are constrained by parametric knowledge and can induce hallucinations and spurious attributions.
Approach:	They propose a model that uses a multi-hop med-search QA synthesis method to apply the DR paradigm in medical contexts.
Outcome:	The proposed model outperforms larger medical reasoning models on medical benchmarks.

Copied to clipboard

Zekang Li, Cheng Niu, Fandong Meng, Yang Feng, Qian Li, Jie Zhou

EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation (2026.acl-long)

Challenge:	Existing dialogue systems do not exploit document knowledge effectively enough.
Approach:	They propose a Transformer-based architecture for document grounded conversations that incorporates document knowledge into a two-pass decoder to improve context coherence and knowledge correctness.
Outcome:	The proposed model outperforms baselines on context coherence and knowledge relevance on a real-world document grounded dataset.

Copied to clipboard

Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao

Why Do More Experts Fail? A Theoretical Analysis of Model Merging (2026.acl-long)

Challenge:	Existing methods for story evaluation lack reasoning capabilities for open-source models . evolvR framework provides high-fidelity evaluators for story generation tasks .
Approach:	They propose a framework that self-synthesizes chain-of-thought data via a multi-persona strategy . they propose evolvR to provide a reward model for story generation .
Outcome:	The proposed framework achieves state-of-the-art performance on three evaluation benchmarks . it also enhances the quality of generated stories, validating the superiority of the framework .

Copied to clipboard

Zijing Wang, Xingle Xu, YongKang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Daling Wang, Xiaocui Yang, Hinrich Schuetze

Challenge:	Existing methods for model merging struggle to maintain performance gains as the number of merged models increases.
Approach:	They propose a Reparameterized Heavy-Tailed method to extend the merged model’s coverage and enhance performance.
Outcome:	The proposed method extends the merged model’s coverage and enhances performance on 19 benchmarks, including knowledge-intensive and general-purpose tasks.

VPL: Visual Proxy Learning Framework for Zero-Shot Medical Image Diagnosis (2024.findings-emnlp)

Copied to clipboard

Jiaxiang Liu, Tianxiang Hu, Huimin Xiong, Jiawei Du, Yang Feng, Jian Wu, Joey Zhou, Zuozhu Liu

Past Meets Present: Creating Historical Analogy with Large Language Models (2025.acl-long)

Challenge:	Insufficient medical text precision and the modal disparity between text and vision spaces pose challenges for vision-language models like CLIP.
Approach:	They propose a visual proxy learning framework that combines a text refinement module and a stable Sinkhorn algorithm to enhance the diagnostic performance.
Outcome:	The proposed model outperforms the state-of-the-art CLIP inference by 1.69% to 15.31% on five datasets covering various diseases.

Copied to clipboard

Nianqi Li, Siyu Yuan, Jiangjie Chen, Jiaqing Liang, Feng Wei, Zujie Liang, Deqing Yang, Yanghua Xiao

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Historical analogies are important abilities that help people make decisions and understand the world.
Approach:	They propose a historical analogy acquisition task that uses large language models to acquire historical analogies.
Outcome:	The proposed method mitigates hallucinations and stereotypes when LLMs generate historical analogies.

Copied to clipboard

Yihan Jiao, Zhehao Tan, Dan Yang, Duolin Sun, Jie Feng, Yue Shen, Jian Wang, Peng Wei

HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models (2025.acl-long)

Challenge:	In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections.
Approach:	They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge.
Outcome:	Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

Copied to clipboard

Songtao Jiang, Yan Zhang, Yeying Jin, Zhihang Tang, Yangyang Wu, Yang Feng, Jian Wu, Zuozhu Liu

Think Better, Not Longer: Token-Level Marginal Utility for Efficient Reasoning in Large Reasoning Models (2026.acl-long)

Challenge:	Existing methods for medical vision-language models overlook modality misalignment . HSCR generates high-quality preference data with higher sampling probability .
Approach:	They propose a hierarchical self-contrastive reward approach that addresses two challenges in alignment . they leverage the inherent capability of Med-VLMs to generate dispreferred responses .
Outcome:	The proposed approach improves accuracy and trustworthiness of medical vision-label models with 2,000 training entries.

Copied to clipboard

Jiawei Li, Yang Gao, Huashan Sun, Chong Feng

ToolCPT: Improving Tool Utilization in LLM Agents via Continuous Pre-training (2026.findings-acl)

Challenge:	Large reasoning models (LRMs) generate explicit Chain-of-Thought rationales, but often suffer from "overthinking".
Approach:	They propose a unified training framework to synthesize concise reasoning chains by identifying tokens that reduce the model’s likelihood of the correct answer.
Outcome:	Experiments on deepSeek-R1-Distill-Qwen backbones show that MUTO yields better efficiency-accuracy Pareto frontier.

Copied to clipboard

Yifan Yang, Jinghui Lu, null Evadeng, Ao Yang, Peijie Yu, TingHao YU, Feng Zhang

Gaussian Multi-head Attention for Simultaneous Machine Translation (2022.findings-acl)

Challenge:	Current approaches to enhancing tool use for LLM-based agents focus on post-training fine-tuning or test-time context extension.
Approach:	They propose to enhance tool knowledge for LLM-based agents during continuous pre-training . they curate 5.1 million code artifacts from large-scale, high-quality code repositories .
Outcome:	The proposed model outperforms existing methods on out-of-distribution tools on multiple benchmarks.

Copied to clipboard

Learning Optimal Policy for Simultaneous Machine Translation via Binary Search (2023.acl-long)

Challenge:	Existing methods for siMT do not explicitly model the alignment to perform the control.
Approach:	They propose to model alignment and translation in a unified manner by Gaussian Multi-head Attention (GMA) they propose to integrate alignment-related priors into the translation model to determine final attention.
Outcome:	The proposed method outperforms strong baselines on trade-off between translation and latency.

Copied to clipboard

Examining False Positives under Inference Scaling for Mathematical Reasoning (2025.emnlp-main)

Challenge:	Simultaneous machine translation model needs a precise translation policy to achieve good latency-quality trade-offs.
Approach:	They propose a method for building the optimal translation policy online via binary search by employing explicit supervision.
Outcome:	Experiments on four translation tasks show that the proposed method exceeds strong baselines across all latency scenarios.

Copied to clipboard

Yu Wang, Nan Yang, Liang Wang, Furu Wei, Fuli Feng

GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing (2026.acl-long)

Challenge:	Recent advances in language models have led to significant improvements in mathematical reasoning across benchmarks.
Approach:	They analyze the prevalence of false positives in language models by using heuristic evaluation methods . they find that false positive models produce correct final answers but with flawed deduction paths .
Outcome:	The proposed model performance improvements are based on the proposed model and its evaluation metrics.

Copied to clipboard

Ming Wang, Shuang Wu, Bixuan Wang, Lu Lin, Yuxin Chen, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang, Yufan Sun

Challenge:	Large language models (LLMs) inherit contamination from training corpora, directional bias under social-desirability framing, and limited responsiveness to context beyond the item text.
Approach:	They propose a paradigm that reformulates TAT, Rorschach, and SCT with newly generated stimuli and organises assessment as a three-stage pipeline.
Outcome:	The proposed paradigm reformulates TAT, Rorschach, and SCT with newly generated stimuli and organises assessment as a three-stage pipeline.

Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment (2025.findings-acl)

Copied to clipboard

Xiaotian Zhang, Ruizhe Chen, Yang Feng, Zuozhu Liu

MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation (2023.acl-long)

Challenge:	Existing methods for aligning language models with human preferences rely on reward signals and additional annotated data, limiting their scalability and adaptability to diverse human values.
Approach:	They propose a discriminative paradigm that leverages the intrinsic preference judgment capabilities of the model to align language models with human preferences.
Outcome:	The proposed model is scalable and efficient, paving the way for more adaptive personalized alignment.

Copied to clipboard

Jiazhan Feng, Qingfeng Sun, Can Xu, Pu Zhao, Yaming Yang, Chongyang Tao, Dongyan Zhao, Qingwei Lin

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Challenge:	MMDialog is a dataset of 1.08 million real-world dialogues with 1.53 million unique images across 4,184 topics.
Approach:	They propose to use a curated set of 1.08 million dialogues with 1.53 million unique images to generalize the open domain.
Outcome:	The proposed system can predict responses to multi-modal content with state-of-the-art techniques and measure their performance.

Copied to clipboard

Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang

Modeling Dual Read/Write Paths for Simultaneous Machine Translation (2022.acl-long)

Challenge:	Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach:	They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome:	The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.

Copied to clipboard

Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce (P18-2)

Challenge:	Simultaneous machine translation (SiMT) outputs translation while reading source sentence . existing methods do not direct the read/write path, resulting in poor performance .
Approach:	They propose a method which introduces duality constraints to direct the read/write path . they propose to map the read path in two SiMT models to satisfy duality constraint .
Outcome:	Experiments on En-Vi and De-En tasks show that the proposed method outperforms baselines under all latency.

Copied to clipboard

Minghui Qiu, Liu Yang, Feng Ji, Wei Zhou, Jun Huang, Haiqing Chen, Bruce Croft, Wei Lin

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention (2026.acl-long)

Challenge:	Recent researches focus on deep learning and reinforcement learning for multi-turn information seeking conversation systems.
Approach:	They propose an efficient and effective multi-turn conversation model based on convolutional neural networks and extend it to adapt the knowledge learned from a resource-rich domain to enhance the performance.
Outcome:	The proposed model performs better than the existing model on an industrial chatbot called AliMe Assist.

Copied to clipboard

Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen

TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization (2024.naacl-long)

Challenge:	Recent advances in large language models (LLMs) have focused on test-time scaling to improve reasoning quality but at the cost of efficiency.
Approach:	They propose a training-free framework that enhances reasoning accuracy and stability with minimal overhead.
Outcome:	The proposed framework yields consistent gains across general, coding, and STEM tasks while remaining highly efficient.

Copied to clipboard

Liyan Tang, Igor Shalyminov, Amy Wong, Jon Burnsky, Jake Vincent, Yu’an Yang, Siffi Singh, Song Feng, Hwanjun Song, Hang Su, Lijia Sun, Yi Zhang, Saab Mansour, Kathleen McKeown

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

Challenge:	Existing LLMs hallucinate significant amounts of factual errors in the dialogue domain, regardless of the model’s size.
Approach:	They propose to evaluate topic-focused dialogue summarization by using large language models (LLMs) they use human annotations to evaluate factual consistency and explain factually inconsistent sentences.
Outcome:	The proposed evaluation benchmark on topic-focused dialogue summarization shows that existing LLMs hallucinate significant amounts of factual errors regardless of the model’s size.

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

UniCOQE: Unified Comparative Opinion Quintuple Extraction As A Set (2023.findings-acl)

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

Zinong Yang, Feng Xu, Jianfei Yu, Rui Xia

TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM (2025.coling-main)

Challenge:	Existing methods decompose the COQE task into multiple subtasks and solve them in a pipeline manner, but ignore the intrinsic connection between subtask and the error propagation among stages.
Approach:	They propose a unified generative model that solves COQE in one shot by concatenating all the comparative tuples into a target output sequence.
Outcome:	The proposed model significantly outperforms the SOTA method on multiple benchmarks and ablation experiments.

Copied to clipboard

Huiying Cao, Yiqun Zhang, Shi Feng, Xiaocui Yang, Daling Wang, Yifei Zhang

Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator (2023.findings-acl)

Challenge:	Empathetic conversation is a crucial characteristic in daily conversations between individuals.
Approach:	They propose an Emotional Knowledge Tool Calling framework which encapsulates commonsense knowledge bases as empathetic tools, enabling LLMs to integrate external knowledge flexibly.
Outcome:	The proposed framework can generate empathetic responses effectively on the TOOL-ED dataset.

Copied to clipboard

Ziwei He, Meng Yang, Minwei Feng, Jingcheng Yin, Xinbing Wang, Jingwen Leng, Zhouhan Lin

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)

Challenge:	Existing transformer models are computationally demanding and prohibitively costly for long sequences due to the quadratic complexity of its selfattention module.
Approach:	They propose a transformer-based model that inherits weights from large pretrained models by removing redundancies in hidden sequences using the ready-made Fast Fourier Transform operator.
Outcome:	The proposed model outperforms the standard BART model on the long-range modeling benchmark LRA with significant improvements in speed and space.

Copied to clipboard

Zekai Ye, Qiming Li, Xiaocheng Feng, Libo Qin, Yichong Huang, Baohang Li, Kui Jiang, Yang Xiang, Zhirui Zhang, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin

D2PCM:A Multi-Turn Dialogue Dataset with Personalized Contextual Memory (2026.findings-acl)

Challenge:	Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination.
Approach:	They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns.
Outcome:	The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages.

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, Chunyang Gao, Jingyu Yao, Junlan Feng

Type Enhanced BERT for Correcting NER Errors (2023.findings-acl)

Challenge:	Conventional interactive algorithms have predominantly treated memory as a contextual element, neglecting the nuanced cognitive processes involved in individualized memory encoding and retrieval.
Approach:	They propose a multi-turn dialogue dataset with Personalized Contextual Memory to facilitate advanced research on personalized memory processing.
Outcome:	The proposed datasets provide a comprehensive benchmark to facilitate advanced research on personalized memory processing.

Copied to clipboard

Kuai Li, Chen Chen, Tao Yang, Tianming Du, Peijie Yu, Dong Du, Feng Zhang

Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation (2022.findings-emnlp)

Challenge:	Named entity recognition (NER) is the task of identifying spans that belong to particular categories, such as person, location, organization, etc.
Approach:	They propose a method that integrates named entity’s type information into BERT by an adapter layer and integrates it into a gazetteer.
Outcome:	The proposed method outperforms baselines in multiple corpus.

Copied to clipboard

Shaolei Zhang, Shoutao Guo, Yang Feng

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

Challenge:	Existing methods to balance source and target information at the token level are limited by the number of received source tokens.
Approach:	They propose a Wait-info Policy to balance source and target at the information level . they quantify the amount of info contained in each token and compare it with previous outputs .
Outcome:	The proposed method outperforms baselines under and achieves better balance . it is based on comparisons between the total info of previous target outputs and received source inputs .

Copied to clipboard

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

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

MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis (2026.findings-acl)

Copied to clipboard

Xingle Xu, YongKang Liu, Dexian Cai, Shi Feng, Xiaocui Yang, Daling Wang, Yifei Zhang

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

Challenge:	Existing approaches to multimodal sentiment analysis treat entire modality as an independent unit for feature enhancement or denoising, which often suppresses redundant noise at the cost of weakening critical information.
Approach:	They propose a ModaLity-aware noise dynAmic editiNg framework that performs modality-awful block partitioning by dividing features of each modality into multiple blocks.
Outcome:	Experiments on five models and four datasets show that MoLAN+ achieves the state-of-the-art performance.

Copied to clipboard

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

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

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

Copied to clipboard

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

WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models (2025.acl-long)

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

Copied to clipboard

Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

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

Challenge:	Recent code large language models have demonstrated impressive performance on code-related tasks.
Approach:	They propose a paradigm that learns from expert battles to address these limitations . they create an arena where leading LLMs challenge each other with evaluations .
Outcome:	The proposed model improves on existing models by leveraging expert battles . it achieves state-of-the-art performance even without relying on proprietary models .

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

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

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

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

Knowledge Diffusion for Neural Dialogue Generation (P18-1)

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

Copied to clipboard

Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, Dawei Yin

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Challenge:	End-to-end neural dialogue generation does not employ knowledge to guide the generation.
Approach:	They propose a neural knowledge diffusion model to introduce knowledge into dialogue generation.
Outcome:	The proposed model outperforms baseline models on a real-world dataset.

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Auto Search Indexer for End-to-End Document Retrieval (2023.findings-emnlp)

Copied to clipboard

Tianchi Yang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang

CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation (2020.acl-main)

Challenge:	Generative retrieval heavily relies on the “preprocessed” document identifiers, thus limiting its retrieval performance and ability to retrieve new documents.
Approach:	They propose a fully end-to-end retrieval paradigm that can learn the best docids for existing and new documents automatically via a semantic indexing module.
Outcome:	The proposed model outperforms baselines on public and industrial datasets and can handle new documents.

Copied to clipboard

Lei Shen, Yang Feng

KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships (2021.findings-emnlp)

Challenge:	Existing methods for generating emotion-controllable response are inadequate due to content consistency and lack of coherence.
Approach:	They propose a framework that extends the emotion-controllable response generation to a dual task to generate emotional responses and emotional queries alternatively.
Outcome:	The proposed framework outperforms baseline models in coherence, diversity, and relation to emotion factors.

Copied to clipboard

Lei He, Suncong Zheng, Tao Yang, Feng Zhang

SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflage (2025.findings-acl)

Challenge:	Existing knowledge-enhanced pretrained language models focus on entity information and ignore fine-grained relationships between entities.
Approach:	They propose to incorporate KG into the language learning process to obtain a KG-enhanced pretrained Language Model.
Outcome:	The proposed model improves on several knowledge-driven tasks, such as entity typing and relation classification, compared with the state-of-the-art knowledge-enhanced PLMs.

Copied to clipboard

Jihui Yan, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang, Yinzhi Zhao

MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have made safety issues of LLMs more prominent and critical.
Approach:	They propose a framework which attacks LLMs through semantic camouflage and replaces unsafe content with semantic features to conceal malicious intent .
Outcome:	The proposed framework outperforms existing models in over 80% of cases and is highly effective against various defenses.

Copied to clipboard

Zihan Wang, Xiaocui Yang, YongKang Liu, Shi Feng, Daling Wang, Yifei Zhang

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

Challenge:	Existing research focuses solely on text, leaving a gap with practical applications.
Approach:	They propose to synthesize a multimodal conversational recommendation dataset using multimodal large language models to automatically synthesized data from 7,000 conversations in the Clothing domain.
Outcome:	The proposed dataset contains 83,148 utterances from 7,000 conversations centered around the Clothing domain.

Copied to clipboard

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

QDMR-based Planning-and-Solving Prompting for Complex Reasoning Tasks (2024.lrec-main)

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

Copied to clipboard

Jinfeng Huang, Qiaoqiao She, Wenbin Jiang, Hua Wu, Yang Hao, Tong Xu, Feng Wu

Structure-Discourse Hierarchical Graph for Conditional Question Answering on Long Documents (2023.findings-acl)

Challenge:	Existing Plan-and-Solve prompting methods are difficult to implement for complex questions.
Approach:	They propose a plan-and-solve prompting method based on Question Decomposition Meaning Representation (QDMR) it allows LLM to generate a QDMR graph to represent problem-solving logic .
Outcome:	The proposed method can represent and execute the problem-solving logic of complex questions more accurately than existing methods.

Copied to clipboard

Haowei Du, Yansong Feng, Chen Li, Yang Li, Yunshi Lan, Dongyan Zhao

Structured Data in NLP

Challenge:	Existing approaches to conditional question answering on long documents ignore document structure and discourse relations between sentences in document sections.
Approach:	They construct a Structure-Discourse Hierarchical Graph and conduct bottom-up information propagation to address this issue.
Outcome:	The proposed approach outperforms the existing methods on the conditional question answering on long documents by 3.0 EM score and 2.4 F1 score on answer measuring, and 2.2 EM and 1.9 F1 scores on jointly answer and condition measuring.

Fundamental Capabilities of Large Language Models and their Applications in Domain Scenarios: A Survey (2024.acl-long)

Copied to clipboard

Jiawei Li, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, Yixiao Wu, 林一冠林一冠, Bin Xu, Ren Bowen, Chong Feng, Yang Gao, Heyan Huang

FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability (2024.acl-long)

Challenge:	Existing benchmark-based evaluations cannot accurately reflect the performance of real-world applications.
Approach:	They propose a reliable strategy for domains to choose more robust LLMs for real-world applications.
Outcome:	The proposed strategy addresses the challenges faced by domains to choose more robust LLMs for real-world applications.

Copied to clipboard

Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, Ran Xu, Wenpeng Yin, Caiming Xiong

Challenge:	Existing benchmarks fail to assess large language models’ format-following proficiency adequately.
Approach:	They propose a benchmark to evaluate large language models' ability to follow complex, domain-specific formats.
Outcome:	The proposed framework evaluates large language models' ability to follow complex, domain-specific formats across open-source and closed-source models.

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Models (2026.acl-long)

Copied to clipboard

Qiguang Chen, Chengyu Luan, Jiajun Wu, Qiming Yu, Yi Yang, Yizhuo Li, Jingqi Tong, Xiachong Feng, Libo Qin, Wanxiang Che

Pixel-Level Reasoning Segmentation via Multi-turn Conversations (2025.acl-long)

Challenge:	Existing multimodal reasoning benchmarks for large vision-language models emphasize single-image analysis and fail to exploit contextual information across multiple images.
Approach:	They propose a benchmark to evaluate Olympiad-level reasoning when evidence is distributed over multiple images.
Outcome:	The proposed model outperforms existing models on bi-image Olympiads and Gemini-3-Pro on multimodal Olympiad-level reasoning tasks.

Copied to clipboard

Dexian Cai, Xiaocui Yang, YongKang Liu, Daling Wang, Shi Feng, Yifei Zhang, Soujanya Poria

StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning (2024.acl-long)

Challenge:	Existing visual perception systems focus on region-level segmentation in single-turn dialogues . existing systems cannot reason at the pixel level and comprehend dynamic user intent .
Approach:	They propose a task that tracks evolving user intent via multi-turn interactions for fine-grained segmentation.
Outcome:	The proposed method outperforms existing baselines in segmentation and reasoning metrics.

Copied to clipboard

Shaolei Zhang, Qingkai Fang, Shoutao Guo, Zhengrui Ma, Min Zhang, Yang Feng

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations (2024.findings-emnlp)

Challenge:	Existing simultaneous translation methods focus on text-to-text and speech-totext translation.
Approach:	They propose a Simul-S2ST model that jointly learns translation and simultaneous policy in a unified framework of multi-task learning.
Outcome:	The proposed model can perform offline and simultaneous speech recognition, speech translation and speech synthesis via an "All-in-One" seamless model.

Copied to clipboard

Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, Jing Tang

Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders (2025.acl-long)

Challenge:	Existing LLMs are delicate and elusive in prompt words and styles.
Approach:	They propose an LLM-acquainted prompting technique that includes proficient "native-speaking" they propose to use in-context learning to prompt LLMs to perform high-performance reasoning .
Outcome:	The proposed technique achieves step-wise prompts in zero-shot scenarios while maintaining the prompt quality.

Copied to clipboard

Boyi Deng, Yu Wan, Baosong Yang, Yidan Zhang, Fuli Feng

Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Challenge:	Large Language Models (LLMs) exhibit impressive abilities in various domains such as text generation, instruction following, and reasoning.
Approach:	They propose a method to decompose the activations of Large Language Models into a sparse linear combination of SAE features.
Outcome:	The proposed method shows that some features are strongly related to specific languages, while others are unaffected by ablating them.

Copied to clipboard

Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference (2026.acl-long)

Challenge:	Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Approach:	They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models.
Outcome:	The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio.

Copied to clipboard

Zhengyi Li, Yakai Wang, Jingwen Leng, Kang Yang, Yu Yu, Jiaping Gui, Yu Feng, Ning Liu, Minyi Guo

DR-HM: Distill-then-Reinforce Training with Cognition-Aware Data Synthesis for Harmful Meme Detection (2026.findings-acl)

Challenge:	Existing work reveals only randomly permuted activations to the client, allowing adversaries to extract model weights.
Approach:	They propose an attack that aligns differently shuffled activations to a common permutation and exploits them to extract model weights.
Outcome:	The proposed attack can align shuffled activations to a common permutation and exploit them to extract model weights with a query cost of approximately $1.

Copied to clipboard

Zihan Cheng, Jianxiang Ma, Xiaocui Yang, Peidong Wang, Wen Zhang, Shi Feng, Daling Wang, Yifei Zhang, Mingfu Zhang

Generating Diverse Translation from Model Distribution with Dropout (2020.emnlp-main)

Challenge:	Current methods for harmful meme detection lack the knowledge required to identify such hate . current methods lack the ability to identify cultural stereotypes and visual metaphors .
Approach:	They propose a framework that decomposes meme analysis into a human-inspired reasoning process . they propose DR-HM to transfer knowledge from closed-source models while mitigating biases .
Outcome:	The proposed framework outperforms existing methods on three benchmark datasets.

Copied to clipboard

Xuanfu Wu, Yang Feng, Chenze Shao

Trustworthy and Explainable Causal Representation Learning in Transformers (2026.findings-acl)

Challenge:	Existing neural machine translation models lack diversity in their generation.
Approach:	They propose to generate diverse translations by deriving Bayesian models and sampling models from them for inference.
Outcome:	The proposed method makes a better trade-off between diversity and accuracy.

Copied to clipboard

Yang Liu, Yinghao Zhang, Lin Liu, Jiuyong Li, Debo Cheng, Zaiwen Feng

Harder Task Needs More Experts: Dynamic Routing in MoE Models (2024.acl-long)

Challenge:	Existing approaches to interpretable representation learning rely on masks that weight the significance of input features, but the origin of these masks is uncertain.
Approach:	They propose a causal framework that directly learns identifiable representations from attention weights rather than relying on importance masks.
Outcome:	The proposed framework learns identifiable and explainable representations from attention weights, rather than masks, and guarantees faithfulness on real-world datasets.

Copied to clipboard

Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng

Triviality Corrected Endogenous Reward (2026.acl-long)

Challenge:	Unlike existing MoE approaches that rely on fixed TopK Routing, our dynamic expert selection framework dynamically allocates experts based on the confidence level in expert selection for each input.
Approach:	They propose a dynamic expert selection framework that dynamically allocates experts based on the confidence level in expert selection for each input.
Outcome:	The proposed method achieves an average improvement of 0.7% with less than 90% activated parameters and outperforms dense models in QA and machine translation tasks.

Copied to clipboard

Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao

Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas (2025.acl-long)

Challenge:	Recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards focuses on open-ended text generation, requiring either annotated data or powerful closed-source models.
Approach:	They propose a method that rewards the relative information gain between a specialist and a generalist reference policy, modulated by a probability-dependent correction mechanism.
Outcome:	The proposed model improves on multiple writing benchmarks and model architectures without external supervision and validates generality across different generation tasks.

Copied to clipboard

Nishant Balepur, Vishakh Padmakumar, Fumeng Yang, Shi Feng, Rachel Rudinger, Jordan Lee Boyd-Graber

Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)

Challenge:	a recent study shows that LLMs can't tailor outputs to users with uncommon preferences . despite the success of persona inference, we may need debiasing and abstention.
Approach:	They propose to use preference data to infer needs and interests of users who prefer either output . they argue that training on preference data augmented with PI boosts personalization .
Outcome:	The proposed method can be used to improve personalization with less privacy concerns.

Copied to clipboard

Bohan Li, Jiannan Guan, Longxu Dou, Yunlong Feng, Dingzirui Wang, Yang Xu, Enbo Wang, Qiguang Chen, Bichen Wang, Xiao Xu, Yimeng Zhang, Libo Qin, Yanyan Zhao, Qingfu Zhu, Wanxiang Che

Nature-Inspired Population-Based Evolution of Large Language Models (2026.acl-long)

Challenge:	Existing data on MBTI personality detection are based on self-reported labels and fail to capture the full range of population personality traits.
Approach:	They construct a manually annotated MBTI personality detection dataset with soft labels under the guidance of psychologists and use them to identify the task.
Outcome:	The MBTIBench is the first manually annotated MBti personality detection dataset with soft labels under the guidance of psychologists.

Copied to clipboard

Yiqun Zhang, Peng Ye, Xiaocui Yang, Shi Feng, Shufei Zhang, Lei Bai, Wanli Ouyang, Shuyue Hu

Low-resource Neural Machine Translation with Cross-modal Alignment (2022.emnlp-main)

Challenge:	a new framework for population-based evolution of large language models is emerging . a population-driven evolution of LLMs is a key component of evolution, authors say .
Approach:	They propose a framework that allows for population-based evolution of large language models . they start with a population of parent LLMs and allow this population to evolve .
Outcome:	The proposed framework outperforms existing methods on 12 datasets.

Copied to clipboard

Zhe Yang, Qingkai Fang, Yang Feng

MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction (2023.findings-acl)

Challenge:	Existing neural machine translation techniques rely on large monolingual corpus, which is costly for some low-resource languages.
Approach:	They propose a cross-modal contrastive learning method to learn a shared space for all languages by additional visual modality.
Outcome:	The proposed method can learn cross-modal and cross-lingual alignment with small amount of image-text pairs and achieves significant improvements over the text-only baseline.

Copied to clipboard

Li Yang, Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Yu Chen, Madian Khabsa, Sinong Wang, Zenglin Xu, Dongfang Liu

AgentOCR: Reimagining Agent History via Optical Self-Compression (2026.acl-long)

Challenge:	Existing methods for product attribute value extraction focus on extracting values for a set of known attributes with sufficient training data.
Approach:	They propose a prompt tuning approach to extract attributes from product information using mixed prompts.
Outcome:	The proposed approach improves on two product benchmarks and shows parameter-efficient training and avoids model overfitting.

Copied to clipboard

Lang Feng, Fuchao Yang, Feng Chen, Xin Cheng, Haiyang Xu, Zhenglin Wan, Ming Yan, Bo An

Visual Data in NLP

Challenge:	Recent advances in large language models (LLMs) have enabled agentic systems trained with reinforcement learning over multi-turn interaction, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token and memory costs.
Approach:	They propose a framework that represents the accumulated observation-action history as a compact rendered image.
Outcome:	The proposed framework preserves over 95% of text-based agent performance while significantly reducing token consumption (>50%), yielding consistent token and memory efficiency.

Palette of Language Models: A Solver for Controlled Text Generation (2025.naacl-long)

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, XiaotingWu XiaotingWu, Junlan Feng, Chao Deng

One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit (2025.acl-long)

Challenge:	Recent advances in large language models have revolutionized text generation with their remarkable capabilities.
Approach:	They propose to combine a single-attribute model with a discriminative model to achieve a combination strategy that incorporates positive correlation and attribute enhancement.
Outcome:	The proposed method is adapted for single-attribute control scenario and achieves surpassing results.

Copied to clipboard

Weitao Ma, Xiyuan Du, Xiaocheng Feng, Lei Huang, Yichong Huang, Huiyi Zhang, Xiaoliang Yang, Baohang Li, Xiachong Feng, Ting Liu, Bing Qin

Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization (2025.findings-acl)

Challenge:	Existing methods for modifying large language models focus on individual models, resulting in errors and hallucinations.
Approach:	They propose an ensemble-based approach that employs a plug-in model as the editing module and a dynamic weight mechanism to enhance its effectiveness.
Outcome:	The proposed approach outperforms existing methods while achieving superior editing efficiency.

Copied to clipboard

Yilun Qiu, Xiaoyan Zhao, Yang Zhang, Yimeng Bai, Wenjie Wang, Hong Cheng, Fuli Feng, Tat-Seng Chua

Challenge:	Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization.
Approach:	They propose a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization.
Outcome:	The proposed approach extracts inter-user differences to enhance LLM personalization.

TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning (2026.findings-acl)

Copied to clipboard

Jinyang Wu, Chonghua Liao, Mingkuan Feng, Shuai Zhang, Zhengqi Wen, Haoran Luo, Ling Yang, Huazhe Xu, Jianhua Tao

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Challenge:	Existing RL methods rely on unstructured self-sampling to fit scalar rewards, resulting in inefficient rollouts.
Approach:	They propose a structured template-guided RL framework that augments policy optimization with explicit template guidance.
Outcome:	Experiments show that TemplateRL outperforms GRPO and GRPI by 99% on AIME and 41% on AMC with superior stability on weak models and remarkable cross-domain generalization.

Copied to clipboard

Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song

Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances (2021.acl-long)

Challenge:	Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach:	They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome:	The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.

Copied to clipboard

Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie Zhou

G-Cap: A Game Character Caption Generator (2026.acl-long)

Challenge:	Recent intelligent open-domain chatbots have made substantial progress thanks to the rapid development of large-scale pre-training approaches.
Approach:	They propose a dynamic flow mechanism to model the context flow and a model to capture the information dynamics across dialogue utterances.
Outcome:	The proposed model outperforms the DialoGPT on the dialogue generation task.

Copied to clipboard

Yang Yang, Feng Hu, Haiming Zhang, XU Cheng, Gui Zheng, Liang Yao, Wenqi Ren

Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement (2024.findings-emnlp)

Challenge:	Existing studies on Large Vision-Language Models (LVLMs) primarily focus on real-world scenarios, leaving surreal, highly stylized, and semantically hybrid virtual-world situations significantly underexplored.
Approach:	They propose to use a manually annotated benchmark to evaluate LVLMs' ability to perceive and describe game character from the virtual-world.
Outcome:	The proposed task evaluates LVLMs’ ability to perceive and describe game character from the virtual-world.

Copied to clipboard

Yunlong Feng, Dechuan Teng, Yang Xu, Honglin Mu, Xiao Xu, Libo Qin, Qingfu Zhu, Wanxiang Che

Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding (2026.eacl-long)

Challenge:	Decompilation is the process of converting compiled code back into a high-level programming language for analysis when source code is unavailable.
Approach:	They propose two methods to improve decompilation performance without fine-tuning and fine-grained alignment enhancement to achieve further improvements.
Outcome:	The proposed methods achieved a Re-Executability performance improvement of approximately 3.90% on the Decompile-Eval benchmark, establishing a new state-of-the-art performance of 52.41%.

Copied to clipboard

Juncheng Wang, Zhe Hu, Chao Xu, Siyue Ren, Yuxiang Feng, Yang Liu, Baigui Sun, Shujun Wang

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

Challenge:	Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts.
Approach:	They propose a lightweight auxiliary model trained with a GAE-inspired objective to predict final instruction-following quality from partial generations.
Outcome:	The proposed model achieves 10 points improvement in CLAP score over baseline AR models while maintaining computational parity with best-of-N decoding.

Copied to clipboard

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

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

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation (2025.findings-emnlp)

Copied to clipboard

Chengbing Wang, Yang Zhang, Zhicheng Wang, Tianhao Shi, Keqin Bao, Fuli Feng, Tat-Seng Chua

SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

Challenge:	Light Latent-space Decoding (L2D) is an efficient and efficient latent- space decoding method.
Approach:	They propose to bypass language-space decoding by matching candidate items with LLM's internal thought representations in the latent space.
Outcome:	The proposed method is 10x faster than language-space decoding while maintaining or enhancing performance.

Copied to clipboard

Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang

Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation (2021.naacl-main)

Challenge:	Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach:	They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome:	The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.

Copied to clipboard

Shuhao Gu, Yang Feng, Wanying Xie

Program Enhanced Fact Verification with Verbalization and Graph Attention Network (2020.emnlp-main)

Challenge:	Existing methods for domain adaptation suffer from catastrophic forgetting, large domain divergence, and model explosion.
Approach:	They propose a method which prunes the model and keeps the important neurons or parameters responsible for both general-domain and in-domain translation.
Outcome:	The proposed method improves on different language pairs and domains compared with strong baselines.

Copied to clipboard

Xiaoyu Yang, Feng Nie, Yufei Feng, Quan Liu, Zhigang Chen, Xiaodan Zhu

Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization? (2024.emnlp-main)

Challenge:	Existing methods for fact verification based on structured data are challenging and require further study.
Approach:	They propose a program-enhanced verbalization and a graph attention network to integrate programs and execution into textual inference models.
Outcome:	The proposed framework achieves a new state-of-the-art accuracy on a benchmark dataset . it is compared with existing frameworks on symbolic and informal inference models .

Copied to clipboard

Jianfeng He, Runing Yang, Linlin Yu, Changbin Li, Ruoxi Jia, Feng Chen, Ming Jin, Chang-Tien Lu

TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration (2025.emnlp-main)

Challenge:	Text summarization is a key natural language generation task, but the high cost of inaccurate summaries raises concerns about the reliability of uncertainty estimation on text summarisation (UE-TS) evaluation methods.
Approach:	They propose a UE-TS benchmark that evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets.
Outcome:	The proposed benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with human-annotation analysis incorporated where applicable.

Copied to clipboard

Yanshu Li, Jianjiang Yang, Tian Yun, Pinyuan Feng, Jinfa Huang, Ruixiang Tang

KC-ISA: An Implicit Sentiment Analysis Model Combining Knowledge Enhancement and Context Features (2022.coling-1)

Challenge:	Multimodal in-context learning (ICL) is a key mechanism for harnessing the capabilities of large vision–language models.
Approach:	They propose a transformer-based model with task-aware attention that dynamically configures ICL sequences.
Outcome:	Experiments on five LVLMs and nine datasets show that TACO surpasses baselines across diverse ICL tasks.

Copied to clipboard

Minghao Xu, Daling Wang, Shi Feng, Zhenfei Yang, Yifei Zhang

Sentiment Analysis

Challenge:	Existing research results on explicit sentiment analysis are limited . implicit sentiment analysis is a process of analyzing text based on whether it contains explicit sentiment words.
Approach:	They propose a model that integrates external knowledge and contextual features . they use a knowledge graph to supplement implicit sentiment expression .
Outcome:	The proposed model can achieve better results on the SMP2019 implicit sentiment analysis dataset.

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

Copied to clipboard

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

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues (2022.emnlp-main)

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

Copied to clipboard

Jiao Ou, Jinchao Zhang, Yang Feng, Jie Zhou

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space (2024.acl-long)

Challenge:	Existing methods to augment dialogue datasets are labor-intensive and time-consuming . Currently, smoking is harmful for your health.
Approach:	They propose a data augmentation method to augment dialogue responses with different semantics by counterfactual inference.
Outcome:	The proposed method outperforms baselines on multiple downstream tasks.

Copied to clipboard

Shaolei Zhang, Tian Yu, Yang Feng

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

Challenge:	Large Language Models (LLMs) sometimes produce untruthful responses despite knowing the correct knowledge.
Approach:	They propose an inference-time intervention method to activate the truthfulness of Large Language Models (LLMs) by editing the features within LLM’s internal representations that govern the truthful.
Outcome:	The proposed method improves the truthfulness of 13 advanced LLMs by an average of 20% on TruthfulQA benchmark.

Copied to clipboard

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

Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts (2024.findings-acl)

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

Copied to clipboard

Tian Yu, Shaolei Zhang, Yang Feng

Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency (2021.findings-acl)

Challenge:	Large Language Models (LLMs) are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations.
Approach:	They propose a lightweight method to adaptively recognize and mask untruthful context from the inputs and a new evaluation metric to further study the LLMs’ ability to accept truthful information and resist untrusted information.
Outcome:	The proposed method can detect and mask untruthful context from the inputs and significantly improve the quality of LLMs’ responses when presented with misleading information.

Copied to clipboard

Zekang Li, Jinchao Zhang, Zhengcong Fei, Yang Feng, Jie Zhou

Improving Language Model Reasoning with Self-motivated Learning (2024.lrec-main)

Challenge:	Existing methods to evaluate consistency capacity of open-domain chatbots are costly and low-efficient.
Approach:	They propose an efficient framework for evaluating consistency of open-domain chatbots . they use human judges to interact with chatbot, which is costly and low-efficient .
Outcome:	The proposed framework can assess the consistency capacity of chatbots and achieve a high ranking correlation with the human evaluation.

Copied to clipboard

Yunlong Feng, Yang Xu, Libo Qin, Yasheng Wang, Wanxiang Che

Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving (2025.findings-acl)

Challenge:	Large-scale high-quality training data is important for improving the performance of models.
Approach:	They propose a framework that motivates the model to automatically generate rationales on existing datasets and improves the performance of reasoning through reinforcement learning.
Outcome:	The proposed model outperforms InstructGPT on multiple reasoning datasets and outperformed InstructGPT on other datasets.

Copied to clipboard

Kaiyue Feng, Yilun Zhao, Yixin Liu, Tianyu Yang, Chen Zhao, John Sous, Arman Cohan

Challenge:	a benchmark for university-level physics problem solving contains 1,297 expert-annotated problems . a proprietary model, o3-mini, achieves only 59.9% accuracy, highlighting fundamental weaknesses in scientific reasoning, conceptual understanding, and mathematical precision.
Approach:	They introduce Physics, a benchmark for university-level physics problem solving.
Outcome:	The proposed model achieves only 59.9% accuracy on the most advanced model, o3-mini . the proposed model is a powerful tool for evaluating models on advanced problems .

SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning (2026.findings-acl)

Copied to clipboard

Fanqi Kong, Weiqin Zu, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng

Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models (2026.acl-long)

Challenge:	Existing benchmarks for Multimodal Large Language Models (MLLMs) have been lacking due to the rich nature of social interaction.
Approach:	They propose a video benchmark to evaluate MLLMs' capabilities across social scene understanding, social state reasoning, and social dynamics prediction.
Outcome:	The proposed benchmarks evaluate MLLMs' capabilities across social scene understanding, social state reasoning, and social dynamics prediction tasks.

Copied to clipboard

Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian, Jianhua Tao

Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features (2024.findings-acl)

Challenge:	In-context learning (ICL) struggles with complex reasoning due to superficial, example-level implicit imitation.
Approach:	They propose an automated method that shifts from surface-level examples to more guidance-oriented thought patterns.
Outcome:	The proposed method achieves 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5% accuracy.

Copied to clipboard

Mengyu Bu, Shuhao Gu, Yang Feng

JX4MEI: Multimodal Semantically-Enhanced LLM for Joint Multimodal Emotion-Intent Explanation and Classification (2026.findings-acl)

Challenge:	Existing models do not differentiate between semantic and linguistic features, resulting in the entanglement of knowledge and linguistics within the model.
Approach:	They propose to exploit both semantic and linguistic features to enhance multilingual translation by disentangling encoder representations and integrating low-level linguistic encoders.
Outcome:	The proposed model improves zero-shot translation while maintaining performance in supervised translation on multilingual datasets.

Copied to clipboard

YiJie Huang, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Ning Yuan, Zhuoyue Jia, Wen Zhang

Generating Classical Chinese Poems from Vernacular Chinese (D19-1)

Challenge:	Existing multimodal emotion and intent recognition tasks focus on classification, not rationale and intrinsic connections between these states.
Approach:	They propose a task that requires models to jointly predict emotion and intent while generating natural language explanations for why they co-occur.
Outcome:	The proposed model outperforms baseline models in prediction and explanation generation.

Copied to clipboard

Zhichao Yang, Pengshan Cai, Yansong Feng, Fei Li, Weijiang Feng, Elena Suet-Ying Chiu, Hong Yu

Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers (2026.acl-long)

Challenge:	Existing models for classical Chinese poetry generation only allow users to use keywords to interfere with the meaning of generated poems.
Approach:	They propose a model to generate classical Chinese poems from vernacular . their model uses unsupervised machine translation to generate Chinese poems . human evaluation shows it can generate high-quality poems comparable to amateur poems - authors .
Outcome:	The proposed model improves the perplexity and BLEU of the proposed model compared with typical models and human evaluation shows it generates high-quality poems comparable to amateur poems.

Copied to clipboard

Xin Chen, Feng Jiang, Yiqian Zhang, Hardy Chen, Shuo Yan, Wenya Xie, Min Yang, Shujian Huang

RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning (2026.findings-acl)

Challenge:	Existing reasoning-oriented LLMs lack a blind self-thinking paradigm . current models fail to recognize when their reasoning is underinformed or based on ambiguous user instructions .
Approach:	They propose a new reasoning paradigm that transforms LLMs into proactive inquirers that interleave reasoning with clarification.
Outcome:	The proposed model outperforms baseline models on mathematical reasoning, code generation, and document editing.

Copied to clipboard

Yitao Xiao, Shaoyong Guo, Guoming Yang, Qingnan Wang, Yinlin Ren, Xuesong Qiu, Qi Feng

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)

Challenge:	Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks.
Approach:	They propose a new framework for routing using large language models . they formalize routing as node selection through edge-weight prediction .
Outcome:	The proposed framework outperforms the best single LLM and baselines on five datasets . it achieves 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%.

Copied to clipboard

Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward (2025.naacl-long)

Challenge:	Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Approach:	They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Outcome:	The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy.

Copied to clipboard

Ruohong Zhang, Liangke Gui, Zhiqing Sun, Yihao Feng, Keyang Xu, Yuanhan Zhang, Di Fu, Chunyuan Li, Alexander G Hauptmann, Yonatan Bisk, Yiming Yang

Explainable Text Classification with LLMs: Enhancing Performance through Dialectical Prompting and Explanation-Guided Training (2025.findings-emnlp)

Challenge:	Existing studies have demonstrated that direct preference optimization (DPO) can be effective in generalizing large language models, but its effectiveness in video domain remains limited.
Approach:	They propose a framework that utilizes detailed video captions as a proxy of video content to enable language models to incorporate this information as supporting evidence for scoring video Question Answering (QA) predictions.
Outcome:	The proposed framework shows that it can be used to align language models with video content and improves performance on open-ended video QA tasks.

Copied to clipboard

Huaming Du, Lei Yuan, Cancan Feng, Guisong Liu, Gang Kou, Carl Yang

Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation (2021.acl-long)

Challenge:	Existing explanation methods that generate keywords may be less effective due to missing critical contextual information.
Approach:	They propose a new method to generate explanations for possible labels using LLMs and a dialectical prompt.
Outcome:	The proposed method significantly improves accuracy and explanation quality over state-of-the-art methods on multiple datasets from diverse domains.

Copied to clipboard

Yang Feng, Shuhao Gu, Dengji Guo, Zhengxin Yang, Chenze Shao

BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)

Challenge:	Neural machine translation models are usually based on attention-based encoder-decoder frameworks.
Approach:	They introduce a seer decoder into the encoder-decoder framework during training . they force the conventional decoded decodes to simulate the behavior of the seer .
Outcome:	The proposed method outperforms baselines on Chinese, English and German translation tasks.

Copied to clipboard

Ran Xin, Chenguang Xi, Jie Yang, Feng Chen, Hang Wu, Xia Xiao, Yifan Sun, Shen Zheng, Ming Ding

Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks (2021.acl-long)

Challenge:	Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored.
Approach:	They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases.
Outcome:	The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods.

Copied to clipboard

Xiaocui Yang, Shi Feng, Yifei Zhang, Daling Wang

Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translation (2022.findings-emnlp)

Challenge:	Existing studies only considered the representation of a single image-text post . Fig. 1 shows that multimodal sentiment expressions have global characteristics .
Approach:	They propose a multi-channel Graph Neural Networks with Sentiment-awareness approach for image-text sentiment detection.
Outcome:	The proposed approach is effective for image-text sentiment detection on three publicly available datasets.

Copied to clipboard

Chenze Shao, Zhengrui Ma, Yang Feng

Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation (2024.findings-acl)

Challenge:	Non-autoregressive models lack the ability to capture sequential dependency . Existing approaches to model sequential dependency have to apply a sequential decision process at inference time .
Approach:	They propose a Viterbi decoding framework to capture sequential dependency . they propose to find the optimal translation path under any length constraint .
Outcome:	The proposed framework improves the performance of DA-Transformer while maintaining similar speedup.

Copied to clipboard

Langlin Huang, Yang Feng

FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation (2025.acl-demo)

Challenge:	Subword tokenization is a common method for vocabulary building in NMT systems . but, it has its disadvantages, such as a vocabulary cannot be modified once it is learned .
Approach:	They propose a method that learns contextualized information of varying scales . they propose byte-based tokenization to solve these problems with few embedding parameters .
Outcome:	Experiments show that the proposed method outperforms subword-based methods in multilingual and out-of-domain scenarios.

Copied to clipboard

Zhang Zhuocheng, Yang Feng, Min Zhang

A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking (2020.acl-main)

Challenge:	Existing frameworks for retrieval-augmented generation (RAG) lack new techniques, difficulties in algorithm reproduction and sharing, and high system overhead.
Approach:	They propose a retrieval-augmented generation framework specifically designed for research and prototyping that supports text-based, multimodal, and network-based RAG.
Outcome:	The proposed framework supports text-based, multimodal, and network-based RAG, providing comprehensive lifecycle support alongside efficient asynchronous processing and persistent caching capabilities.

Copied to clipboard

Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu, Jie Zhou

FrontCoder: Scaling Visual Fidelity in Front-End Code Generation (2026.findings-acl)

Challenge:	Existing methods for dialogue state tracking ignore the slot imbalance problem and treat all slots indiscriminately, which limits the learning of hard slots.
Approach:	They propose to employ a contextual hierarchical attention network to enhance the DST by learning contextual representations.
Outcome:	The proposed approach achieves 52.68% and 58.55% joint accuracy on multiWOZ 2.0 and MultiWOZ 2.1 datasets and significantly improves performance (+1.24% and +5.98%)

Copied to clipboard

Jun Feng, Jian Yang, Wei Zhang, Jing Wang, Keyi Chen, Xiaokun Yang, Weicheng Gu, Yihang Lou, Yan Bai, Xianglong Liu

Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding (2024.findings-emnlp)

Challenge:	Existing work on front-end code generation fails to provide visual fidelity and rendering quality for front- end developers.
Approach:	They propose a three-stage pipeline to enhance front-end code generation capabilities in LLMs . they use synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning .
Outcome:	The proposed model achieves competitive performance with frontier models while maintaining generation efficiency.

Copied to clipboard

Liang Zhao, Xiachong Feng, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin, Ting Liu

A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation (2024.acl-long)

Challenge:	Existing methods to enhance length extrapolation of large language models have been developed, but a systematic survey is lacking.
Approach:	They propose to examine the effects of positional encoding on length extrapolation.
Outcome:	The proposed methods improve the extrapolation of large language models, but they are still lacking a systematic survey.

Copied to clipboard

Zhengrui Ma, Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Min Zhang

Improving Domain Adaptation Translation with Domain Invariant and Specific Information (N19-1)

Challenge:	Existing translation pipelines require additional cascade components to achieve speech-to-speech translation.
Approach:	They propose a non-autoregressive generation framework for simultaneous speech translation . it integrates both text-to-text and speech-tospeech tasks into a unified framework .
Outcome:	The proposed framework outperforms state-of-the-art models in speech-to-text and speech- to-speech tasks.

Copied to clipboard

Shuhao Gu, Yang Feng, Qun Liu

Non-autoregressive Streaming Transformer for Simultaneous Translation (2023.emnlp-main)

Challenge:	Neural machine translation models are based on the encoder-decoder architecture, which makes them overfitting to frequent observations.
Approach:	They propose a method to explicitly model out-of-domain information in an encoder-decoder framework . they propose combining out- of-domain training data with out-out-of domain data .
Outcome:	The proposed method outperforms baselines on multiple data sets.

Copied to clipboard

Zhengrui Ma, Shaolei Zhang, Shoutao Guo, Chenze Shao, Min Zhang, Yang Feng

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

Challenge:	Simultaneous machine translation models are trained to strike a balance between latency and translation quality.
Approach:	They propose a non-autoregressive streaming Transformer which generates blank tokens and decodes repetitive tokens to adjust its READ/WRITE strategy flexibly.
Outcome:	The proposed model outperforms previous strong autoregressive models on various benchmarks on siMT.

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.

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

Copied to clipboard

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Greedy Search with Probabilistic N-gram Matching for Neural Machine Translation (D18-1)

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Copied to clipboard

Chenze Shao, Xilin Chen, Yang Feng

Non-Autoregressive Models for Fast Sequence Generation (2022.emnlp-tutorials)

Challenge:	Neural machine translation models are usually trained with word-level loss under teacher forcing algorithm . however, this method suffers from exposure bias due to high variance of gradient estimation .
Approach:	They propose a method with a differentiable sequence-level training objective . they use greedy search to alleviate the problem of exposure bias .
Outcome:	Experiments on Chinese-to-English translation tasks show that the proposed method outperforms the reinforcement-based methods.

Copied to clipboard

Yang Feng, Chenze Shao

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Autoregressive (AR) models can only generate target sequence word-by-word due to the AR mechanism and suffer from slow inference.
Approach:	This tutorial provides an introduction to non-autoregressive sequence generation.
Outcome:	This tutorial explains how to generate non-autoregressive sequence generation models.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception (2026.findings-acl)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Jilong Zhu, Yang Feng

Visual Data in NLP

Challenge:	Existing input-centric solutions fail to reverse this intrinsic mechanism of information loss.
Approach:	They propose a Variational Information Flow framework that leverages a probabilistic perspective to model visual saliency relevant to the question-answer pair as a latent distribution.
Outcome:	The proposed framework improves general VQA, fine-grained perception and visual grounding.

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (N18-1)

Copied to clipboard

Zhen Yang, Wei Chen, Feng Wang, Bo Xu

Back Translation for Speech-to-text Translation Without Transcripts (2023.acl-long)

Challenge:	Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks.
Approach:	They propose an approach for applying GANs to NMT by building a conditional sequence generative adversarial net with two adversarials.
Outcome:	The proposed model outperforms the existing RNNSearch and Transformer on English-German and Chinese-English translation tasks.

Copied to clipboard

Qingkai Fang, Yang Feng

AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment (2025.emnlp-main)

Challenge:	End-to-end speech-totext translation (ST) is often achieved by utilizing source transcripts, but transcripts are only sometimes available since numerous unwritten languages exist worldwide.
Approach:	They propose an algorithm to synthesize pseudo ST data from monolingual target data to enhance ST without generating source transcripts.
Outcome:	The proposed method achieves an average boost of 2.3 BLEU on MuST-C En-De, En-Fr, and En-Es datasets.

Copied to clipboard

Mengyu Bu, Shaolei Zhang, Zhongjun He, Hua Wu, Yang Feng

Addressing the Length Bias Challenge in Document-Level Neural Machine Translation (2023.findings-emnlp)

Challenge:	Multilingual large language models (LLMs) possess impressive multilingual understanding and generation capabilities, but performance and cross-lingual alignment often lag for non-dominant languages.
Approach:	They propose a representation-level framework to enhance multilingual performance of pre-trained LLMs by integrating multilingual semantic alignment and language feature integration.
Outcome:	The proposed framework improves multilingual capability of pre-trained LLMs by bringing representations closer and improving cross-lingual alignment.

Copied to clipboard

Zhang Zhuocheng, Shuhao Gu, Min Zhang, Yang Feng

Improving Autoformalization Using Direct Dependency Retrieval (2026.acl-long)

Challenge:	Document-level neural machine translation (DNMT) models incorporate context information through increased maximum lengths of source and target sentences.
Approach:	They propose a sliding decoding strategy that limits the length of target sentences . they propose 'length-normalized attention mechanism' to aid the model in focusing on target information .
Outcome:	The proposed method can achieve state-of-the-art results on open datasets.

Copied to clipboard

Shaoqi Wang, Lu Yu, Siwei Lou, Feng Yan, Chunjie Yang, Qing Cui, Jun Zhou

Decoder-only Streaming Transformer for Simultaneous Translation (2024.acl-long)

Challenge:	Existing methods for hallucinate formal dependencies lack scalability and precision to leverage ever-growing public datasets.
Approach:	They propose a retrieval-augmented framework based on Direct Dependency Retrieval to generate formal dependencies from natural-language mathematical descriptions and verify their existence via an efficient Suffix Array Check (SAC).
Outcome:	The proposed framework outperforms state-of-the-art methods in retrieval precision and recall and can be used to validate formal representations in a public dataset.

Copied to clipboard

Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction (2024.findings-acl)

Challenge:	Existing methods for siMT focus on the Encoder-Decoder architecture, but there are limitations in training and inference.
Approach:	They propose a model that generates translation while reading source tokens . they propose Streaming Self-Attention mechanism tailored for the Decoder-only architecture .
Outcome:	The proposed model achieves state-of-the-art performance on three translation tasks.

Copied to clipboard

Xiaoyuan Li, Wenjie Wang, Moxin Li, Junrong Guo, Yang Zhang, Fuli Feng

Token-level Proximal Policy Optimization for Query Generation (2025.emnlp-main)

Challenge:	Existing evaluations focus on problem-solving from examiner perspective, overlooking a dual perspective of examiner regarding error identification and correction.
Approach:	They propose to use an annotated dataset to evaluate large language models from the examiner perspective and to use diverse prompts to evaluate eleven representative LLMs.
Outcome:	The proposed model outperforms all models while LLaMA-2-7B has comparable abilities to closed-source models GPT-3.5 and Gemini Pro.

Copied to clipboard

Yichen Ouyang, Lu Wang, Fangkai Yang, Pu Zhao, Chenghua Huang, Jianfeng Liu, Bochen Pang, Yaming Yang, Yuefeng Zhan, Hao Sun, Qingwei Lin, Saravan Rajmohan, Weiwei Deng, Dongmei Zhang, Feng Sun

Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval? (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have improved search engines and recommendation systems through their text understanding capabilities.
Approach:	They propose a token-level proximal policy optimization approach to empower LLMs to perform better in query generation through fine-tuning.
Outcome:	The proposed approach outperforms existing LLMs on an open-source and industrial dataset.

Copied to clipboard

Hengyi Feng, Zeang Sheng, Meiyi Qiang, Yang Li, Wentao Zhang

Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval (2025.emnlp-main)

Challenge:	Rapid advances in multimodal large language models have revolutionized cross-modality understanding.
Approach:	They propose a method that uses whitening transformations to adjust MLLM representation spaces . they propose ML models that are dominated by textual semantics and visual semantics .
Outcome:	The proposed approach improves zero-shot multimodal retrieval performance without fine-tuning efforts.

Copied to clipboard

Tianlu Zheng, Yifan Zhang, Xiang An, Ziyong Feng, Kaicheng Yang, Qichuan Ding

Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning (2025.findings-acl)

Challenge:	a large-scale visionlanguage pre-training framework is limited by the scarcity of large-sized annotated vision-language data . noise-resistant data construction pipeline is needed to filter and caption web-sourced images . noisy text tokens can be a problem for fine-grained representation learning .
Approach:	They develop a noise-resistant data construction pipeline that leverages in-context learning capabilities of MLLMs to automatically filter and caption web-sourced images.
Outcome:	The proposed framework improves cross-modal alignment by masking noisy textual tokens based on the gradient-attention similarity score.

Copied to clipboard

Ziang Ye, Zhenru Zhang, Yang Zhang, Jianxin Ma, Junyang Lin, Fuli Feng

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach (2024.findings-acl)

Challenge:	Existing approaches to enhance agent capabilities for Large Language Models treat all tokens equally . however, reasoning tokens versus boilerplate tokens differ in importance and learning complexity . recent research has focused on enhancing agent capabilities in large language models .
Approach:	They propose a Shuffle-Aware Discriminator (SHAD) for adaptive token discrimination . they propose SHAD method which adaptively emphasizes reasoning tokens during fine-tuning .
Outcome:	The proposed method improves performance over standard fine-tuning methods.

Copied to clipboard

Jingyuan Yang, Dapeng Chen, Yajing Sun, Rongjun Li, Zhiyong Feng, Wei Peng

Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data? (2024.acl-long)

Challenge:	Large Language Models generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt.
Approach:	They propose to refine a Large Language Model (LLM) with prompt-output pairs with equivalent semantics to achieve semantic consistency.
Outcome:	The proposed method improves the semantic consistency and task performance of LLMs.

Copied to clipboard

Qingkai Fang, Shaolei Zhang, Zhengrui Ma, Min Zhang, Yang Feng

GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding (2026.acl-long)

Challenge:	Existing two-pass direct speech-to-speech translation models require parallel speech data to train, which is challenging to collect.
Approach:	They propose a two-pass direct speech-to-speech translation (S2ST) model that decomposes the task into speech- to-text translation (s2TT) and text-tospech (TTS) they propose 'composer' S2ST model that integrates pretrained S2TT and TTS models into a direct S2 ST model.
Outcome:	The proposed model integrates pretrained S2TT and TTS models into a direct S2ST model without parallel speech data.

Copied to clipboard

Weicai Long, Yusen Hou, Junning Feng, Houcheng su, Shuo Yang, Donglin Xie, Yanlin Zhang

Text-like Encoding of Collaborative Information in Large Language Models for Recommendation (2024.acl-long)

Challenge:	Existing benchmarks focus on specialized DNA models trained for sequence prediction or evaluate biological knowledge using text-only questions.
Approach:	They propose a benchmark to evaluate general-purpose LLMs on sequence-based genome inference tasks.
Outcome:	The proposed benchmark outperforms baseline models on sequence-based genome inference tasks.

Copied to clipboard

Yang Zhang, Keqin Bao, Ming Yan, Wenjie Wang, Fuli Feng, Xiangnan He

FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs (2026.findings-acl)

Challenge:	Existing methods to adapt Large Language Models for Recommendation (LLMRec) do not represent collaborative information in a text-like format, which may not align optimally with LLMs.
Approach:	They propose a novel LLMRec method that integrates collaborative information through text-like encoding.
Outcome:	Extensive experiments show that BinLLM integrates collaborative information better with LLMs.

Copied to clipboard

Yun Hong, Yan Zhou, Yang Feng

GTM: A Generative Triple-wise Model for Conversational Question Generation (2021.acl-long)

Challenge:	Recent research has made significant progress in developing empathetic spoken chatbots based on large language models (LLMs).
Approach:	They propose an end-to-end empathetic spoken chatbot trained efficiently that generates emotionally expressive speech and outperforms other emmpathetic models in emphatic dialogue, SER, and SpokenQA tasks.
Outcome:	The proposed model outperforms other empathetic models on e-dialog, SER, and SpokenQA tasks and achieves strong results on several speech tasks.

Copied to clipboard

Lei Shen, Fandong Meng, Jinchao Zhang, Yang Feng, Jie Zhou

MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning (2026.findings-acl)

Challenge:	Experimental results show that opendomain conversational question generation improves the quality of questions in terms of fluency, coherence and diversity over competitive baselines.
Approach:	They propose a triple-wise model with hierarchical variations for open-domain conversational question generation using a post-question-answer triple and one-to-many semantic mappings.
Outcome:	The proposed model significantly improves the quality of questions in terms of fluency, coherence and diversity over baselines.

Copied to clipboard

Ruijun Huang, Zhiqiao Kang, Yuxuan Zhu, Junxiong Li, Jiahao Zhao, Minghuan Tan, Feng Jiang, Min Yang

Importance-based Neuron Allocation for Multilingual Neural Machine Translation (2021.acl-long)

Challenge:	Large Language Models (LLMs) exhibit severe hallucinations, which undermine reliability of automated scientific document understanding systems.
Approach:	They propose a framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization.
Outcome:	The proposed framework significantly reduces hallucination rates and improves overall accuracy on the MeasEval benchmark.

Copied to clipboard

Wanying Xie, Yang Feng, Shuhao Gu, Dong Yu

Identifying and Mitigating Social Bias Knowledge in Language Models (2025.findings-naacl)

Challenge:	Existing approaches to multilingual neural machine translation tend to preserve general knowledge, but ignore language-specific knowledge.
Approach:	They propose to divide model neurons into general and language-specific parts based on their importance across languages.
Outcome:	The proposed model can preserve general knowledge but ignore language-specific knowledge on several languages, and is universal and cost-effective.

Copied to clipboard

Ruizhe Chen, Yichen Li, Jianfei Yang, Yang Feng, Joey Tianyi Zhou, Jian Wu, Zuozhu Liu

Enhancing Context Modeling with a Query-Guided Capsule Network for Document-level Translation (D19-1)

Challenge:	Existing methods for debiasing may generate incorrect or nonsensical predictions but leave aside individual commonsense facts, resulting in modified knowledge that elicits unreasonable or undesired predictions.
Approach:	They propose a framework that identifies encoding locations of biases within language models and then applies the Fairness-Stamp (FAST) they also propose 'BiaScope' to evaluate the retention of commonsense knowledge and generalization across paraphrased social biase.
Outcome:	The proposed framework surpasses state-of-the-art baselines with superior debiasing performance while not compromising the overall model capability for knowledge retention and prediction.

Copied to clipboard

Zhengxin Yang, Jinchao Zhang, Fandong Meng, Shuhao Gu, Yang Feng, Jie Zhou

Enhancing Neural Machine Translation with Semantic Units (2023.findings-emnlp)

Challenge:	Context modeling is essential to generate coherent and consistent translation for document-level Neural Machine Translations.
Approach:	They propose a query-guided capsule network to cluster context information into different perspectives from which the target translation may concern.
Outcome:	The proposed model outperforms baseline models on multiple datasets of different domains.

Copied to clipboard

Langlin Huang, Shuhao Gu, Zhang Zhuocheng, Yang Feng

LLM as a metric critic for low resource relation identification (2024.findings-emnlp)

Challenge:	Existing methods to model and leverage semantic units in natural language do not provide a complete understanding of the whole sentence.
Approach:	They propose a method which models the integral meanings of semantic units within a sentence . they propose 'word pair encoder' to help identify the boundaries of semantic unit boundaries .
Outcome:	The proposed method outperforms baselines and supports the semantic unit representation of subwords and tokens.

Copied to clipboard

Zhe Yang, Yi Huang, Yaqin Chen, Xiaoting Wu, Junlan Feng, Chao Deng

Semi-Supervised Disfluency Detection (C18-1)

Challenge:	Existing studies show that small language models (SLMs) overfit in low resource situations . however, the gap between pre-training and fine-tuning leads to performance decay .
Approach:	They propose to combine large language models and LLM for relation identification by co-evolution . they propose to use a masked language model prompt to generate a relation identification task .
Outcome:	The proposed model can handle low resource relation identification tasks with minimal overfitting . the proposed model provides essential background knowledge to assist training process .

Copied to clipboard

Feng Wang, Wei Chen, Zhen Yang, Qianqian Dong, Shuang Xu, Bo Xu

Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)

Challenge:	Detecting disfluency can be difficult because of the flexible nature of reparandum structure and the lack of a nested structure.
Approach:	They propose a semi-supervised approach which extracts hidden features from self-attention without any Recurrent Neural Network (RNN) or Convolutional Neural Net (CNN).
Outcome:	The proposed approach improves over baselines by using unlabelled data . identifying and removing non-fluent factors would help to improve spontaneous speech quality .

Copied to clipboard

Fengyuan Liu, Yi Huang, Sichun Luo, Yuqi Wang, Yazheng Yang, Xinye Li, Zefa Hu, Junlan Feng, Qi Liu

One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation (2022.naacl-main)

Challenge:	Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio.
Approach:	They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search.
Outcome:	The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search.

Copied to clipboard

Chenze Shao, Xuanfu Wu, Yang Feng

Event Detection without Triggers (N19-1)

Challenge:	Existing non-autoregressive neural machine translation models suffer from multimodality problem . multi-modality is not solved by a teacher forcing algorithm, limiting model capability .
Approach:	They propose a method that generates multiple reference translations for each source sentence . they compare the NAT output with all references and select the one that best fits the simulated model .
Outcome:	The proposed method achieves 29.82 BLEU with only one decoding pass on WMT14 En-De .

Copied to clipboard

Shulin Liu, Yang Li, Feng Zhang, Tao Yang, Xinpeng Zhou

Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation (2022.emnlp-main)

Challenge:	Existing approaches to event detection require annotated triggers and event types in training data.
Approach:	They propose a framework that encodes the representation of a sentence based on target event types.
Outcome:	The proposed framework achieves competitive performances compared with state-of-the-art methods.

Copied to clipboard

Qifan Wang, Li Yang, Xiaojun Quan, Fuli Feng, Dongfang Liu, Zenglin Xu, Sinong Wang, Hao Ma

Speeding Up Neural Machine Translation Decoding by Cube Pruning (D18-1)

Challenge:	Existing automatic question generation methods focus on encoding passage and answer to generate question.
Approach:	They propose an automatic question generation approach which integrates question generation with its dual problem, question answering, into a unified primal-dual framework.
Outcome:	The proposed approach outperforms existing methods on SQuAD and HotpotQA benchmarks.

Copied to clipboard

Wen Zhang, Liang Huang, Yang Feng, Lei Shen, Qun Liu

Customizing In-context Learning for Dynamic Interest Adaption in LLM-based Recommendation (2025.findings-acl)

Challenge:	Neural machine translation suffers from slow translation speed due to the large search space . a trade-off has to be made between translation quality and speed, argues a new study .
Approach:	They apply cube pruning technique to speed up dynamic programming into neural machine translation to speed it up.
Outcome:	The proposed method can translate faster on GPUs and CPUs with better translation quality than naive beam search.

Copied to clipboard

Keqin Bao, Ming Yan, Yang Zhang, Jizhi Zhang, Wenjie Wang, Fuli Feng, Xiangnan He

Low-Resource NLP

Challenge:	Existing Large Language Model (LLM)-based recommender systems face challenges to adapt to dynamic user interests without any model-level updates.
Approach:	They propose a framework that establishes recommendation-oriented in-context learning by structuring recent user interactions and current inputs into ICL formats.
Outcome:	The proposed model adapts to dynamic user interests without model updates without any model updates and is available online at https://anonymous.4open.science/r/RecICL-8003.

Mixup Decoding for Diverse Machine Translation (2021.findings-emnlp)

Copied to clipboard

Jicheng Li, Pengzhi Gao, Xuanfu Wu, Yang Feng, Zhongjun He, Hua Wu, Haifeng Wang

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)

Challenge:	Existing methods for generating multiple translations for source and target languages neglect the one-to-many mapping between the source and the target languages.
Approach:	They propose a method to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding.
Outcome:	Experiments on WMT’16 en-ro, WMT'14 en de, and WMT ‘17 zh-en show that the proposed method outperforms all previous diverse machine translation methods.

Copied to clipboard

Zijing Wang, YongKang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schuetze

CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering (2026.acl-long)

Challenge:	Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance.
Approach:	They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation.
Outcome:	The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs.

Copied to clipboard

Zili Wei, Yilin Wang, Xiaocui Yang, Shi Feng, Weidong Bao, Daling Wang, Zihan Wang, Yifei Zhang

Simple and Effective Text Matching with Richer Alignment Features (P19-1)

Challenge:	Existing methods for iterative retrieval-augmented generation (iRAG) suffer from greedy single-path expansion and granularity–demand mismatch .
Approach:	They propose a model that constructs candidate triples and history-conditionally integrates them to distill core triples to generate the next-hop query.
Outcome:	The proposed model mitigates the greedy single-path expansion and granularity–demand mismatch by preserving multiple plausible evidence chains.

Copied to clipboard

Runqi Yang, Jianhai Zhang, Xing Gao, Feng Ji, Haiqing Chen

Challenge:	Existing models only use a single inter-sequence alignment layer to make full use of this process.
Approach:	They propose to keep three key features available for inter-sequence alignment . they conduct experiments on four well-studied benchmark datasets .
Outcome:	The proposed model is able to perform on four well-studied datasets with fewer parameters and the inference speed is at least 6 times faster than similar models.

Exploring Pre-trained Language Models for Event Extraction and Generation (P19-1)

Copied to clipboard

Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan, Dongsheng Li

EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction (2024.findings-emnlp)

Challenge:	Existing methods to extract event data are laborious to create and limited in size.
Approach:	They propose an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles.
Outcome:	The proposed method surpasses existing methods on the ACE2005 dataset and improves on the previous methods.

Copied to clipboard

Li Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu, Jingang Wang, Fuli Feng, Zenglin Xu, Yi Fang, Lifu Huang, Dongfang Liu

Language-agnostic BERT Sentence Embedding (2022.acl-long)

Challenge:	Existing methods to extract product attribute value require multiple extractions to obtain all corresponding values.
Approach:	They propose an Efficient product Attribute Value Extraction approach using lightweight sparse-layer interaction.
Outcome:	The proposed method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large.

Copied to clipboard

Fangxiaoyu Feng, Yinfei Yang, Daniel Cer, Naveen Arivazhagan, Wei Wang

Language Models as Continuous Self-Evolving Data Engineers (2025.emnlp-main)

Challenge:	Existing methods for learning bilingual sentence embeddings are not well explored.
Approach:	They propose to combine best methods for learning multilingual sentence embeddings with pre-trained models to achieve 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba.
Outcome:	The proposed model achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, above the 65.5% achieved by LASER.

Copied to clipboard

Peidong Wang, Ming Wang, Zhiming Ma, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Kaisong Song

CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation (2023.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data.
Approach:	They propose a paradigm that enables LLMs to train themselves by generating, cleaning, reviewing and annotating data with preference information.
Outcome:	The proposed model can generate, clean, review, and annotate data with preference information significantly reducing time and cost of post-training data construction.

Copied to clipboard

Yan Zhou, Qingkai Fang, Yang Feng

Enhancing LLM-Based Social Bot via an Adversarial Learning Framework (2025.emnlp-main)

Challenge:	Existing methods to translate speech signals into text are limited by the modality gap between speech and text.
Approach:	They propose Cross-modal Mixup via Optimal Transport to overcome the modality gap between speech and text by finding alignment between modalities.
Outcome:	Experiments on the MuST-C ST benchmark show that CMOT achieves an average BLEU of 30.0 in 8 translation directions, outperforming previous methods.

Copied to clipboard

Fanqi Kong, Xiaoyuan Zhang, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng

Robustness in NLP

Challenge:	Social media platforms provide an ideal testbed for large language models that exhibit human-like behavior.
Approach:	They propose an LLM-based social **Bot that enhances human-like generative capabilities through an adversarial learning framework.
Outcome:	The proposed framework generates human-like content aligned with diverse user profiles . it exhibits strong social responsiveness, more accurately modeling opinion dynamics .

NEAT: Neuron-Based Early Exit for Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Kang Liu, YongKang Liu, Xiaocui Yang, Peidong Wang, Wen Zhang, Shi Feng, Yifei Zhang, Daling Wang

Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework (2022.acl-long)

Challenge:	Existing approaches to reduce overthinking require additional rollout computation or externally labeled datasets.
Approach:	They propose a Neuron-based Early reAsoning exiT framework that monitors neuron-level activation dynamics to enable training-free early exits.
Outcome:	The proposed framework reduces the amount of reasoning steps generated by LRMs while maintaining accuracy.

Copied to clipboard

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)

Challenge:	Existing methods for simultaneous machine translation (SiMT) are more challenging since the source sentence is always incomplete during translating.
Approach:	They propose a framework to reduce the position bias by bridging the structural gap between SiMT and full-sentence MT.
Outcome:	The proposed framework reduces the position bias by bridging the structural gap between SiMT and full-sentence MT.

Copied to clipboard

Feng Luo, Yu-Neng Chuang, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu

Bridging the Gap between Training and Inference for Neural Machine Translation (P19-1)

Challenge:	Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions.
Approach:	They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary.
Outcome:	The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy.

Copied to clipboard

Wen Zhang, Yang Feng, Fandong Meng, Di You, Qun Liu

MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable Recommendation (2025.acl-long)

Challenge:	Neural Machine Translation generates target words sequentially while at inference it has to generate the entire sequence from scratch.
Approach:	They propose to use ground truth and inference to generate target words sequentially while at inference it has to generate the entire sequence from scratch.
Outcome:	Experiments on Chinese->English and WMT’14 English->German translation tasks show that the proposed model can achieve significant improvements on multiple datasets.

Copied to clipboard

Ching-Wen Yang, Zhi-Quan Feng, Ying-Jia Lin, Che Wei Chen, Kun-da Wu, Hao Xu, Yao Jui-Feng, Hung-Yu Kao

NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs (2026.acl-long)

Challenge:	Existing models that generate generic aspects do not provide personalized informative recommendations.
Approach:	They propose a model that integrates aspect category as another input dimension to facilitate memorizing fine-grained aspect terms.
Outcome:	The proposed model outperforms baseline model on restaurant review datasets in the restaurant domain.

Copied to clipboard

Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang, MuRun Yang, DingYang Lin, Kaiyan Chang, Tong Zheng, Bei Li, Peinan Feng, Quan Du, Tong Xiao, JingBo Zhu

Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy (2021.emnlp-main)

Challenge:	Large language models have significantly advanced Multilingual Machine Translation (MMT) yet scaling to many languages while maintaining robust performance across directions remains challenging.
Approach:	They propose a strategy to reduce the number of translations in one direction . they propose auxiliary parallel sentences to promote cross-lingual transfer .
Outcome:	The proposed model performs on par with or better than substantially larger baselines.

Copied to clipboard

MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation (2025.naacl-long)

Challenge:	Existing methods for simultaneous machine translation require multiple models for different latency levels, resulting in large computational costs.
Approach:	They propose a universal SiMT model with Mixture-of-Experts Wait-k Policy to achieve the best translation quality under arbitrary latency with only one model.
Outcome:	The proposed model outperforms all the strong baselines under different latency levels including the state-of-the-art adaptive policy.

Copied to clipboard

Langlin Huang, Mengyu Bu, Yang Feng

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users (2025.emnlp-main)

Challenge:	Byte-based machine translation systems can be used in multilingual settings.
Approach:	They propose a method that maps each character to specific byte(s) they propose byte-level tokenization that eliminates unknown words .
Outcome:	The proposed method outperforms existing methods without manual adjustment of hyper-parameters and surpasses subword-based models with fewer parameters in Ted-59 dataset.

Copied to clipboard

Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant, Shi Feng, Fumeng Yang, Rachel Rudinger, Jordan Lee Boyd-Graber

Challenge:	We test alignment methods to ensure LLMs are helpful, but they train or evaluate on what users prefer .
Approach:	They test alignment methods to ensure LLMs generate plans that help users . they get 4388 plan executions and 5584 comparisons to measure user preferences .
Outcome:	The proposed approach can be applied to the problem of user preferences and helpfulness.

Calibrating LLM-Based Evaluator (2024.lrec-main)

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data (2025.acl-long)

Challenge:	Existing models for large language models lack the ability to calibrate their outputs towards human preference.
Approach:	They propose a multi-stage, gradient-free approach to calibrate an LLM-based evaluator toward human preference.
Outcome:	The proposed approach improves correlation with expert evaluation on multiple text quality evaluation datasets.

Copied to clipboard

Yu Zhang, Ruijie Yu, Jidong Tian, Feng Zhu, Jiapeng Liu, Xiaokang Yang, Yaohui Jin, Yanyan Xu

STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation (2022.acl-long)

Challenge:	Existing methods for extracting chemical procedures from literature are insufficient and low-quality due to the inherent ambiguity of chemical language and the high cost of human annotation.
Approach:	They propose a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.
Outcome:	The proposed model outperforms the baseline model on R2D and D2A tasks by 10%.

Copied to clipboard

Qingkai Fang, Rong Ye, Lei Li, Yang Feng, Mingxuan Wang

Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning (2026.acl-long)

Challenge:	Existing methods to learn speech representations for end-to-end speech-totext translation (ST) neglect the representation discrepancy across modalities.
Approach:	They propose a method to calibrate the representation discrepancy between modalities by mixing up the representation sequences of different modality inputs.
Outcome:	The proposed method alleviates the cross-modal representation discrepancy and improves on a strong baseline on eight translation directions.

Copied to clipboard

Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing, Qingyi Si, Zhuoran Li, Weikang Gong, Deqing Yang, Yanghua Xiao, Hongcheng Guo

Token-level Adaptive Training for Neural Machine Translation (2020.emnlp-main)

Challenge:	Group Relative Policy Optimization (GRPO) uses a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecting the varying contribution of individual reasoning steps.
Approach:	They introduce Outcome-grounded Advantage Reshaping (OAR) which redistributes advantages based on how much each token influences the model’s final answer.
Outcome:	Empirical results show that OAR-G outperforms GRPO on a high-fidelity attribution signal and suppresses low-impact tokens while preserving the advantage mass.

Copied to clipboard

Shuhao Gu, Jinchao Zhang, Fandong Meng, Yang Feng, Wanying Xie, Jie Zhou, Dong Yu

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

Challenge:	Existing token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural machine translation (NMT).
Approach:	They propose to assign tokens with different frequencies to target tokens during training to encourage the model to pay more attention to low-frequency tokens.
Outcome:	The proposed model yields consistent improvements on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens.

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.

Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems (2026.acl-long)

Copied to clipboard

Ziyuan Yang, Wenxuan Ding, Shangbin Feng, Yulia Tsvetkov

Learning to Leverage High-Order Medical Knowledge Graph for Joint Entity and Relation Extraction (2023.findings-acl)

Challenge:	Existing research is leveraging multiple language models with diverse skills and strengths to collaborate.
Approach:	They propose mitigation strategies to mitigate the impact of malicious models by employing external supervisors to disable/mask them out to reduce their influence.
Outcome:	The proposed mitigation strategies recover 95.31% of initial performance while making model collaboration systems fully resistant to malicious models remains an open question.

Copied to clipboard

Zhe Yang, Yi Huang, Junlan Feng

RWKV-CLIP: A Robust Vision-Language Representation Learner (2024.emnlp-main)

Challenge:	Medical terms are difficult to understand and relations between medical entities become complicated.
Approach:	They propose to leverage medical domain knowledge for extracting entities and relations for Chinese medical texts by building a heterogeneous graph based on medical knowledge graph.
Outcome:	The proposed method is more effective than state-of-the-art methods on real Chinese medical texts.

Copied to clipboard

Tiancheng Gu, Kaicheng Yang, Xiang An, Ziyong Feng, Dongnan Liu, Weidong Cai, Jiankang Deng

MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings (2026.acl-long)

Challenge:	Using large image-text datasets, large-scale image-data sets have been used for visionlanguage pre-training.
Approach:	They propose a framework that leverages Large Language Models to combine and refine information from web-based image-text pairs, synthetic captions, and detection tags.
Outcome:	The proposed framework can combine and refine information from web-based image-text pairs, synthetic captions, and detection tags.

Copied to clipboard

Yiqun Zhang, Hao Li, Zihan Wang, Shi Feng, Xiaocui Yang, Daling Wang, Bo Zhang, Lei Bai, Shuyue Hu

Diversity and Consistency: Exploring Visual Question-Answer Pair Generation (2021.findings-emnlp)

Challenge:	Multi-turn, long-horizon tasks require dozens of sequential model calls per episode.
Approach:	They propose a cost-aware multi-turn LLM routing tool which encodes interaction history and candidate models into joint history–model embeddings and learns an outcome estimator from logged trajectories to predict turn-level model utility.
Outcome:	The proposed model reduces cost and performance by 58.7% on ScienceWorld and on Humanity’s Last Exam (HLE) and even reduces costs for held-out tasks.

Copied to clipboard

Sen Yang, Qingyu Zhou, Dawei Feng, Yang Liu, Chao Li, Yunbo Cao, Dongsheng Li

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)

Challenge:	Existing tasks to generate question-answer pairs from visual images are under-explored.
Approach:	They propose a task that targets question-answer pair generation from visual images.
Outcome:	The proposed model can generate diverse or consistent QAPs on two benchmarks.

Copied to clipboard

Peidong Wang, Zhiming Ma, Xin Dai, YongKang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang

Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)

Challenge:	Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors .
Approach:	They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details.
Outcome:	The proposed method improves accuracy, inference efficiency, and real-time processing capabilities.

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Liang Zhao, Yuchun Fan, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference (2022.tacl-1)

Challenge:	Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive.
Approach:	They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources.
Outcome:	Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources.

Copied to clipboard

Yufei Feng, Xiaoyu Yang, Xiaodan Zhu, Michael Greenspan

Explainability & Interpretability in NLP

Challenge:	a neural network model for natural language inference (NLI) is proposed.
Approach:	They propose a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision that rewards specific reasoning paths through policy gradients.
Outcome:	The proposed model shows superior capability in monotonicity inference, generalization, and interpretability compared with previous models on the existing datasets.

Extending Context Window of Large Language Models from a Distributional Perspective (2024.emnlp-main)

Copied to clipboard

Yingsheng Wu, Yuxuan Gu, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin

Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths (2026.acl-long)

Challenge:	Existing scaling methods for extending context window rely on empirical approaches and lack understanding of the internal distribution within RoPE resulting in suboptimal performance.
Approach:	They propose to optimize the context window extending task from the view of rotary angle distribution by minimizing disturbance between rotary angles to maintain consistency with the pre-training phase.
Outcome:	The proposed approach reduces by up to 72% of the distributional disturbance when extending LLaMA2’s context window to 8k, and reduces it by up 32% when extending to 16k.

Copied to clipboard

YiJie Huang, Xiaocui Yang, Shi Feng, Wen Zhang, Kaisong Song, Yifei Zhang, Daling Wang

CARE-STaR: Constraint-aware Self-taught Reasoner (2025.findings-acl)

Challenge:	Existing query-based alignment modules enforce uniform cross-attention across all layers, leading to computational redundancy.
Approach:	They propose a framework that allows for asynchronous query-based alignment with large-scale visual features.
Outcome:	The proposed framework matches or surpasses baseline performance while reducing alignment FLOPs by approximately 37% during training and inference.

Copied to clipboard

Zhiliang Li, Bo Tang, Yijun Niu, Beihong Jin, Qiwen Shi, Yuchen Feng, Zhiyu Li, Jie Hu, Mingchuan Yang, Feiyu Xiong

Investigating Human and LLMs’ Decisions in Unverifiable Environments: A Case Study with GitHub Activity Overview (2026.findings-acl)

Challenge:	Recent research on instruction following has demonstrated that LLMs can handle complex instructions.
Approach:	They propose to assign constraints to different levels of constraints in instructions . they use chain-of-thought and self-taught reasoner methods to identify constraints .
Outcome:	The proposed method outperforms supervised fine-tuning (SFT) on three instruction-following benchmarks.

Copied to clipboard

Zheng Jiang, Wei Wang, Gaowei Zhang, Yang Feng, Yi Wang

Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality (2026.acl-long)

Challenge:	examining the behaviors of Large Language Models as artificial social actors is underexplored, especially in unverifiable scenarios where conventional benchmarking has little to help improve their abilities.
Approach:	They propose a method to collect, compare, and reason about human and LLMs' decisions in an unverifiable scenario and use it to examine their behaviors.
Outcome:	The proposed method compared human and LLM decisions in an unverifiable scenario on GitHub and found that proprietary LLMs behave more like humans than open-source LLM systems.

Copied to clipboard

Mengyu Bu, Yang Feng

Learnable Privacy Neurons Localization in Language Models (2024.acl-short)

Challenge:	Large language models exhibit strong general intelligence, yet their multilingual performance remains imbalanced.
Approach:	They propose a compositional encoder-LLM-decoder architecture that offloads multilingual understanding to external pretrained translation models while preserving the LLM as an English-centric core for general knowledge processing and reasoning.
Outcome:	The proposed architecture outperforms baseline models on four large language models across understanding, reasoning, and generation.

Copied to clipboard

Ruizhe Chen, Tianxiang Hu, Yang Feng, Zuozhu Liu

Simultaneous Machine Translation with Tailored Reference (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) memorize and disclose private information, especially Personally Identifiable Information (PII) concerns regarding privacy and security within human society remain poorly understood.
Approach:	They propose to use learnable binary weight masks to localize PII-sensitive neurons within LLMs by deactivating localized privacy neurons.
Outcome:	The proposed method localizes PII-sensitive neurons across all layers and shows the property of PI I specificity.

Copied to clipboard

Information-Transport-based Policy for Simultaneous Translation (2022.emnlp-main)

Challenge:	Existing SiMT models are trained using the same reference disregarding the varying amounts of available source information at different latency.
Approach:	They propose a method that provides tailored reference for the SiMT models trained at different latency by rephrasing ground-truth to the tailored reference.
Outcome:	The proposed method achieves state-of-the-art translation performance on three translation tasks.

Copied to clipboard

MedThink: A Rationale-Guided Framework for Explaining Medical Visual Question Answering (2025.findings-naacl)

Challenge:	Simultaneous translation (ST) outputs translation while receiving source inputs . low latency restriction restricts ST to translating target tokens based on current received source tokens.
Approach:	They propose a system that outputs translation while receiving source inputs . it uses a read/write policy to decide whether to translate a target token or wait for the next source token .
Outcome:	The proposed model outperforms baselines and achieves state-of-the-art on text-to-text and speech-to text tasks.

Copied to clipboard

Xiaotang Gai, Chenyi Zhou, Jiaxiang Liu, Yang Feng, Jian Wu, Zuozhu Liu

Explainability & Interpretability in NLP

Challenge:	Existing models for medical visual question answering are limited in their interpretation and interpretation . a semi-automated annotation process is used to streamline data preparation and build new benchmark datasets .
Approach:	They propose a semi-automated annotation process to streamline data preparation and build new benchmark Med-VQA datasets.
Outcome:	The proposed method achieves an accuracy of 83.5% on R-RAD, 86.3% on RSLAKE and 87.2% on RPath.

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation (2020.coling-main)

Copied to clipboard

Shuhao Gu, Yang Feng

HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)

Challenge:	Neural machine translation models suffer from catastrophic forgetting during continual training . models tend to overfit to frequent observations in the in-domain data but forget previously learned knowledge.
Approach:	They investigated the causes of catastrophic forgetting in NMT models by examining their parameters and modules.
Outcome:	The proposed model forgets previously learned knowledge and swings to fit new data . the results show that some parameters are important for both the general-domain and in-domain translation and the great change of them during continual training brings about the performance decline in general- domain.

Copied to clipboard

Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao

Linguistics & Cognitive NLP

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs).
Approach:	They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.
Outcome:	The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters.

HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)

Copied to clipboard

Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs (2025.findings-acl)

Challenge:	Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation.
Approach:	They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write .
Outcome:	The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays.

Copied to clipboard

Guhao Feng, Kai Yang, Yuntian Gu, Xinyue Ai, Shengjie Luo, Jiacheng Sun, Di He, Zhenguo Li, Liwei Wang

Understanding and Bridging the Modality Gap for Speech Translation (2023.acl-long)

Challenge:	Despite the success of transformer-based large language models, understanding and enhancing their mathematical capabilities remains a significant challenge.
Approach:	They propose to use numerical precision as a key factor that influences LLMs' effectiveness in arithmetical tasks to determine their effectiveness.
Outcome:	The proposed models perform better in arithmetic tasks than transformer-based models with standard numerical precision.

Copied to clipboard

Qingkai Fang, Yang Feng

Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables (P19-1)

Challenge:	Existing methods to improve end-to-end speech translation (ST) use multitask learning, but there is always a modality gap between ST and MT due to the differences between speech and text.
Approach:	They propose a method to bridge the modality gap between ST and MT by leveraging (text) machine translation data.
Outcome:	The proposed method bridges the modality gap and achieves significant improvements over baseline in all eight directions.

Copied to clipboard

Lei Shen, Yang Feng, Haolan Zhan

RATION: Entropy-Driven Task-Adaptive Visual Attention Allocation Framework for Multimodal Reasoning (2026.findings-acl)

Challenge:	Existing work on multi-turn conversations has focused on the relationship between the response and context, but it is lacking a model to model the relationship.
Approach:	They propose a conversational semantic relationship RNN model to construct hierarchical dependency between utterances and their context.
Outcome:	The proposed model significantly improves the quality of responses in terms of fluency, coherence, and diversity compared to baseline methods.

Copied to clipboard

Xingle Xu, Fanheng Kong, Dexian Cai, Shi Feng, Xiaocui Yang, Daling Wang, Yifei Zhang

IG-Pruning: Input-Guided Block Pruning for Large Language Models (2025.emnlp-main)

Challenge:	Prior studies have focused on strengthening multimodal reasoning by improving representation alignment or increasing computation, but these methods do not characterize the differences in visual demands across tasks.
Approach:	They propose an entropy-driven task-adaptive visual attention allocation framework that uses visual attention entropic as a control signal to dynamically allocate attention according to task demands.
Outcome:	The proposed framework achieves consistent performance gains across diverse reasoning tasks, datasets, and models, providing a clear direction toward more reliable multimodal reasoning.

Copied to clipboard

Kangyu Qiao, Shaolei Zhang, Yang Feng

End-to-End Simultaneous Speech Translation with Differentiable Segmentation (2023.findings-acl)

Challenge:	Existing methods for efficient inference rely on fixed block masks, which can lead to suboptimal performance.
Approach:	They propose an input-aware block-wise pruning method that dynamically selects layer masks at inference time.
Outcome:	The proposed method outperforms state-of-the-art static depth pruning methods . it is particularly suitable for resource-constrained deployment scenarios .

Copied to clipboard

BERT-BC: A Unified Alignment and Interaction Model over Hierarchical BERT for Response Selection (2024.lrec-main)

Speech & Audio in NLP

Challenge:	Existing methods to perform simultaneous speech translation always separate segmentation from the underlying model.
Approach:	They propose to use Differentiable Segmentation (DiSeg) to learn segmentation from the translation model.
Outcome:	Experimental results show that the proposed model can learn segmentation from the translation model.

Copied to clipboard

Zhenfei Yang, Beiming Yu, Yuan Cui, Shi Feng, Daling Wang, Yifei Zhang

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems (2026.acl-long)

Challenge:	Recent performance boosting for dialogue response selection task achieved by Cross-Encoder based models is limited and the learned models have poor generalization capability in realistic scenarios.
Approach:	They propose a model that combines the representation-based Bi-Encoder and interaction-based Cross-Encoding to achieve better semantic representation.
Outcome:	The proposed model can achieve state-of-the-art performance on three benchmark datasets for multi-turn response selection.

Copied to clipboard

Shuhang Chen, Hangjie Yuan, Yunqiu Xu, Pengwei Liu, Tao Feng, Jun Cen, Zeying Huang, Yi Yang

Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt (2023.findings-acl)

Challenge:	Existing multimodal large language models (MLLMs) exhibit significant limitations when extracting essential information and reasoned properties from diagrams and performing complex reasoning based on these visual inputs.
Approach:	They propose a benchmark that provides a fine-grained evaluation of MLLMs’ perception and reasoning capabilities.
Outcome:	The proposed benchmark shows that existing MLLMs exhibit limitations when extracting essential information and reasoned properties from diagrams and performing complex reasoning based on these visual inputs.

Copied to clipboard

Xiaocui Yang, Shi Feng, Daling Wang, Qi Sun, Wenfang Wu, Yifei Zhang, Pengfei Hong, Soujanya Poria

Sentiment Analysis

Challenge:	Existing studies require massive labeled data to train models for multimodal data analysis.
Approach:	They propose a novel multimodal prompt model that captures specific aspect terms in a few-shot scenario.
Outcome:	The proposed model outperforms baselines on two MABSA-related tasks on a few-shot dataset.

MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents (2026.acl-long)

Copied to clipboard

Ruihan Chen, Qiming Li, Xiaocheng Feng, Weihong Zhong, Xiaoliang Yang, Yuxuan Gu, Zekun Zhou, Yunfei Lu, Haoyu Ren, Kun Chen, Dandan Tu, Bing Qin

Scaling Law for Document Neural Machine Translation (2023.findings-emnlp)

Challenge:	Existing GUI benchmarks lack fine-grained diagnostics to identify which capabilities lead to task failures.
Approach:	They propose a multilingual P R GUI Benchmark to assess LVLMs' language capabilities . they propose XLI to align non-English hidden states with English ones during inference .
Outcome:	The proposed benchmark reveals consistent gaps between English and non-English settings . it reduces the cross-lingual gaps with an average gain of 6.5% in non- English settings compared to static benchmarks .

Copied to clipboard

Zhang Zhuocheng, Shuhao Gu, Min Zhang, Yang Feng

ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation (2026.acl-long)

Challenge:	Neural machine translation (NMT) methods fail to capture discourse phenomena such as pronominal anaphora, lexical consistency, and document coherence as the input text exceeds a single sentence.
Approach:	They examine the effects of model scale, data scale, and sequence length on translation quality when model size is limited.
Outcome:	The proposed model scales and data scales are compared with the existing models and show that increasing sequence length improves translation quality when model size is limited.

Copied to clipboard

Zhuoyue Gao, Xiaohui Wang, Xiaocui Yang, Wen Zhang, Daling Wang, Shi Feng, Yifei Zhang