Papers by Feng Liu

S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)

Challenge:	High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context .
Approach:	They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage.
Outcome:	The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora.

Copied to clipboard

Feng Jiang, Zhiyu Lin, Yiyang Liu, Liumeng Xue, Fan Bu, Yuhao Du, Xiangying Chen, Benyou Wang, Haizhou Li

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

Challenge:	Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits.
Approach:	They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression.
Outcome:	The proposed system enables more natural, robust, and human-aligned speech agents.

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

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

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

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

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

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

Empowering Math Problem Generation and Reasoning for Large Language Model via Synthetic Data based Continual Learning Framework (2025.emnlp-main)

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

Qian Wan, Wangzi Shi, Jintian Feng, Shengyingjie Liu, Luona Wei, Zhicheng Dai, Jianwen Sun

Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning (2025.findings-emnlp)

Challenge:	Existing learning frameworks for large language models (LLMs) for math problem generation are limited and lack quality data.
Approach:	They propose a synthetic data based continual learning framework to improve LLMs ability for MPG and math reasoning.
Outcome:	The proposed framework improves performance on large language models and math reasoning using supervised fine-tuning, data synthesis and direct preference optimization.

Copied to clipboard

Shengyuan Wang, Jie Feng, Tianhui Liu, Dan Pei, Yong Li

TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching (2020.coling-main)

Challenge:	Large language models (LLMs) have extensive world knowledge, but often generate inaccurate geospatial knowledge.
Approach:	They propose a framework for evaluation of large language models to mitigate hallucinations . they use Kahneman-Tversky Optimization to align LLMs with their reality .
Outcome:	The proposed evaluation framework uncovers hallucinations in 20 advanced LLMs.

Copied to clipboard

Heng Gong, Yawei Sun, Xiaocheng Feng, Bing Qin, Wei Bi, Xiaojiang Liu, Ting Liu

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-Context QA (2025.findings-acl)

Challenge:	Recent studies show that pre-trained language models can produce informative and fluent text with the help of large-scale datasets, but they suffer insufficient learning problem with limited training data.
Approach:	They propose to use table transformation module with template to rewrite structured table in natural language as input for GPT-2 and exploit multi-task learning with two auxiliary tasks to preserve table’s structural information.
Outcome:	The proposed model outperforms existing systems on most few-shot settings.

Copied to clipboard

Jiajie Zhang, Yushi Bai, Xin Lv, Wanjun Gu, Danqing Liu, Minhao Zou, Shulin Cao, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li

Question Answering

Challenge:	Current long-context large language models lack citations to support their responses, making verification difficult due to potential hallucinations.
Approach:	They propose to use off-the-shelf LLMs to automatically construct long-context QA instances with precise sentence-level citations and leverage this pipeline to construct a large-scale SFT dataset for LQAC.
Outcome:	The proposed pipeline can generate responses with fine-grained citations on the fly, surpassing existing models including GPT-4o.

SGG-R 3: From Next-Token Prediction to End-to-End Unbiased Scene Graph Generation (2026.findings-acl)

Copied to clipboard

Jiaye Feng, Qixiang Yin, Yuankun Liu, Tong Mo, Weiping Li

EDIS: Entity-Driven Image Search over Multimodal Web Content (2023.emnlp-main)

Challenge:	Existing methods for scene graph generation lack task-specific structured reasoning and sparse, long-tailed relation distributions.
Approach:	They propose a structured reasoning framework that integrates task-specific Chain-of-Thought and reinforcement learning with group sequence policy optimization to achieve unbiased scene graph generation.
Outcome:	The proposed framework achieves superior performance on two benchmarks.

Copied to clipboard

Siqi Liu, Weixi Feng, Tsu-Jui Fu, Wenhu Chen, William Wang

Adaptive Multi-pass Decoder for Neural Machine Translation (D18-1)

Challenge:	Existing image retrieval methods require large datasets and a large candidate set.
Approach:	They propose a news-domain dataset for cross-modal image search with 1 million web images . they propose combining multimodal image-text pairs with a million candidates .
Outcome:	The proposed dataset challenges state-of-the-art methods with dense entities and the large-scale candidate set.

Copied to clipboard

Xinwei Geng, Xiaocheng Feng, Bing Qin, Ting Liu

Dual-Channel Evidence Fusion for Fact Verification over Texts and Tables (2022.naacl-main)

Challenge:	End-to-end neural machine translation (NMT) has attracted increasing attention in recent years.
Approach:	They propose an adaptive multi-pass decoder which introduces a flexible multi- pass polishing mechanism to extend the capacity of NMT via reinforcement learning.
Outcome:	The proposed architecture improves Chinese-English translation with 1.55 BLEU . the proposed architecture adopts a flexible multi-pass polishing mechanism .

Copied to clipboard

Nan Hu, Zirui Wu, Yuxuan Lai, Xiao Liu, Yansong Feng

Fact & Claim Verification

Challenge:	Existing fact extraction and verification tasks only consider evidence of a single format . Existing models convert evidence into either sentences or tables, thus losing context information .
Approach:	They propose a Dual Channel Unified Format fact verification model which unifies various evidence into parallel streams, i.e., natural language sentences and a global evidence table, simultaneously.
Outcome:	The proposed model outperforms existing models in two formats by a large margin . it makes the most of existing tables and tables to absorb evidence of two formats .

SciPedia: Unlocking the Value of Scientific Data for Pre-training (2026.acl-long)

Copied to clipboard

Yiwei Qin, Zhen Huang, Tiantian Mi, Weiye Si, Qipeng Guo, Siyuan Feng, Pengfei Liu

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning (2026.findings-acl)

Challenge:	High-quality scientific data is critical for advancing LLMs, yet academic literature remains underutilized.
Approach:	They construct a large-scale raw scientific corpus but identify a critical Learnability Gap . they develop a multi-stage pipeline featuring content cleaning and pedagogical augmentation .
Outcome:	The proposed approach boosts average performance by +2.12 (3B) and +2.95 (7B) on in-domain tasks.

Copied to clipboard

Wenfeng Feng, Penghong Zhao, Guochao Jiang, Chuzhan Hao, Guohua Liu, Yuewei Zhang

Commonsense Subgraph for Inductive Relation Reasoning with Meta-learning (2025.coling-main)

Challenge:	extending grouping-based methods to agentic reasoning presents unique challenges . frequent environment interactions and tool invocations render intra-group advantage estimation unstable .
Approach:	They propose a grouping-based method that uses a single round of rollouts to stabilize advantage estimation.
Outcome:	a new RL framework outperforms grouping-based methods in retrieval tasks and advanced mathematical reasoning benchmarks.

Copied to clipboard

Feng Zhao, Zhilu Zhang, Cheng Yan, Xianggan Liu

Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics (2026.acl-long)

Challenge:	Existing subgraph-based models focus on predicting missing relations in knowledge graphs . a new meta-learning model extracts concepts from entities to construct commonsense subgraphs based on semantic information .
Approach:	They propose a commonsense subgraph meta-learning model that extracts concepts from entities to construct commonsensible subgraphs.
Outcome:	The proposed model outperforms existing models in inductive reasoning tasks and in few-shot scenarios.

Copied to clipboard

Yilong Chen, Junyuan Shang, Yuchen Feng, Zhenyu Zhang, Naibin Gu, Ziqi Wang, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang

Challenge:	Mixture-of-Experts (MoE) is a cornerstone for scaling LLMs, yet its training dynamics remain poorly understood, often leading to sub-optimal specialization.
Approach:	They propose to use Helmholtz Free Energy and Router Entropy to study the MoE lifecycle and identify a universal Three-Stage Phase Transition .
Outcome:	The proposed model reduces perplexity and improves expert distinctiveness, offering a principled path toward thermodynamically aligned computation.

Exploring End-to-End Differentiable Natural Logic Modeling (2020.coling-main)

Copied to clipboard

Yufei Feng, Zi’ou Zheng, Quan Liu, Michael Greenspan, Xiaodan Zhu

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

Challenge:	Existing approaches to integrate natural logic with neural networks are brittle and prone to fail in the presence of noise and uncertainty.
Approach:	They propose to integrate natural logic with neural networks to create differentiable models that integrate natural reasoning with subsymbolic vector representations and neural components.
Outcome:	The proposed model can model monotonicity-based reasoning, compared to baseline models without inductive bias.

Copied to clipboard

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

SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis (2020.acl-main)

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

Hao Tian, Can Gao, Xinyan Xiao, Hao Liu, Bolei He, Hua Wu, Haifeng Wang, Feng Wu

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

Challenge:	sentiment knowledge is ignored in sentiment analysis, despite its use in pretraining.
Approach:	They propose to use sentiment knowledge to learn a unified sentiment representation for multiple sentiment analysis tasks.
Outcome:	The proposed method outperforms strong pre-training baseline on three kinds of sentiment tasks.

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

FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning (2026.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

Yujie Feng, Hao Wang, Jian Li, Xu Chu, Zhaolu Kang, Yiran Liu, Yasha Wang, Philip S. Yu, Xiao-Ming Wu

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

Challenge:	Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting.
Approach:	They propose a framework that aligns replay schedules with a model-centric notion of time.
Outcome:	Experiments on three benchmarks show that FOREVER consistently mitigates catastrophic forgetting.

Copied to clipboard

Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level (2024.emnlp-main)

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

Zhaopeng Feng, Ruizhe Chen, Yan Zhang, Zijie Meng, Zuozhu Liu

MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation (2022.coling-1)

Challenge:	General-purpose Large Language Models (LLMs) like GPT-4 have exhibited strong translation abilities.
Approach:	They propose to use a model-agnostic model to refine the performance of general-purpose large-language models for machine translation (MT) by utilizing Gemma-2B/7B as the backbone.
Outcome:	The proposed model-agnostic and cost-effective tool improves the performance of general-purpose large-language models for machine translation (MT) by integrating it with any general-use LLM.

Copied to clipboard

Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang

From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM (2025.coling-main)

Challenge:	Existing zero-shot dialogue generation systems rely on large-scale pre-trained language models.
Approach:	They propose a multilingual learning framework for zero-shot dialogue generation that can transfer knowledge from an English corpus to a non-English corpus with zero samples.
Outcome:	The proposed framework can transfer knowledge from an English corpus to a non-English corpus with zero samples.

Copied to clipboard

Jianyu Liu, Yi Huang, Sheng Bi, Junlan Feng, Guilin Qi

Knowledge Representation

Challenge:	Existing methods for generating follow-up questions are limited to shallow contextual questions that are uninspiring and have a large gap to the human level.
Approach:	They propose a three-stage external knowledge-enhanced follow-up question generation method which generates questions by identifying contextual topics, building a knowledge graph online, and finally combining these with a large language model to generate the final question.
Outcome:	The proposed method generates questions by identifying contextual topics, building a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question.

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

Rethinking Task-Specific Knowledge Distillation: Contextualized Corpus as Better Textbook (2022.emnlp-main)

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

Chang Liu, Chongyang Tao, Jianxin Liang, Tao Shen, Jiazhan Feng, Quzhe Huang, Dongyan Zhao

Deep Attention Diffusion Graph Neural Networks for Text Classification (2021.emnlp-main)

Challenge:	Existing methods for knowledge distillation use a two-stage paradigm: general distillation with a task-agnostic general corpus and task-specific distillation using augmented task- specific corpus.
Approach:	They propose a contextualized corpus that contextualizes task corpus with large-scale general corpus through relevance-based text retrieval to improve student learning.
Outcome:	The proposed model improves on the GLUE benchmark and shows that it is better than generalized corpus and augmented task-specific corpus.

Copied to clipboard

Yonghao Liu, Renchu Guan, Fausto Giunchiglia, Yanchun Liang, Xiaoyue Feng

No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discovery (2025.findings-emnlp)

Challenge:	Existing methods for text classification based on graph neural networks (GNNs) consider only one-hop neighborhoods and low-frequency information within texts, which suffer from over-smoothing issues if many graph layers are stacked.
Approach:	They propose a deep attention diffusion Graph Neural Network model to learn text representations by bridging the chasm of interaction difficulties between a word and its distant neighbors.
Outcome:	The proposed model outperforms existing methods on standard benchmark datasets on a set of textual features.

Copied to clipboard

Xiaoxue Han, Pengfei Hu, Chang Lu, Jun-En Ding, Feng Liu, Yue Ning

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

Challenge:	Deep learning models lacking interpretability and interactivity, authors say . lack of interactive mechanisms prevents clinicians from incorporating their own knowledge into decision-making process.
Approach:	a new deep learning model is proposed to improve interpretability and interactivity . authors propose a knowledge-enhanced agent-driven causal discovery framework .
Outcome:	a new model improves interpretability and interactivity on EHR data . the proposed model improve interpretability through explicit reasoning and causal analysis .

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

MT3: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation (2026.acl-long)

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

Zhaopeng Feng, Yupu Liang, Shaosheng Cao, Jiayuan Su, Jiahan Ren, Zhijie Zhou, Wenxuan Huang, Jian Wu, Zuozhu Liu

Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing (2026.acl-industry)

Challenge:	Text Image Machine Translation (TIMT) is a critical subfield of machine translation . it requires accurate optical character recognition, robust visual-text reasoning, and high-quality translation a challenge .
Approach:	They propose a multi-task optimization framework to specialize MLLMs into expert TIMT models.
Outcome:	The proposed model outperforms baselines on the latest in-domain MIT-10M benchmark.

Copied to clipboard

Chao Feng, Zihan Liu, Siddhant Gupta, Jan von der Assen

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

Challenge:	Hardware-in-the-Loop (HIL) testing is essential for automotive validation but suffers from fragmented and underutilized test artifacts.
Approach:	They propose to integrate semantic retrieval with domain-adapted large language models to support test engineers in real-world HIL workflows.
Outcome:	The proposed system improves perceived helpfulness, truthfulness, and satisfaction over general-purpose LLMs.

Copied to clipboard

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

More than Classification: A Unified Framework for Event Temporal Relation Extraction (2023.acl-long)

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

Quzhe Huang, Yutong Hu, Shengqi Zhu, Yansong Feng, Chang Liu, Dongyan Zhao

Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction (2025.findings-acl)

Challenge:	Existing methods for event temporal relation extraction ignore meaning of relations and wipe out their intrinsic dependency.
Approach:	They propose a unified event temporal relation extraction framework that transforms temporal relations into logical expressions of time points and completes the ETRE by predicting the relations between certain time points.
Outcome:	The proposed framework outperforms the state-of-the-art model on TB-Dense and MATRES by 0.3% on both datasets.

Copied to clipboard

Yuting Huang, Chengyuan Liu, Yifeng Feng, Yiquan Wu, Chao Wu, Fei Wu, Kun Kuang

MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation (2025.acl-long)

Challenge:	Existing jailbreak methods create a forced instruction-following scenario, or search adversarial prompts with prefix or suffix tokens to achieve a specific representation manually or automatically.
Approach:	They propose a method that rewrites the original instruction to achieve a jailbreak . they propose rewriting the original instructions to improve the attack strategy .
Outcome:	The proposed method is more efficient and easier to identify since no additional features are introduced.

Copied to clipboard

Haochen Xue, Feilong Tang, Ming Hu, Yexin Liu, Qidong Huang, Yulong Li, Chengzhi Liu, Zhongxing Xu, Chong Zhang, Chun-Mei Feng, Yutong Xie, Imran Razzak, Zongyuan Ge, Jionglong Su, Junjun He, Yu Qiao

Uncertainty-Aware Test-Time Search for Optimization Problem Solving (2026.acl-long)

Challenge:	Existing multimodal large language models lack the ability to memorize, recall, and reason in sustained interactions.
Approach:	They propose a multimodal real-world conversation benchmark for evaluating open-ended abilities of multimodal large language models.
Outcome:	The proposed benchmarks show that the models perform better in open-ended conversations.

Copied to clipboard

Linlin Yu, Xujiang Zhao, Dong Li, Yanchi Liu, Wei Cheng, Zhengzhang Chen, Chen Zhao, Feng Chen, Haifeng Chen

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

Challenge:	Language model hallucinations and limited availability of labeled datasets often result in misaligned formulations, code errors and feasibility failures.
Approach:	They propose a Monte Carlo Tree Search framework that automates optimization problems from natural language descriptions with efficiency and reliability.
Outcome:	The proposed framework achieves state-of-the-art solution accuracy and reduces token usage.

Copied to clipboard

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

Two-Stage Regularization-Based Structured Pruning for LLMs (2026.acl-long)

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

Mingkuan Feng, Jinyang Wu, Siyuan Liu, Shuai Zhang, Hongjian Fang, Ruihan Jin, Feihu Che, Pengpeng Shao, Zhengqi Wen, Jianhua Tao

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

Challenge:	Structural pruning is a promising solution for large language models . prior structured pruning methods remove unimportant parameters based on certain metrics .
Approach:	They propose a structural pruning method that iteratively learns the weights of transformer layers by adding their l1-norm to the loss function.
Outcome:	The proposed pruning method outperforms strong layer-wise pruning methods without requiring retraining.

Copied to clipboard

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

Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge (2025.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

Zhuo Liu, Moxin Li, Xun Deng, Qifan Wang, Fuli Feng

Challenge:	LLM-as-a-Judge uses large language models to evaluate the quality of LLM generated responses, but training proxy judge models using evaluation data generated by powerful teacher models introduces a critical yet previously overlooked issue: teacher preference bias.
Approach:	They propose a new setting that incorporates an additional assistant model, which is not biased toward the teacher model’s responses, to complement the training data.
Outcome:	The proposed model reduces teacher preference bias while maintaining strong performance across six evaluation benchmarks.

A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting (2026.acl-industry)

Copied to clipboard

Yu Lei, Zixuan Wang, Yiqing Feng, Junru Zhang, Yahui Li, Liu Chu, Wang Tongyao, Dongyang Li

Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models (2025.naacl-long)

Challenge:	Recent industrial credit scoring models rely heavily on manually tuned statistical learning methods due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness.
Approach:	They propose a framework that reformulates credit scoring as a multi-scale sequential learning problem.
Outcome:	FinLangNet improves KS and bad debt rate by 6.3 pp in real world deployments.

Copied to clipboard

Ziche Liu, Rui Ke, Yajiao Liu, Feng Jiang, Haizhou Li

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

Challenge:	Existing studies focus on data selection but lack a clear, unified framework . variability in experimental settings complicates systematic comparisons .
Approach:	They propose a three-stage scheme to standardize data selection for fine-tuning large language models . they propose unified comparison approach that incorporates ratio-based efficiency and ranking-based feasibility metrics to address inconsistencies across experiments.
Outcome:	The proposed scheme outperforms existing methods in a dozen key studies and identifies key challenges.

Copied to clipboard

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

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

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

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

SEP-MLDC: A Simple and Effective Paradigm for Multi-Label Document Classification (2025.findings-naacl)

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

Copied to clipboard

Han Liu, Shuqin Li, Xiaotong Zhang, Yuanyuan Wang, Feng Zhang, Hongyang Chen, Hong Yu

Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks (2024.acl-long)

Challenge:	Existing methods focus on optimizing document features, overlooking the potential of high-quality label features to enhance classification performance.
Approach:	They propose a multi-label document classification paradigm that utilizes large language models to expand the label content and generate pseudo-samples for the tail categories.
Outcome:	The proposed method significantly outperforms state-of-the-art models.

Copied to clipboard

Yichen Wang, Shangbin Feng, Abe Hou, Xiao Pu, Chao Shen, Xiaoming Liu, Yulia Tsvetkov, Tianxing He

How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension (2023.findings-acl)

Challenge:	Existing studies on this topic focus on the robustness of specific detectors or particular attack methods.
Approach:	They stress test the detectors’ robustness to malicious attacks under realistic scenarios using LLMs and metric-based detectors.
Outcome:	The proposed methods are based on a set of LLM-based models and their performance is compared under different budget levels.

Copied to clipboard

Chen Zhang, Jiuheng Lin, Xiao Liu, Yuxuan Lai, Yansong Feng, Dongyan Zhao

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)

Challenge:	Despite recent progress in multi-answer MRC, there is no systematic analysis of how this phenomenon arises and how to better address it.
Approach:	They develop a taxonomy to categorize commonly-seen multi-answer MRC instances and examine how well different paradigms deal with different types of multi-announced questions.
Outcome:	The proposed taxonomy categorizes commonly-seen multi-answer instances and analyzes how well different paradigms deal with different types of multi-announced instances.

Copied to clipboard

Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents (2026.acl-long)

Challenge:	Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool.
Approach:	They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images .
Outcome:	The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images.

Copied to clipboard

Xinshun Feng, Xinhao Song, Lijun Li, Gongshen Liu, Jing Shao

CR-LLM: A Dataset and Optimization for Concept Reasoning of Large Language Models (2024.findings-acl)

Challenge:	Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks.
Approach:	They propose a tool-memory based self-evolving agentic framework that integrates planning with execution.
Outcome:	The proposed framework is able to extract explicit knowledge from historical data and leverage inter-trajectory correlations to densify reward signals.

Copied to clipboard

Nianqi Li, Jingping Liu, Sihang Jiang, Haiyun Jiang, Yanghua Xiao, Jiaqing Liang, Zujie Liang, Feng Wei, Jinglei Chen, Zhenghong Hao, Bing Han

A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature (D19-1)

Challenge:	Existing concept reasoning related datasets suffer from modeledge leakage and context leakage.
Approach:	They propose a concept reasoning for large language models with modeledge leakage prevention and context leakage preventive methods to improve the models' conceptual reasoning abilities.
Outcome:	The proposed method significantly improves the existing models and reasoning methods, achieving a 7% increase in accuracy compared to CoT and showing better granularity.

Copied to clipboard

He Zhao, Zhunchen Luo, Chong Feng, Anqing Zheng, Xiaopeng Liu

Text Classification

Challenge:	Existing academic search engines cannot detect relevant papers where a resource is mentioned.
Approach:	They propose a framework to model the role and function of on-line resource citations . they construct a dataset SciRes, which includes 3,088 manually annotated resource contexts based on a multi-task framework .
Outcome:	The proposed model achieves the best results on both the classification task and recommendation task.

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

Copied to clipboard

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

Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness (2025.findings-emnlp)

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

Lingnan Xu, Chong Feng, Kaiyuan Zhang, Liu Zhengyong, Wenqiang Xu, Fanqing Meng

Conditional Dichotomy Quantification via Geometric Embedding (2025.acl-long)

Challenge:	Existing approaches to retrieval-augmented generation ignore valuable structure that is crucial for document organization.
Approach:	They propose a framework that explicitly incorporates structural information throughout the RAG process.
Outcome:	The proposed framework incorporates structural information throughout the RAG process.

Copied to clipboard

Shaobo Cui, Wenqing Liu, Yiyang Feng, Jiawei Zhou, Boi Faltings

Representation Learning

Challenge:	Existing methods that rely on semantic similarity fail to capture the nuanced oppositional dynamics essential for these applications.
Approach:	They propose a task that formalizes the measurement of conditional dichotomy by using a dichotomian framework.
Outcome:	The proposed framework provides carefully constructed datasets covering debate, defeasible inference, and causal reasoning scenarios.

A New Approach to Overgenerating and Scoring Abstractive Summaries (2021.naacl-main)

Copied to clipboard

Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu

MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling (2025.findings-emnlp)

Challenge:	Abstractive summarization is a learning objective to produce system outputs that resemble reference summaries on a word-to-word basis.
Approach:	They propose a two-staged strategy to generate multiple variants of the target summary and score and select admissible ones according to users’ needs.
Outcome:	The proposed approach can achieve state-of-the-art on benchmark summarization datasets.

Copied to clipboard

Zhaopeng Feng, Jiahan Ren, Jiayuan Su, Jiamei Zheng, Hongwei Wang, Zuozhu Liu

PRIM: Towards Practical In-Image Multilingual Machine Translation (2025.emnlp-main)

Challenge:	MT-RewardTree provides a framework for constructing, evaluating, and deploying process reward models in machine translation (MT)
Approach:	They propose a method for automatically generating token-level preference pairs using approximate Monte Carlo Tree Search.
Outcome:	The proposed framework achieves state-of-the-art performance in token-level evaluation and sequence-level analysis.

Copied to clipboard

Yanzhi Tian, Zeming Liu, Zhengyang Liu, Chong Feng, Xin Li, Heyan Huang, Yuhang Guo

Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection (2025.emnlp-main)

Challenge:	Current research on in-image machine translation focuses on synthetic data with simple background, single font, fixed text position, and bilingual translation.
Approach:	They propose an end-to-end model to handle the challenge of practical conditions in PRIM . they annotate a real-world one-line text image with complex background, fonts, diverse text positions .
Outcome:	The proposed model improves translation quality and visual effect compared to other models.

Copied to clipboard

Hong Zhang, Feng Zhao, Ruilin Zhao, Cheng Yan, Kangzheng Liu

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

Challenge:	Existing methods for instruction selection rely on external models or rules, overlooking the intrinsic association between pre-trained model and instruction data.
Approach:	They propose a method that utilizes noise injection to identify the quality of instruction data without relying on external models.
Outcome:	The proposed method outperforms the model trained on the entire dataset and established baselines.

Copied to clipboard

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

Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation (2025.findings-acl)

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

Yingfeng Luo, Tong Zheng, Yongyu Mu, Bei Li, Qinghong Zhang, Yongqi Gao, Ziqiang Xu, Peinan Feng, Xiaoqian Liu, Tong Xiao, JingBo Zhu

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

Challenge:	Recent advances in machine translation have focused on a single pre-trained decoder . encoder-decoder architectures have received relatively little attention in NMT .
Approach:	They propose a method that leverages LLMs as MT encoders and pairs them with lightweight decoders to develop universal translation models.
Outcome:	The proposed method matches or surpasses baselines in terms of translation quality but achieves 75% reduction in memory footprint of the KV cache.

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

DocMEdit: Towards Document-Level Model Editing (2025.findings-acl)

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

Li Zeng, Zeming Liu, Chong Feng, Heyan Huang, Yuhang Guo

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

Challenge:	Existing models only output short phrases or sentences, raising doubts about their practical usability.
Approach:	They propose a dataset focused on document-level model editing that aims to correct errors and outdated knowledge in Large language models (LLMs) they propose to use document-based model editing to improve model capabilities in real-world scenarios.
Outcome:	The proposed model editing task improves model capabilities in real-world scenarios and reduces the cost of retraining.

Copied to clipboard

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

Large Language Model-based Human-Agent Collaboration for Complex Task Solving (2024.findings-emnlp)

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

Xueyang Feng, Zhi-Yuan Chen, Yujia Qin, Yankai Lin, Xu Chen, Zhiyuan Liu, Ji-Rong Wen

TaoType: Predicting Fine-Grained Typing Intent for Faster Search (2026.acl-industry)

Challenge:	Recent advances in large language models have led to the development of LLM-based autonomous agents.
Approach:	They propose a Reinforcement Learning-based Human-Agent Collaboration method which trains a policy model to determine the most opportune stages for human intervention within the task-solving process.
Outcome:	The proposed method improves human-agent collaboration significantly through well-planned, limited human intervention.

Copied to clipboard

Yipeng Yu, Yichen Yuan, Chengxiao Feng, Xu Liu

AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection (2025.acl-long)

Challenge:	Large-scale industrial ranking systems operate under stringent real-time performance requirements.
Approach:	They propose a client-side framework that determines whether a user’s query is complete at each typing . this method leverages client-based typing behavior for real-time early prediction .
Outcome:	The proposed framework achieves offline precision/recall/accuracy of 0.7936/0.8196/0.7742 and decreases online response time by 640.5193.65 milliseconds.

Copied to clipboard

Han Liu, Changya Li, Xiaotong Zhang, Feng Zhang, Fenglong Ma, Wei Wang, Hong Yu

From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems (2025.findings-emnlp)

Challenge:	Increasing number of parameters can be challenging under resource-constrained environments.
Approach:	They propose a parameter-efficient fine-tuning method with fewer parameters and finer granularity that can adaptively select important parameters for each task.
Outcome:	The proposed method can fine-tune important parameters for each task, while maintaining the same weights.

Copied to clipboard

Zekun Zhou, Xiaocheng Feng, Lei Huang, Xiachong Feng, Ziyun Song, Ruihan Chen, Liang Zhao, Weitao Ma, Yuxuan Gu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

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

Challenge:	rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance research.
Approach:	They organize the relevant studies into three main categories: hypothesis formulation, hypothesis validation, and manuscript publication.
Outcome:	The authors summarize the current state of research in three main areas: hypothesis formulation, hypothesis validation, and manuscript publication.

Copied to clipboard

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

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding (2025.acl-srw)

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

Copied to clipboard

Qi Feng, Yihong Liu, Hinrich Schuetze

DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)

Challenge:	Existing curriculum learning approaches rely on manually defined difficulty metrics which may not accurately reflect the model’s own perspective.
Approach:	They propose a self-adaptive curriculum learning paradigm that prioritizes fine-tuning examples based on difficulty scores predicted by pre-trained language models (PLMs) they evaluate four datasets covering binary and multi-class classification tasks.
Outcome:	The proposed model leads to faster convergence and improved performance compared to standard random sampling.

Copied to clipboard

Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao, Zhifang Sui

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

Challenge:	DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination.
Approach:	They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions.
Outcome:	The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models .

Copied to clipboard

Xiaotian Zhang, Ruizhe Chen, Yang Feng, Zuozhu Liu

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

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

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

Continual Dialogue State Tracking via Reason-of-Select Distillation (2024.findings-acl)

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

Yujie Feng, Bo Liu, Xiaoyu Dong, Zexin Lu, Li-Ming Zhan, Xiao-Ming Wu, Albert Lam

RAAMove: A Corpus for Analyzing Moves in Research Article Abstracts (2024.lrec-main)

Challenge:	Existing research on dialogue systems has focused on domain-specific offline systems lacking adaptation abilities.
Approach:	They propose a Reason-of-Select distillation method that enhances smaller models with a novel "meta-reasoning" capability.
Outcome:	Experiments show that the proposed method significantly improves the performance and generalization capabilities of existing models.

Copied to clipboard

Hongzheng Li, Ruojin Wang, Ge Shi, Xing Lv, Lei Lei, Chong Feng, Fang Liu, Jinkun Lin, Yangguang Mei, Linnan Xu

Revealing the Parallel Multilingual Learning within Large Language Models (2024.emnlp-main)

Challenge:	RAAMove is a comprehensive multi-domain corpus dedicated to the annotation of move structures in Research Article (RA) abstracts.
Approach:	They propose a multi-domain corpus dedicated to the annotation of move structures in RA abstracts.
Outcome:	The proposed corpus is based on a human-annotated dataset and a BERT-based model to verify its effectiveness.

Copied to clipboard

Yongyu Mu, Peinan Feng, Zhiquan Cao, Yuzhang Wu, Bei Li, Chenglong Wang, Tong Xiao, Kai Song, Tongran Liu, Chunliang Zhang, JingBo Zhu

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)

Challenge:	Large language models (LLMs) can handle multilingual and cross-lingual text within a single input; however, previous studies focusing on using English as the pivot language to enhance language understanding and reasoning focus on using multiple languages.
Approach:	They propose to use parallel multilingual input to enhance the model's comprehension of the input and to examine how multilingual processing affects prediction.
Outcome:	The proposed model can handle multilingual and cross-lingual text within a single input, but previous studies focused on using English as the pivot language to enhance language understanding and reasoning.

Copied to clipboard

Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu

Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Challenge:	Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints.
Approach:	They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs.
Outcome:	The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications.

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin

Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework (2022.emnlp-main)

Challenge:	Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach:	They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome:	The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.

Copied to clipboard

Yiquan Wu, Yifei Liu, Weiming Lu, Yating Zhang, Jun Feng, Changlong Sun, Fei Wu, Kun Kuang

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

Challenge:	Existing models lack interpretability due to the neglect of rationale in the prediction process.
Approach:	They propose a rationale-based legal judgment prediction framework that follows the judge's real trial logic and provides good interactivity and interpretability.
Outcome:	The proposed framework provides good interactivity and interpretability which enables practical use.

Copied to clipboard

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

Well Begun Is Half Done: An Implicitly Augmented Generative Framework with Distribution Modification for Hierarchical Text Classification (2024.lrec-main)

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

Huawen Feng, Jingsong Yan, Junlong Liu, Junhao Zheng, Qianli Ma

GeAR: Generation Augmented Retrieval (2025.findings-acl)

Challenge:	Hierarchical Text Classification (HTC) is a challenging task which aims to extract the labels in a tree structure corresponding to a given text.
Approach:	They propose an explicit-agmented-generativ-e framework with distribution modification for hierarchical text classification.
Outcome:	The proposed framework improves on the initial distributions of tail classes and avoids misinterpreting predictions on unbalanced data.

Copied to clipboard

Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang

Telling the Whole Story: A Manually Annotated Chinese Dataset for the Analysis of Humor in Jokes (D19-1)

Challenge:	Document retrieval techniques are used to compute semantic similarity between a query and documents, but the scalar similarity fails to reflect enough information, hindering the interpretation of retrieval results.
Approach:	They propose a method which improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.
Outcome:	The proposed method improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.

Copied to clipboard

Dongyu Zhang, Heting Zhang, Xikai Liu, Hongfei Lin, Feng Xia

Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations (2022.coling-1)

Challenge:	Humor plays important role in human communication, which makes it important problem for natural language processing.
Approach:	They propose a novel annotation scheme to give scenarios of how humor arises in text . they report reasonable agreement between annotators and analyze the dataset .
Outcome:	The proposed scheme gives scenarios of how humor arises in text . it contains key words that trigger humor, character relationship, scene, and humor categories .

Copied to clipboard

Jiazhan Feng, Chongyang Tao, Zhen Li, Chang Liu, Tao Shen, Dongyan Zhao

Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)

Challenge:	Recent work on grounding dialogue agents with knowledge documents has sparked increased attention . hand-labeling data to that end is time-consuming and many datasets lack knowledge annotations .
Approach:	They propose a reciprocal learning approach to optimize a knowledge retriever and a response ranker for knowledge-grounded response retrieval without ground-truth knowledge labels.
Outcome:	The proposed model outperforms previous state-of-the-art methods on two public benchmarks.

Copied to clipboard

Yuanxing Liu, Weinan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che

MUSTIE: Multimodal Structural Transformer for Web Information Extraction (2023.acl-long)

Challenge:	E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations .
Approach:	They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues.
Outcome:	The proposed methods can be very effective in some cases, the authors say .

Copied to clipboard

Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Zenglin Xu, Shaoliang Nie, Sinong Wang, Madian Khabsa, Hamed Firooz, Dongfang Liu

CASA: Causality-driven Argument Sufficiency Assessment (2024.naacl-long)

Challenge:	Recent sequential modeling approaches focus on extracting information from textual sources while ignoring rich information from other modalities such as image and web layout.
Approach:	They propose a novel MUltimodal Structural Transformer that integrates multiple modalities for web information extraction.
Outcome:	The proposed model outperforms existing methods on WebSRC and Common Crawl benchmarks.

Copied to clipboard

Xiao Liu, Yansong Feng, Kai-Wei Chang

Challenge:	Existing methods to assess the sufficiency of arguments are laborious and inconsistent due to subjective criteria.
Approach:	They propose a causality-driven argument sufficiency assessment framework that uses the probability of sufficience to estimate the probability that a premise event would lead to a conclusion when both premise and conclusion events are absent.
Outcome:	The proposed framework identifies insufficient arguments and improves them in a writing aid application.

Democratizing Reasoning Ability: Tailored Learning from Large Language Model (2023.emnlp-main)

Copied to clipboard

Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

Aligning Translation-Specific Understanding to General Understanding in Large Language Models (2024.emnlp-main)

Challenge:	Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature.
Approach:	They propose a tailored learning approach to distill the exclusive reasoning ability to smaller LMs to facilitate democratization.
Outcome:	The proposed approach enables the democratization of the exclusive reasoning ability by leveraging the black-box model as a reasoning teacher.

Copied to clipboard

Yichong Huang, Baohang Li, Xiaocheng Feng, Wenshuai Huo, Chengpeng Fu, Ting Liu, Bing Qin

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

Challenge:	Large Language models (LLMs) have remarkable abilities in understanding complex texts . however, understanding misalignment leads to LLMs mistakenly translating complex concepts .
Approach:	They propose a translation process that aligns the translation-specific understanding with the general understanding to improve translation quality and reduce translation literalness.
Outcome:	The proposed translation process improves translation quality and reduces translation literalness by -25% -51%.

Copied to clipboard

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

Multi-stage Pre-training over Simplified Multimodal Pre-training Models (2021.acl-long)

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

Tongtong Liu, Fangxiang Feng, Xiaojie Wang

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

Challenge:	Existing multimodal pre-training models require large amounts of training data and have huge model sizes, making them impossible to apply in low-resource situations.
Approach:	They propose a multi-stage pre-training method which uses information at different granularities from word, phrase to sentence in both texts and images to pre-train a model in stages.
Outcome:	The proposed method outperforms the original model in Image-Text Retrieval task and outperformed the original LXMERT model in 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

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

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

WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)

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

An-Lan Wang, Jingqun Tang, Lei Liao, Hao Feng, Qi Liu, Xiang Fei, Jinghui Lu, Han Wang, Hao Liu, Yuliang Liu, Xiang Bai, Can Huang

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

Challenge:	Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world .
Approach:	They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions.
Outcome:	The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents.

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.

HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy (2024.emnlp-main)

Copied to clipboard

YongKang Liu, Yiqun Zhang, Qian Li, Tong Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schuetze

EvoNarrator: Modeling Scientific Evolution for Feasible Hypothesis Generation (2026.acl-long)

Challenge:	Existing approaches to fine-tuning language models use zeroth-order optimizers to conserve GPU memory.
Approach:	They propose a full-parameter fine-tuning strategy which updates a subset of parameters at each training step.
Outcome:	The proposed approach reduces the amount of gradients and optimizer state parameters residing in GPU memory at the same time, thereby reducing GPU memory usage.

Copied to clipboard

Xiaoying Le, Pengfei Qian, Yuanzhao Zhai, Xu Zhang, Qian Liu, Feng Dawei, Bo Ding

Challenge:	Scientific discovery evolution does not occur ex nihilo but is characterized by structural deepening and reconfiguration of existing functionalities.
Approach:	They propose a framework for hypothesis generation based on evolutionary narratives . they extract structured P-M-L-F quadruples from citation networks and introduce a mechanism to assess their semantic compatibility.
Outcome:	The proposed framework reduces logical disconnects by evaluating its semantic compatibility.

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

Copied to clipboard

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

SAD: A Large-Scale Strategic Argumentative Dialogue Dataset (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

YongKang Liu, Jiayang Yu, Mingyang Wang, Yiqun Zhang, Ercong Nie, Shi Feng, Daling Wang, Kaisong Song, Hinrich Schuetze

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

Challenge:	Argumentation is a key part of human reasoning and decision-making . existing argumentative corpora focus on single-turn settings, but multi-turn dialogues are often realized as multi-turned dialogues .
Approach:	They present a dataset for strategic multi-turn argumentation dialogues . they annotate each utterance with five strategy types, allowing multiple strategies per utterrance .
Outcome:	The proposed dataset shows that explicit prompting improves fluency, stylistic coherence and persuasiveness.

Copied to clipboard

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

A Coarse-to-Fine Prototype Learning Approach for Multi-Label Few-Shot Intent Detection (2024.findings-emnlp)

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

Copied to clipboard

Xiaotong Zhang, Xinyi Li, Feng Zhang, Zhiyi Wei, Junfeng Liu, Han Liu

Low-Resource NLP

Challenge:	Existing methods for few-shot intent detection are limited due to data scarcity and lack of information for unseen domains.
Approach:	They propose to enhance utterance representations with label synset augmentation and refine prototypes by distilling coarse domain knowledge from a universal teacher model.
Outcome:	The proposed approach outperforms existing methods in terms of accuracy and generalization across domains.

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment (2025.emnlp-industry)

Copied to clipboard

Xiaochong Lan, Jie Feng, Yinxing Liu, null Xinleishi, Yong Li

Multi-Granularity Structural Knowledge Distillation for Language Model Compression (2022.acl-long)

Challenge:	Existing methods for assessing review quality are unscalable across domains and fail to adapt to evolving content patterns.
Approach:	They propose an LLM-based agent framework that automates the discovery of interpretable features.
Outcome:	The proposed framework improves on a large-scale online platform with a billion-level user base.

Copied to clipboard

Chang Liu, Chongyang Tao, Jiazhan Feng, Dongyan Zhao

Arxiv Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance (2024.emnlp-demo)

Challenge:	Existing methods to transfer knowledge to a small model are not enough to represent the rich semantics of a text.
Approach:	They propose to distill the knowledge to a student hierarchically across layers using a large teacher-student framework.
Outcome:	Experimental results show that the proposed method outperforms distillation methods on GLUE benchmark.

Copied to clipboard

Guanyu Lin, Tao Feng, Pengrui Han, Ge Liu, Jiaxuan You

ReTraCk: A Flexible and Efficient Framework for Knowledge Base Question Answering (2021.acl-demo)

Challenge:	Existing solutions for document QA fail to provide personalized and up-to-date information efficiently.
Approach:	They propose to deploy a self-evolving, efficient LLM system that can offer personalized research services, maintaining a real-time updated database.
Outcome:	The proposed system saves 69.92% of time after efficient deployment.

Copied to clipboard

Shuang Chen, Qian Liu, Zhiwei Yu, Chin-Yew Lin, Jian-Guang Lou, Feng Jiang

Rethinking Text-based Protein Understanding: Retrieval or LLM? (2025.emnlp-main)

Challenge:	Existing neural semantic parsing methods for knowledge base question answering are lacking . a generic and extensible framework is lacking for KBQA.
Approach:	They propose a neural semantic parsing framework for large scale knowledge base question answering . they propose 'retriever-transducer-checker' framework that provides a retriever and a transducer .
Outcome:	The proposed framework is ranked at top1 overall performance on the GrailQA leaderboard and achieves competitive performance on typical WebQuestionsSP benchmark.

Copied to clipboard

Juntong Wu, Zijing Liu, He Cao, Li Hao, Bin Feng, Zishan Shu, Ke Yu, Li Yuan, Yu Li

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering (2026.acl-long)

Challenge:	Recent studies have focused on integrating protein-related knowledge into large language models through continued pretraining and multi-modal alignment.
Approach:	They propose a retrieval-enhanced method which significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.
Outcome:	The proposed method significantly outperforms fine-tuned LLMs for protein-to-text generation and shows accuracy and efficiency in training-free scenarios.

Copied to clipboard

Yi Fang, Wenjie Wang, Mingfeng Xue, Boyi Deng, Fengli Xu, Dayiheng Liu, Fuli Feng

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

Challenge:	Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs’ hidden states.
Approach:	They propose to decompose strategy-entangled hidden states into a disentangled feature space by using Sparse Autoencoders to identify the few strategy-specific features from the vast pool of SAE features.
Outcome:	The proposed method outperforms existing methods by 15% in control effectiveness.

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

CORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response Selection (2023.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

Chongyang Tao, Jiazhan Feng, Tao Shen, Chang Liu, Juntao Li, Xiubo Geng, Daxin Jiang

MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning (2025.findings-emnlp)

Challenge:	Existing methods to train retrieval-based dialogue systems are suboptimal . existing methods to optimize retrieval and rerank modules are sub-optimal, causing sub-optimum performance.
Approach:	They propose a retrieval-based dialogue system with a fast retriever and a smart response reranker that combine the best of both worlds.
Outcome:	The proposed method can learn from each other and evolve together . it can be used in industrial applications and has powered industrial applications.

Copied to clipboard

Zhaopeng Feng, Shaosheng Cao, Jiahan Ren, Jiayuan Su, Ruizhe Chen, Yan Zhang, Jian Wu, Zuozhu Liu

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

Challenge:	Large-scale reinforcement learning (RL) methods have proven effective in enhancing the reasoning abilities of large language models.
Approach:	They propose an open-source adaptation of the R1-Zero RL framework for machine translation (MT) their code is available at https://github.com/fzp0424/MT-R1-zero.
Outcome:	The proposed framework surpasses towerinstruct-7B-v0.2 on the english-chinese benchmark by 1.26 points.

Copied to clipboard

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

M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)

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

Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu

MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs (2020.acl-main)

Challenge:	Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains.
Approach:	They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs.
Outcome:	The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods.

Copied to clipboard

Jifan Yu, Gan Luo, Tong Xiao, Qingyang Zhong, Yuquan Wang, Wenzheng Feng, Junyi Luo, Chenyu Wang, Lei Hou, Juanzi Li, Zhiyuan Liu, Jie Tang

Evaluating the Tradeoff Between Abstractiveness and Factuality in Abstractive Summarization (2023.findings-eacl)

Challenge:	Massive open online courses (MOOCs) are a popular educational platform for advanced research.
Approach:	They propose to use MOOCCube to build a large-scale data repository of over 700 MOOC courses, 100k concepts, 8 million student behaviors with an external resource.
Outcome:	The proposed datasets show that they can facilitate research in MOOCs.

Copied to clipboard

Markus Dreyer, Mengwen Liu, Feng Nan, Sandeep Atluri, Sujith Ravi

DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection (2022.emnlp-main)

Challenge:	Abstractive summarization models generate fluent and well-formed output but lack semantic faithfulness, or factuality, with respect to the input documents.
Approach:	They propose new factuality metrics that adjust for the degree of abstractiveness . they propose to visualize the rates of change in factual as we gradually increase abstractiveity .
Outcome:	The proposed models generate fluent and well-formed summaries but lack semantic faithfulness, or factuality, with respect to the input documents.

Copied to clipboard

Yongkang Liu, Shi Feng, Wei Gao, Daling Wang, Yifei Zhang

Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis (2021.naacl-main)

Challenge:	Existing retrieval-based dialogue systems suffer from slow inference or huge number of parameters.
Approach:	They propose a lightweight fully convolutional architecture for response selection using convolution.
Outcome:	The proposed architecture extracts matching features of context and response from 3D views.

Copied to clipboard

Xiao Liu, Da Yin, Yansong Feng, Yuting Wu, Dongyan Zhao

Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario (2022.emnlp-main)

Challenge:	Existing studies focus on analyzing structured data, while mining causal relationship among factors from unstructured data is of great importance.
Approach:	They propose a graph-based causal inference framework which builds causal graphs from fact descriptions without much human involvement.
Outcome:	The proposed framework can capture nuance from fact descriptions among confusing charges and provide explainable discrimination in few-shot settings.

Copied to clipboard

Xiao Liu, Yansong Feng, Jizhi Tang, Chengang Hu, Dongyan Zhao

The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code (2023.findings-acl)

Challenge:	Existing models fail to learn and use culinary knowledge in a compositional way, argues a new study.
Approach:	They propose a task that asks models to modify a base recipe according to the change of an ingredient.
Outcome:	The proposed model can perform compositional generalization in a realistic setting . existing models have difficulties in modifying ingredients while preserving original style .

Copied to clipboard

Xiao Liu, Da Yin, Chen Zhang, Yansong Feng, Dongyan Zhao

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

Challenge:	entailment a)
Approach:	entailment : We want to explore whether Code-LLMs with code prompts are better . encoding a code prompt is better than text-only LLMs, they say .
Outcome:	entailment : Our results show that Code-LLMs with code prompts are better compared to text-only LLMs.

Copied to clipboard

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

Trustworthy and Explainable Causal Representation Learning in Transformers (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

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

N-LTP: An Open-source Neural Language Technology Platform for Chinese (2021.emnlp-demo)

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

Wanxiang Che, Yunlong Feng, Libo Qin, Ting Liu

Probing and Boosting Large Language Models Capabilities via Attention Heads (2025.emnlp-main)

Challenge:	Existing tools that teach an independent model for each task are not supported in Chinese.
Approach:	They propose an open-source neural language platform supporting six Chinese NLP tasks . source code, documentation, and pre-trained models are available at https://github.com/hit-SCIR/ltp .
Outcome:	The proposed platform supports six Chinese NLP tasks.

Copied to clipboard

Dezhi Zhao, Xin Liu, Xiaocheng Feng, Hui Wang, Bing Qin

Triviality Corrected Endogenous Reward (2026.acl-long)

Challenge:	Existing approaches to identifying capabilities rely on external signals with limited structural grounding . emergence of specific capabilities remains poorly understood .
Approach:	They propose a lightweight approach that links LLM capabilities to internal components by identifying correspondences at the level of attention heads.
Outcome:	The proposed approach improves accuracy on MMLU and BBH by 1 to 1.5 points over gradient-based method and 5 to 6 points over other intermediate-state baselines.

Copied to clipboard

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

Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning (2023.findings-emnlp)

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

Chang Liu, Chongyang Tao, Jianxin Liang, Jiazhan Feng, Tao Shen, Quzhe Huang, Dongyan Zhao

Recipe2Plan: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions (2025.findings-emnlp)

Challenge:	Existing methods to accelerate inference speed are model compression and dynamic computation (e.g., dynamic token pruning).
Approach:	They propose a two-stage knowledge distillation framework that produces a customized small language model for dynamic token pruning.
Outcome:	The proposed framework can make the small language model more customized for dynamic token pruning and achieve better speed-performance trade-off.

Copied to clipboard

Zirui Wu, Xiao Liu, Jiayi Li, Lingpeng Kong, Yansong Feng

Humans or LLMs as the Judge? A Study on Judgement Bias (2024.emnlp-main)

Challenge:	Existing evaluation benchmarks focus on single task performance, ignoring multitask planning and execution efficiency.
Approach:	They propose a benchmark framework based on real-world cooking scenarios . recipe2plan challenges agents to optimize cooking time through parallel task execution .
Outcome:	The proposed benchmarks highlight the need for improved temporal awareness and global multitasking capabilities in large language models.

Copied to clipboard

Guiming Chen, Shunian Chen, Ziche Liu, Feng Jiang, Benyou Wang

MHGRL: An Effective Representation Learning Model for Electronic Health Records (2024.lrec-main)

Challenge:	Proprietary models such as GPT-4, Claude, Gemini-Pro and others are being democratized to improve evaluations of LLMs.
Approach:	They propose a framework that is free from referencing groundtruth annotations for investigating Misinformation Oversight Bias, Gender Bia,*Authority Bia and Beauty Bia's on LLM and human judges.
Outcome:	The proposed framework investigates Misinformation Oversight Bias, Gender Bia,*Authority Bia and **Beauty Bia' on LLM and human judges.

Copied to clipboard

Feiyan Liu, Liangzhi Li, Xiaoli Wang, Feng Luo, Chang Liu, Jinsong Su, Yiming Qian

DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping (2026.findings-acl)

Challenge:	Effective EHR representations are key to achieving high performance in healthcare applications.
Approach:	They propose a multimodal heterogeneous graph-enhanced representation learning to learn EHR representations using medical ontology and textual notes.
Outcome:	The proposed model outperforms baseline models on two real clinical datasets in downstream tasks.

Copied to clipboard

Wei Fan, Wenlin Yao, Zheng Li, Feng Yao, Xin Liu, Liang Qiu, Qingyu Yin, Yangqiu Song, Bing Yin

Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning (2026.findings-acl)

Challenge:	Existing approaches to planning involve implicit planning or introduce explicit planners without systematically optimizing the planning stage.
Approach:	They propose an end-to-end RL framework that enhances the planning capabilities of deep research agents.
Outcome:	Experiments show that DeepPlanner improves planning quality and achieves state-of-the-art results under a lower training budget.

Copied to clipboard

Heng Yu, Rui Li, Qi Liu, Wenjun Feng, Junfeng Kang, Yi Zhan

Can Graph Descriptive Order Affect Solving Graph Problems with LLMs? (2025.acl-long)

Challenge:	Existing methods for retrieval-augmented generation fail to provide explicit supervision for internal reasoning process.
Approach:	They propose an Evaluation-driven Retrieval-Augmented Reasoning framework that uses reinforcement learning and a fine-grained evaluation reward to optimize the process.
Outcome:	Eval-RAR outperforms existing methods on QA benchmarks on seven single-hop and multi-hop tasks.

Copied to clipboard

Yuyao Ge, Shenghua Liu, Baolong Bi, Yiwei Wang, Lingrui Mei, Wenjie Feng, Lizhe Chen, Xueqi Cheng

Transformation of Dense and Sparse Text Representations (2020.coling-main)

Challenge:	Large language models (LLMs) have achieved significant success in reasoning tasks, including mathematical reasoning and logical deduction.
Approach:	They conduct the first comprehensive analysis of how the order of graph descriptions impacts LLM performance.
Outcome:	The results show that graph descriptions significantly improve LLMs’ comprehension of graph structures, and the robustness of LLM models to graph description order varies across different tasks.

Copied to clipboard

Wenpeng Hu, Mengyu Wang, Bing Liu, Feng Ji, Jinwen Ma, Dongyan Zhao

How to Represent Context Better? An Empirical Study on Context Modeling for Multi-turn Response Selection (2022.findings-emnlp)

Challenge:	Existing approaches to NLP to leverage sparsity have been limited due to the gap with dense representations.
Approach:	They propose a Semantic Transformation method to bridge dense and sparse spaces and propose supervised NLP tasks to use both spaces.
Outcome:	Experiments with classification tasks and natural language inference tasks show that the proposed method is effective.

Copied to clipboard

Jiazhan Feng, Chongyang Tao, Chang Liu, Rui Yan, Dongyan Zhao

SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget (2024.acl-long)

Challenge:	Existing work on building a conversational system for open domain human-machine conversation is attracting more attention . early models concatenate all utterances or independently encode each dialogue turn, which may lead to an inadequate understanding of dialogue status.
Approach:	They propose to use a turn-aware context modeling layer to adapt existing models . they propose to model multi-turn contexts from the perspective of sequential relationship, local relationship, and query-alike manner .
Outcome:	The proposed method can be adapted to several advanced response selection models.

Copied to clipboard

Rui Kong, Yuanchun Li, Qingtian Feng, Weijun Wang, Xiaozhou Ye, Ye Ouyang, Linghe Kong, Yunxin Liu

Joint Constrained Learning with Boundary-adjusting for Emotion-Cause Pair Extraction (2023.acl-long)

Challenge:	Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) but memory-constrained devices are a major concern in edge AI training and serving.
Approach:	They propose a framework for efficient serving of MoE-based large language models with tunable memory budgets.
Outcome:	Experiments show that SwapMoE can reduce memory consumption while maintaining reasonable accuracy.

Copied to clipboard

Huawen Feng, Junlong Liu, Junhao Zheng, Haibin Chen, Xichen Shang, Qianli Ma

Large Language Models Are Cross-Lingual Knowledge-Free Reasoners (2025.naacl-long)

Challenge:	Emotion-Cause Pair Extraction (ECPE) aims to identify the document’s emotion clauses and corresponding cause clauses.
Approach:	They propose a constrained learning framework with boundary-adjusting for Emotion-Cause Pair Extraction that summarizes prior rules and forces the model to take them into consideration in optimization.
Outcome:	The proposed framework achieves competitive results compared with state-of-the-art methods on unbalanced data and proves robustness on unbalancing data.

Copied to clipboard

Peng Hu, Sizhe Liu, Changjiang Gao, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

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

Challenge:	Large language models have demonstrated impressive reasoning capabilities across multiple languages, but the relationship between capabilities in different languages is less explored.
Approach:	They decompose the process of reasoning tasks into two separate components: knowledge retrieval and knowledge-free reasoning.
Outcome:	The proposed model can be transferred across source-target languages despite secondary impact of resource in some specific target languages, while cross-lingual knowledge retrieval significantly hinders the transfer.

Copied to clipboard

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

Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset (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

Qian Chen, Xianyin Zhang, Yanzhi Liu, Lifan Guo, Feng Chen, Chi Zhang

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

Challenge:	Large Vision-Language Models (LVLMs) have expanded capabilities beyond text understanding . a novel Chinese financial multimodal evaluation benchmark is used to evaluate LVLM capabilities .
Approach:	They propose a Chinese financial multimodal evaluation benchmark to evaluate LVLMs' capabilities . the model has an overall accuracy of 66.11% and an average score of 77.18 .
Outcome:	The proposed model achieves an overall accuracy of 66.11% on the question answering task and an average score of 77.18 on detection, recognition, and information extraction tasks.

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

Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

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

Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Challenge:	Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach:	They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome:	The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.

RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive Learning (2022.emnlp-main)

Copied to clipboard

Yi Zhu, Zhaoqing Zhu, Bingqian Lin, Xiaodan Liang, Feng Zhao, Jianzhuang Liu

Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books (2025.acl-long)

Challenge:	Existing visual relationship detection models only use numeric ids of relation labels for training, but ignore semantic correlation between labels.
Approach:	They propose a visual Relationship prediction framework that transfers natural language knowledge from Contrastive Language-Image Pre-training models to enhance the relationship prediction.
Outcome:	The proposed framework improves visual relationship prediction by matching semantic correlations with relation triplets.

Copied to clipboard

Chen Zhang, Jiuheng Lin, Xiao Liu, Zekai Zhang, Yansong Feng

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues (2022.acl-long)

Challenge:	Using code rules improves rule retrieval and application of grammar books in low-resource languages.
Approach:	They propose to decompose a grammar rule retrieval and application step into two steps . they propose to represent grammar rules as code functions to facilitate LLM reasoning .
Outcome:	The proposed model significantly boosts rule retrieval and application, resulting in 13.1% BLEU improvement.

Copied to clipboard

Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei, Weidong Zhan, Baobao Chang, Sujian Li, Tianyu Liu, Zhifang Sui

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration (2024.emnlp-main)

Challenge:	Existing work in vision language cross-modal reasoning uses binary or multi-choice classification based on source image and textual query.
Approach:	They propose a task where a textual premise is the background presumption on each source image.
Outcome:	The proposed task is based on a dataset of 15,360 movie screenshots and human-curated premise templates from 6 pre-defined categories.

Copied to clipboard

Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher, Chan Young Park, Yejin Choi, Yulia Tsvetkov

Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation (2022.acl-long)

Challenge:	Existing alignment paradigms for large language models learn an averaged human preference and struggle to model diverse preferences across cultures, demographics, and communities.
Approach:	They propose a modular framework that "plugs" into a base LLM a pool of smaller but specialized community LMs where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional.
Outcome:	The proposed framework “plugs into” a base LLM a pool of smaller but specialized community LMs, where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional.

Copied to clipboard

Mingzhe Li, XieXiong Lin, Xiuying Chen, Jinxiong Chang, Qishen Zhang, Feng Wang, Taifeng Wang, Zhongyi Liu, Wei Chu, Dongyan Zhao, Rui Yan

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

Challenge:	Existing studies focus on contrastive learning on the instance level without discriminating the contribution of each word.
Approach:	They propose a hierarchical contrastive learning mechanism which can unify semantic meaning in the input text.
Outcome:	The proposed model outperforms baselines on storytelling, paraphrasing, dialogue generation, and storytelling tasks.

Copied to clipboard

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

‘No’ Matters: Out-of-Distribution Detection in Multimodality Multi-Turn Interactive Dialogue Download PDF (2025.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

Rena Wei Gao, Xuetong Wu, Siwen Luo, Caren Han, Feng Liu

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

Challenge:	Out-of-distribution (OOD) detection is essential for multimodal learning systems . a novel scoring framework is proposed to efficiently detect OOD in multi-round long dialogues .
Approach:	They propose a scoring framework that integrates visual language models with a score framework that detects OOD in two key scenarios.
Outcome:	The proposed framework detects OOD in two key scenarios: mismatches between dialogue and image input pair and previously unseen labels.

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

Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction (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

Yuhao Feng, Yanghui Rao, Yuyao Tang, Ninghua Wang, He Liu

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

Challenge:	Recent studies on ABSA focus on Target-oriented Opinion Words (or Terms) Extraction . Experimental results indicate that TSMSA outperforms the benchmark methods on TOWE significantly .
Approach:	They propose to use a pre-trained language model with multi-head self-attention to integrate TOWE with AOPE to extract aspects and opinion terms in pairs.
Outcome:	The proposed structure outperforms the benchmark methods on TOWE significantly . the proposed structure is similar or even better than state-of-the-art AOPE models .

Copied to clipboard

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

Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations (2023.findings-emnlp)

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

Chengpeng Fu, Xiaocheng Feng, Yichong Huang, Wenshuai Huo, Hui Wang, Bing Qin, Ting Liu

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)

Challenge:	Unsupervised neural machine translation methods have been observed to make particular errors in comparison to supervised machine translation, such as confusing nouns that pertain to the same semantic category.
Approach:	They propose a method that incorporates images at the word level to augment lexical mappings.
Outcome:	Experiments on a multi-lingual dataset show that the proposed method generates more accurate translations with only monolingual data.

Copied to clipboard

Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang

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

Challenge:	Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context.
Approach:	They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts.
Outcome:	The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context.

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

Neighborhood Matching Network for Entity Alignment (2020.acl-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

Yuting Wu, Xiao Liu, Yansong Feng, Zheng Wang, Dongyan Zhao

CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher (2026.acl-long)

Challenge:	Structural heterogeneity between knowledge graphs is an outstanding challenge for entity alignment.
Approach:	They propose a framework for entity alignment that uses a neighborhood matching module to combine neighborhood differences.
Outcome:	The proposed framework outperforms existing methods on three datasets.

Copied to clipboard

Tianlun Liu, Zhiliang Tian, Zhen Huang, Xingzhi Zhou, Wanlong Yu, Tianle Liu, Feng Liu, Dongsheng Li

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Challenge:	Existing models for text understanding fail to adapt to domain shifts in real-world applications . current models do not improve themselves as they are applied to new domains .
Approach:	They propose a continual test-time adaptation framework that adapts to evolving domains . they propose accumulating domains and a refine-then-filter framework to calibrate teacher predictions .
Outcome:	The proposed model excels in a teacher-student framework adaptable to evolving domains.

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

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

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

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

Improving Factual Consistency of News Summarization by Contrastive Preference Optimization (2024.findings-emnlp)

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

Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, Qianli Ma

P3Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models (2024.naacl-long)

Challenge:	Recent advances in news summarization have created problems with “hallucinations” that are factually inconsistent with the source text.
Approach:	They propose to disentangle LLMs’ propensities to generate faithful and fake content by adopting a probing-based specific training method to improve their capacity of distinguishing two types of propensity.
Outcome:	The proposed method disentangles LLMs’ propensities to generate faithful and fake content and improves their ability to distinguish between two types of propensity.

Copied to clipboard

Yuhan Liu, Shangbin Feng, Xiaochuang Han, Vidhisha Balachandran, Chan Young Park, Sachin Kumar, Yulia Tsvetkov

StereoRel: Relational Triple Extraction from a Stereoscopic Perspective (2021.acl-long)

Challenge:	Existing summarization systems alter the political opinions and stances of news articles in more than 50% of summaries, misrepresenting the intent and perspectives of the authors.
Approach:	They propose a model-based summarization approach controlled by political perspective classifiers that preserves the political stance of a generated summary.
Outcome:	The proposed model outperforms state-of-the-art summarization systems and large language models by up to 13.7% in terms of success rate of stance preservation, with competitive performance on standard metrics of summarizing quality.

Copied to clipboard

Xuetao Tian, Liping Jing, Lu He, Feng Liu

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing methods for relational triple extraction still face challenges, including information loss and error propagation.
Approach:	They propose a model which maps relational triples to a three-dimensional space and leverages three decoders to extract them.
Outcome:	The proposed model outperforms the baselines on five public datasets.

Copied to clipboard

Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang

CoV: Chain-of-View Prompting for Spatial Reasoning (2026.findings-acl)

Challenge:	Existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents.
Approach:	They propose a framework that explicitly injects discourse signals into the generation process.
Outcome:	Experiments on question answering and long-document summarization benchmarks show the efficacy of the proposed framework.

Copied to clipboard

Haoyu Zhao, Akide Liu, Zeyu Zhang, Weijie Wang, Feng Chen, Ruihan Zhu, Gholamreza Haffari, Bohan Zhuang

Low-Resource NLP

Challenge:	Embodied question answering requires collecting context that is distributed across multiple viewpoints . most recent vision–language models (VLMs) are constrained to a fixed and finite set of input views .
Approach:	They propose a training-free, test-time reasoning framework that transforms a VLM into an active viewpoint reasoner through a coarse-to-fine exploration process.
Outcome:	The proposed framework improves LLM-Match performance by 11.98% on four mainstream VLMs.

The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation (2023.findings-acl)

Copied to clipboard

Hao Peng, Xiaozhi Wang, Feng Yao, Kaisheng Zeng, Lei Hou, Juanzi Li, Zhiyuan Liu, Weixing Shen

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

Challenge:	Event extraction (EE) is a fundamental information extraction task aimed at extracting events from plain texts.
Approach:	They propose to specify data preprocessing, standardize outputs, and provide pipeline evaluation results to avoid these pitfalls.
Outcome:	The results show that the evaluations are reliable and lack pipeline evaluations.

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 .

Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding (2025.findings-acl)

Copied to clipboard

Tuo Zhang, Tiantian Feng, Yibin Ni, Mengqin Cao, Ruying Liu, Kiana Avestimehr, Katharine Butler, Yanjun Weng, Mi Zhang, Shrikanth Narayanan, Salman Avestimehr

Towards LLM-driven Dialogue State Tracking (2023.emnlp-main)

Challenge:	a new study examines the performance of large vision-language models in understanding art . the Pun Rebus Art Dataset is a multimodal dataset for art understanding rooted in traditional Chinese culture .
Approach:	They propose a multimodal dataset for art understanding deeply rooted in traditional Chinese culture . they aim to facilitate the development of VLMs that can better understand culturally specific content .
Outcome:	The proposed dataset shows that state-of-the-art VLMs struggle with these tasks . the data will facilitate the development of VLM models that can better understand culturally specific content .

Copied to clipboard

Yujie Feng, Zexin Lu, Bo Liu, Liming Zhan, Xiao-Ming Wu

Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time) (D19-1)

Challenge:	emergence of large language models (LLMs) such as GPT3 and ChatGPT has sparked considerable interest in assessing their efficacy across diverse applications.
Approach:	They present a framework for a domain-slot instruction tuning method that allows LDST to achieve performance on par with ChatGPT.
Outcome:	The proposed framework performs better in zero-shot and few-shot settings than previous SOTA methods.

Copied to clipboard

Heng Gong, Xiaocheng Feng, Bing Qin, Ting Liu

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

Challenge:	Seq2Seq models for table-to-text generation have achieved remarkable progress, but modeling table representation in one dimension is inadequate.
Approach:	They propose to model each table cell considering other records in the same row and to enrich table’s representation by modeling each cell in context of other cells in the similar column or with historical data respectively.
Outcome:	The proposed model outperforms baseline and state-of-the-art models on ROTOWIRE, a benchmark dataset of NBA basketball games.

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

Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering (2022.naacl-main)

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

Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Zhifan Feng, Yajuan Lyu, Hong Liu, Yong Zhu

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

Challenge:	Existing video QA models lack the capacity for deep video understanding and flexible multistep reasoning.
Approach:	They propose a video question answering model which performs dynamic multistep reasoning between questions and videos.
Outcome:	The proposed model improves on three widely used video QA datasets and displays better interpretability by backtracing along with the attention mechanisms to the video scene graphs.

Copied to clipboard

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

Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search (2026.findings-acl)

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

Chuzhan Hao, Wenfeng Feng, Guochao Jiang, Guofeng Quan, Guohua Liu, Yuewei Zhang

PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs (2024.findings-acl)

Challenge:	Existing RL-based search agents rely on stochastic exploration, leading to inefficient reasoning trajectories and unstable training.
Approach:	They propose a framework to enhance the performance and training stability of search agents by transforming raw reasoning trajectories into hierarchical experience knowledge.
Outcome:	The proposed framework exhibits strong cross-task and cross-algorithm generalizations on multiple complex agentic search and mathematical reasoning benchmarks.

Copied to clipboard

Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Haorui Wang, Zhen Qin, Feng Han, Jialu Liu, Simon Baumgartner, Michael Bendersky, Chao Zhang

Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference (2023.acl-long)

Challenge:	Knowledge distillation (KD) is a technique for transferring expertise from large teacher models to compact student models with reduced memory footprints and inference costs.
Approach:	They propose to transfer knowledge from large teacher models to compact student models by exploiting teacher-student capacity discrepancies to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.
Outcome:	The proposed framework exploits teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.

Copied to clipboard

Junhao Zheng, Qianli Ma, Shengjie Qiu, Yue Wu, Peitian Ma, Junlong Liu, Huawen Feng, Xichen Shang, Haibin Chen

CodeBERT: A Pre-Trained Model for Programming and Natural Languages (2020.findings-emnlp)

Challenge:	Existing studies attribute catastrophic forgetting to fine-tuning, and they retain pre-trained knowledge indiscriminately without identifying what knowledge is transferable.
Approach:	They propose a unified objective for fine-tuning to retrieve the causality back from pre-trained data and use it to mitigate negative transfer while preserving knowledge.
Outcome:	The proposed method outperforms state-of-the-art fine-tuning methods on commonsense QA datasets and can be implemented as a plug-in module to inflate the performance of existing QA models.

Copied to clipboard

Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, Ming Zhou

Semantic Parsing with Syntax- and Table-Aware SQL Generation (P18-1)

Challenge:	Large pre-trained models have improved performance on a variety of natural language processing tasks.
Approach:	They develop a bimodal pre-trained model for programming language (PL) and natural language (NL) it incorporates a hybrid objective function that detects replaced tokens from generators.
Outcome:	The proposed model performs better on two NL-PL applications by fine-tuning model parameters.

Copied to clipboard

Yibo Sun, Duyu Tang, Nan Duan, Jianshu Ji, Guihong Cao, Xiaocheng Feng, Bing Qin, Ting Liu, Ming Zhou

Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP (2024.findings-emnlp)

Challenge:	Existing approaches generate a SQL query word-by-word but results are incorrect or not executable due to mismatch between question words and table contents.
Approach:	They propose a generative model to map natural language questions into SQL queries.
Outcome:	The proposed model significantly improves state-of-the-art execution accuracy from 69.0% to 74.4% on a large question- SQL dataset.

Copied to clipboard

Zeliang Zhang, Zhuo Liu, Mingqian Feng, Chenliang Xu

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

Challenge:	Despite its versatility, CLIP-based applications often suffer from misunderstandings regarding user intent, leading to discrepancies between the required number of objects and the actual outputs.
Approach:	They empirically evaluate CLIP’s understanding of quantity from text, image, and cross-modal perspectives by carefully designing different experimental settings and datasets.
Outcome:	The proposed model has shown significant success in various downstream tasks, including editing, generation, and quality evaluation.

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

Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification (2021.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

Xuepeng Wang, Li Zhao, Bing Liu, Tao Chen, Feng Zhang, Di Wang

Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark (2024.lrec-main)

Challenge:	Existing methods for hierarchical text classification focus on modeling the text, but the concept of sharing among classes has been ignored in previous work.
Approach:	They propose a concept-based method that explicitly represents the concept and model the sharing mechanism among classes for the hierarchical text classification.
Outcome:	The proposed method outperforms state-of-the-art methods on two widely used datasets.

Copied to clipboard

Feng Jiang, Weihao Liu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Haizhou Li

APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models (2023.emnlp-main)

Challenge:	Compared with sentence-level topic structure, paragraph-level topics can grasp and understand the context of a document from a higher level.
Approach:	They propose a hierarchical paragraph-level topic structure representation with three layers to guide corpus construction.
Outcome:	The proposed method achieves the largest Chinese paragraph-level topic structure corpus, achieving high quality.

Copied to clipboard

Qifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu, Shaoliang Nie, Sinong Wang, Fuli Feng, Lifu Huang, Xiaojun Quan, Zenglin Xu, Dongfang Liu

Length Controlled Generation for Black-box LLMs (2025.acl-long)

Challenge:	Existing prompt tuning methods only introduce prompts at the input layer, limiting performance and leaving large room for improvement.
Approach:	They propose a method that involves tuning a small set of soft prompts for pre-trained language models.
Outcome:	The proposed method outperforms state-of-the-art methods with pre-trained models on the SuperGLUE benchmark.

Copied to clipboard

Yuxuan Gu, Wenjie Wang, Xiaocheng Feng, Weihong Zhong, Kun Zhu, Lei Huang, Ting Liu, Bing Qin, Tat-Seng Chua

HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning (2025.findings-acl)

Challenge:	Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use.
Approach:	They propose an iterative sampling framework that regulates LLMs to generate length-constrained text without modifying the underlying parameters.
Outcome:	The proposed method achieves 100% success rates on Llama3.1 tasks with minimal additional computational overhead.

Copied to clipboard

Xiaoyuan Li, Moxin Li, Rui Men, Yichang Zhang, Keqin Bao, Wenjie Wang, Fuli Feng, Dayiheng Liu, Junyang Lin

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

Challenge:	Existing studies show that large language models are robust in commonsense reasoning . however, some variations in questions can lead to incorrect responses .
Approach:	They propose a large-scale bilingual benchmark consisting of 11,200 cases . they conduct extensive experiments on 41 representative LLMs .
Outcome:	The proposed benchmark systematically evaluates the robustness of large language models in commonsense reasoning.

Copied to clipboard

Shuhao Gu, Yang Feng, Qun Liu

MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation (2026.acl-long)

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

Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu

DPDV: Dual-Pathway and Dual-View Representation Learning for Bridging Information Asymmetry in Text-Video Retrieval (2026.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks.
Approach:	They propose to use a multi-turn reasoning evaluation framework to cover multi-turn interactions with the environments of large language models.
Outcome:	The proposed framework covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions with the environments.

Copied to clipboard

Zequn Xie, Xin Liu, Fangming Feng, Boyun Zhang, Tao Jin

Visual Data in NLP

Challenge:	Existing methods for text-based person anomaly search fail to address the pose-semantic gap . asymmetric cross-modal information poses a challenge to accurately establishing retrieval relationships .
Approach:	They propose a video retrieval framework that partitions visual features into two categories based on relevance to the text query and performs effective interaction.
Outcome:	The proposed framework achieves leading retrieval performance on five benchmark datasets.

Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis (2024.emnlp-main)

Copied to clipboard

Yanjiang Chen, Kai Zhang, Feng Hu, Xianquan Wang, Ruikang Li, Qi Liu

Sentiment Analysis

Challenge:	Existing methods for predicting sentiment polarity of aspects are susceptible to interference caused by irrelevant contexts and lack sentiment knowledge at a data-specific level.
Approach:	They propose a novel Aspect-based sentiment analysis method that leverages attention scores to model the relationships between aspects and contexts.
Outcome:	The proposed method is able to predict sentiments from a set of five benchmark datasets.

TVQACML: Benchmarking Text-Centric Visual Question Answering in Multilingual Chinese Minority Languages (2025.emnlp-main)

Copied to clipboard

Sha Jiu, Yu Weng, Mengxiao Zhu, Chong Feng, Zheng Liu, null Jialedongzhu

How Well Do Text Embedding Models Understand Syntax? (2023.findings-emnlp)

Challenge:	Existing TEC-VQA benchmarks focus on high-resource languages like English and Chinese . existing benchmarks have a "visual-textual misalignment" problem resulting in unreliable evaluation results .
Approach:	They propose a benchmark that expands multilingual QA pairs in non-text-centric datasets through translation to eight languages, including Standard Chinese, Korean, and six minority languages.
Outcome:	The proposed benchmarks are contamination-free and more challenging . they include eight languages including Chinese, Korean, and six minority languages .

Copied to clipboard

Yan Zhang, Zhaopeng Feng, Zhiyang Teng, Zuozhu Liu, Haizhou Li

Representation Learning

Challenge:	Existing text embedding models have not addressed syntactic understanding challenges, highlighting ineffectiveness and enhancing generalization ability.
Approach:	They propose to examine the ability of text embedding models to generalize across syntactic contexts.
Outcome:	The proposed models exhibit high similarity socres at this simple task.

CEAN: Contrastive Event Aggregation Network with LLM-based Augmentation for Event Extraction (2024.eacl-long)

Copied to clipboard

Zihao Meng, Tao Liu, Heng Zhang, Kai Feng, Peng Zhao

LEVEN: A Large-Scale Chinese Legal Event Detection Dataset (2022.findings-acl)

Challenge:	Event Extraction is a crucial yet arduous task in natural language processing (NLP), as its performance is hindered by laborious data annotation.
Approach:	They propose a Contrastive Event Aggregation Network with LLM-based Augmentation to promote low-resource learning and reduce data noise for event extraction.
Outcome:	The proposed approach achieves new state-of-the-art results on the ACE2005 and ERE-EN datasets.

Copied to clipboard

Feng Yao, Chaojun Xiao, Xiaozhi Wang, Zhiyuan Liu, Lei Hou, Cunchao Tu, Juanzi Li, Yun Liu, Weixing Shen, Maosong Sun

Document-level Relationship Extraction by Bidirectional Constraints of Beta Rules (2023.emnlp-main)

Challenge:	Existing legal event detection datasets only cover incomprehensive event types and have limited annotated data.
Approach:	They present a large-scale Chinese legal event detection dataset . they use legal events as side information to promote downstream applications .
Outcome:	The proposed method improves 2.2 points precision in low-resource judgment prediction and 1.5 points precision for unsupervised case retrieval.

Copied to clipboard

Yichun Liu, Zizhong Zhu, Xiaowang Zhang, Zhiyong Feng, Daoqi Chen, Yaxin Li

VIEWS: Entity-Aware News Video Captioning (2024.emnlp-main)

Challenge:	Document-level Relation Extraction (DocRE) aims to extract relations among entity pairs in documents.
Approach:	They propose a logic constraint framework that uses bidirectional constraints to model rules by beta contribtion and reconstruct rule consistency loss by bidirectional constraint.
Outcome:	The proposed framework outperforms existing models in relation extraction performance and logical consistency.

Copied to clipboard

Hammad Ayyubi, Tianqi Liu, Arsha Nagrani, Xudong Lin, Mingda Zhang, Anurag Arnab, Feng Han, Yukun Zhu, Xuande Feng, Kevin Zhang, Jialu Liu, Shih-Fu Chang

Visual Data in NLP

Challenge:	Existing video captioning benchmarks and models produce generic captions for videos that lack specific identification of individuals, locations, or organizations.
Approach:	They propose a task of directly summarizing news videos into captions that are entity-aware . they validate the effectiveness of their approach across three video captioning models .
Outcome:	The proposed approach is effective across three video captioning models.

UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction (2021.findings-acl)

Copied to clipboard

Huanqin Wu, Wei Liu, Lei Li, Dan Nie, Tao Chen, Feng Zhang, Di Wang

SSMLoRA: Enhancing Low-Rank Adaptation with State Space Model (2025.naacl-long)

Challenge:	Mainstream methods that ignore the diversity among keyphrases or weakly capture the relation between tasks implicitly ignore keyphrase diversity.
Approach:	They propose a novel end-to-end learning framework that jointly learns to extract and generate keyphrases by exploiting latent semantic relation between extraction and generation.
Outcome:	The proposed approach outperforms mainstream methods on a benchmarked document on keyphrase prediction.

Copied to clipboard

Jiayang Yu, Yihang Zhang, Bin Wang, Peiqin Lin, YongKang Liu, Shi Feng

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

Challenge:	Fine-tuning requires substantial computational resources and is prone to overfitting when applied to small datasets.
Approach:	They propose a parameter-efficient fine-tuning method that integrates a State Space Model (SSM) to interconnect low-rank matrices.
Outcome:	The proposed method achieves comparable performance to LoRA on the general language understanding evaluation (GLUE) benchmark while using only half the parameters.

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

HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing (2026.findings-acl)

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

Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding, Pengyu Zhao, Yanghua Xiao

ViLBench: A Suite for Vision-Language Process Reward Modeling (2025.emnlp-main)

Challenge:	Existing models for LLM role-playing lack high-quality datasets with explicit reasoning traces and reliable reward signals aligned with human preferences.
Approach:	They propose a unified framework for cognitive-level persona simulation that strictly distinguishes characters’ first-person thinking processes from LLMs’ third-person reasoning.
Outcome:	The proposed framework outperforms the Qwen3-32B baseline model and achieves a 30.26% and 14.97% performance on the minimax benchmarks.

Copied to clipboard

Haoqin Tu, Weitao Feng, Hardy Chen, Hui Liu, Xianfeng Tang, Cihang Xie

An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling (2021.findings-emnlp)

Challenge:	Despite its advantages, evaluation on PRMs remains less explored, especially in the multimodal domain.
Approach:	They propose to benchmark vision large language models as output reward models and process reward models as process-supervised reward models.
Outcome:	The proposed model outperforms both ORM and PRM on vision-language benchmarks and achieves an average improvement of 3.3% over standard CoT and up to 2.5% over its untrained counterpart on ViLBench.

Copied to clipboard

Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Xianchao Zhang

ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models (2024.acl-long)

Challenge:	Intent classification and slot filling are key building blocks in task-oriented dialogue systems.
Approach:	They propose an explicit-joint and supervised-contrastive learning framework for few-shot intent classification and slot filling.
Outcome:	The proposed model extracts intent and slot representations via bidirectional interactions and extends prototypical network to achieve explicit-joint learning.

Copied to clipboard

Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model (2025.emnlp-main)

Challenge:	Existing evaluation methods for large language models are labor-intensive and lack efficiency.
Approach:	They propose a framework dedicated to assessing long-text generation that includes in-depth human-curated meta-questions spanning various domains . they use a set of proxy-quests with pre-annotated answers to assess the content's quality by incorporating the generated texts as contextual background.
Outcome:	The proposed framework assesses the quality of long-text content by matching it with references through human evaluation or automated metrics.

Copied to clipboard

Zhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen, Ning Liu, Zhiyuan Xu, Weibin Meng, Yaxin Peng, Chaomin Shen, Feifei Feng, Yi Xu

From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models (2023.acl-long)

Challenge:	Recent advances in vision-language-action models prioritize robotic action mastery . however, models trained on visual-text pairs struggle to interpret multimodal data .
Approach:	They propose a framework that integrates multimodal data after initial control mastery and a Mixture-of-Experts architecture to minimize task interference.
Outcome:	The proposed framework surpasses state-of-the-art vision-language-action (VLA) methods on multimodal understanding benchmarks and achieves six times higher performance on visual question-answering datasets.

Copied to clipboard

Shangbin Feng, Chan Young Park, Yuhan Liu, Yulia Tsvetkov

Ethical NLP

Challenge:	Hundreds of studies have highlighted ethical issues in NLP models .
Approach:	They propose to measure media biases in LMs trained on diverse data sources . they focus on hate speech and misinformation detection .
Outcome:	The proposed methods quantify the fairness of downstream NLP models trained on politically biased LMs.

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

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

Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes (2025.emnlp-main)

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

Qiunan Du, Zhiliang Tian, Zhen Huang, Kailun Bian, Tianlun Liu, Zhaoning Zhang, Xinwang Liu, Feng Liu, Dongsheng Li

Low-Resource NLP

Challenge:	Existing studies on in-context learning (ICL) focus on the selection of individual examples and ignore correlations among examples.
Approach:	They propose a method to capture positive and negative correlations using the determinantal point process . they optimize the method via kernel decomposition-based MLE to fit a constructed pseudo-labeled dataset .
Outcome:	The proposed method outperforms baselines in ICL example selection.

Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems (2026.acl-long)

Copied to clipboard

Mengzhuo Chen, Junjie Wang, Fangwen Mu, Yawen Wang, Zhe Liu, Huanxiang Feng, Qing Wang

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models (2026.acl-long)

Challenge:	Existing benchmarks rely on partially observable traces that capture only agent outputs . lack of full execution traces obscures many failure causes, authors argue .
Approach:	They propose a benchmark that allows attribution under full execution observability . they find full traces improve attribution accuracy by up to 76.5% over a partial-observation counterpart .
Outcome:	The proposed benchmark improves attribution accuracy by up to 76.5% over a partial-observation counterpart.

Copied to clipboard

Yan Liu, Feng Zhang, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Han Liu, Yangdong Deng

Emotion Trajectory-aware Retrieval for Markov-driven Emotion Anticipation in LLM-based Emotional Support Conversation (2026.findings-acl)

Challenge:	Existing approaches to mitigate inference inefficiency and optimization difficulty are fragmented and constrained by inherent trade-offs.
Approach:	They propose a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer.
Outcome:	The proposed framework achieves a superior balance between inference efficiency and reasoning performance on challenging benchmarks.

Copied to clipboard

Hongyan Wu, Zhiliang Tian, Zhen Huang, Tengyue Hu, Linbo Qiao, Yifu Gao, Feng Liu, Dongsheng Li

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)

Challenge:	Existing strategies focus on planning the next-turn dialogue strategies, while external strategy planners focus on generating empathetic responses.
Approach:	They propose a Markov-driven emotion anticipation framework with emotion trajectory-aware retrieval for LLM-based ESC, which anticipates future emotion states to guide strategy planning and achieve sustained emotional support.
Outcome:	The proposed framework can anticipate future emotions and achieve sustained emotional support on two datasets with two models.

Copied to clipboard

Yifu Huo, Chenglong Wang, Ziming Zhu, Shunjie Xing, Peinan Feng, Tongran Liu, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Zhengtao Yu, Tong Xiao

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

Challenge:	Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories.
Approach:	They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision .
Outcome:	The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision.

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

Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization (2021.acl-long)

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

Xiachong Feng, Xiaocheng Feng, Libo Qin, Bing Qin, Ting Liu

Do LLMs Know and Understand Domain Conceptual Knowledge? (2025.findings-emnlp)

Challenge:	Existing dialogue summarization systems encode text with a number of general semantic features, but these are often not available in open-domain tools.
Approach:	They propose to use DialoGPT to label three types of features on two datasets . they propose to employ pre-trained and non-pre-tried models as dialogue annotators .
Outcome:	The proposed method improves on two dialogue summarization datasets and achieves state-of-the-art performance.

Copied to clipboard

Sijia Shen, Feiyan Jiang, Peiyan Wang, Yubo Feng, Yuchen Jiang, Chang Liu

CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit (2026.acl-long)

Challenge:	Concept sememe tree is a hierarchical structure that represents lexical meaning by combining sememes and their relationships.
Approach:	They introduce a Neighbor Semantic Structure (NSS) and a Chain-of-Thought prompting method to evaluate the effectiveness of various Large Language Models (LLMs) in generating concept sememe trees.
Outcome:	The proposed method guides LLMs through an analysis of a term’s intrinsic core concepts, essential attributes, and semantic relationships, enabling the generation of concept sememe trees.

Copied to clipboard

Kangyu Wang, Zhiyun Jiang, Haibo Feng, Weijia Zhao, Lin Liu, Jianguo Li, Zhenzhong Lan, Weiyao Lin

Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders (2021.acl-long)

Challenge:	Diffusion large language models generate text through iterative denoising with bidirectional attention, enabling richer contextual dependencies.
Approach:	They propose a training-free parallel decoding method that fuses Trace Credit with current logits to boost the confidence of correct but underconfident tokens.
Outcome:	The proposed method achieves 5.48 times speedup with +0.48 accuracy on LLaDA-8B and is orthogonal to mainstream inference optimizations.

Copied to clipboard

Bin Sun, Shaoxiong Feng, Yiwei Li, Jiamou Liu, Kan Li

Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA (2026.findings-acl)

Challenge:	Conditional Variational AutoEncoders (CVAE) can enhance the diversity and informativeness of responses in open-domain dialogue generation tasks.
Approach:	They propose a Conditional Variational AutoEncoder (CVAE) that regularizes latent variables and introduces group information to regularize them.
Outcome:	Empirical results show that the proposed model can significantly boost responses in well-established open-domain dialogue datasets.

Copied to clipboard

Guanhua Chen, Yutong Yao, Shenghe Sun, Ci-jun Gao, Shudong Liu, Lidia S. Chao, Feng Wan, Derek F. Wong

Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition (2024.lrec-main)

Challenge:	Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their capability in visual procedure question answering (VP-QA) remains largely unexplored.
Approach:	They propose a multimodal benchmark specifically designed for visual procedural reasoning that synergizes cross-modal procedure retrieval, context-aware step decomposition, and the next step prediction.
Outcome:	The proposed framework significantly outperforms baselines on visual procedure question answering (VP-QA) Experiments on six VLMs show that it performs better than baselines.

Copied to clipboard

Lianyu Hu, Liqing Gao, Zekang Liu, Wei Feng

NeuReduce: Reducing Mixed Boolean-Arithmetic Expressions by Recurrent Neural Network (2020.findings-emnlp)

Challenge:	Current sign language recognition methods use spatial graphs and temporal modules to capture spatial and temporal features, but their spatial graph modules are typically built on fixed graph structures.
Approach:	They propose a new spatial architecture that captures input-sensitive joint relationships and a temporal module to model multi-scale temporal information to capture complex human dynamics.
Outcome:	The proposed method achieves state-of-the-art accuracy on four large-scale SLR benchmarks.

Copied to clipboard

Weijie Feng, Binbin Liu, Dongpeng Xu, Qilong Zheng, Yun Xu

Numerical Reasoning

Challenge:	Mixed Boolean-Arithmetic (MBA) expressions are difficult to simplify because of interleaving bitwise and arithmical operations.
Approach:	They propose a method to learn and reduce MBA expressions using a string to string method . they propose to use a dataset to train the method to reduce MBA rules .
Outcome:	The proposed method outperforms all other tools in terms of accuracy, solving time, and performance overhead.

Uncertainty-Calibrated Elastic Alignment for Multimodal Sentiment Analysis with Missing Modalities (2026.findings-acl)

Copied to clipboard

Kang He, Yuzhe Ding, Rao Fu, Yukang Feng, Kaipeng Zhang, Yiming Liu, Fei Li, Chong Teng, Donghong Ji

Larger-Context Tagging: When and Why Does It Work? (2021.naacl-main)

Challenge:	Existing methods for multimodal sentiment analysis are often dynamically incomplete.
Approach:	They propose a new uncertainty-calibrated elastic alignment framework to address these issues by employing probabilistic imputation to capture cross-modal ambiguity and leverage the estimated uncertainty to drive elastic alignment.
Outcome:	The proposed framework outperforms state-of-the-art models in multiple benchmarks and consistently outperformed existing models.

Copied to clipboard

Jinlan Fu, Liangjing Feng, Qi Zhang, Xuanjing Huang, Pengfei Liu

Syntactic Text Processing

Challenge:	Existing tagging systems that use sentence-level data are not well understood.
Approach:	They propose a larger-context approach to tagging tasks that incorporates contextual information into existing tapping systems.
Outcome:	The proposed aggregators improve on four tagging tasks and 13 datasets.

MGPO: Thinking with Images via Multi-Turn Grounding-Based Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Xinyu Huang, Yuhao Dong, Weiwei Tian, Bo Li, Rui Feng, Ziwei Liu

Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment (2025.findings-acl)

Challenge:	State-of-the-art large multimodal models face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task.
Approach:	They propose a multi-turn grounding-based policy optimization framework that enables LMMs to iteratively focus on key visual regions by automatically cropping sub-images based on model-predicted grounding coordinates within a multiple-turn conversation framework.
Outcome:	The proposed framework improves on Qwen2.5-VL-7B with 21K samples and surpasses OpenAI’s o1 and GPT-4o models on the out-of-distribution (OOD) V* Bench.

Copied to clipboard

Moxin Li, Yuantao Zhang, Wenjie Wang, Wentao Shi, Zhuo Liu, Fuli Feng, Tat-Seng Chua

On Support Samples of Next Word Prediction (2025.acl-long)

Challenge:	Existing approaches to optimize large language models with human preferences suffer from preference conflicts in the data.
Approach:	They propose to construct Pareto-optimal responses to resolve preference conflicts by using a self-improving DPO framework that enables LLMs to self-generate and select Paret-optimized responses.
Outcome:	The proposed framework achieves superior Pareto Front performance over baselines on two datasets.

Copied to clipboard

Yuqian Li, Yupei Du, Yufang Liu, Feifei Feng, Mou Xiao Feng, Yuanbin Wu

Explainability & Interpretability in NLP

Challenge:	Language models excel in various tasks by making complex decisions, but understanding the rationale behind these decisions remains a challenge.
Approach:	They investigate data-centric interpretability in language models by focusing on the next-word prediction task.
Outcome:	The proposed model supports or deteres specific predictions, while non-support samples play a critical role in generalization and representation learning.

When One LLM Drools, Multi-LLM Collaboration Rules (2026.acl-long)

Copied to clipboard

Shangbin Feng, Wenxuan Ding, Alisa Liu, Zifeng Wang, Weijia Shi, Yike Wang, Shannon Zejiang Shen, Xiaochuang Han, Hunter Lang, Chen-Yu Lee, Tomas Pfister, Yejin Choi, Yulia Tsvetkov

Challenge:	a single general-purpose LLM is not enough to produce a reliable output, argues this paper . a multi-LLM collaboration approach addresses reliability, democratization, and pluralism .
Approach:	They argue that a single general-purpose LLM is not enough to produce a reliable output . they organize existing multi-LLM collaboration methods into a hierarchy based on access and information exchange .
Outcome:	The proposed method addresses reliability, democratization, and pluralism challenges a single LLM fails to produce a reliable output.

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

Copied to clipboard

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

Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)

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

Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality.
Approach:	They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward.
Outcome:	The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability.

Boosting Event Extraction with Denoised Structure-to-Text Augmentation (2023.findings-acl)

Copied to clipboard

Bo Wang, Heyan Huang, Xiaochi Wei, Ge Shi, Xiao Liu, Chong Feng, Tong Zhou, Shuaiqiang Wang, Dawei Yin

Aligning Generative Language Models with Human Values (2022.findings-naacl)

Challenge:	Existing methods for event extraction neglect grammatical incorrectness, structure misalignment, and semantic drifting . et al., 2004; Ahn, 2006) show that the proposed method generates more diverse text representations for event extracting compared with the state-of-the-art.
Approach:	They propose a framework for event extraction that generates additional training data and iteratively selects the effective subset from the generated training data.
Outcome:	The proposed method generates more diverse representations of training data and achieves comparable results with the state-of-the-art.

Copied to clipboard

Ruibo Liu, Ge Zhang, Xinyu Feng, Soroush Vosoughi

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

Challenge:	Existing methods for learning human values do not consider contextual and abstract nature of human values.
Approach:	They propose a reinforcement learning based method that embeds human values judgements into each step of language generation.
Outcome:	The proposed method improves on human values judgements and shows higher alignment performance.

Copied to clipboard

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

Event Detection without Triggers (N19-1)

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

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

Improving Embedding-based Unsupervised Keyphrase Extraction by Incorporating Structural Information (2023.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

Mingyang Song, Huafeng Liu, Yi Feng, Liping Jing

Machine Reading Comprehension Using Structural Knowledge Graph-aware Network (D19-1)

Challenge:	Existing unsupervised keyphrase extraction models ignore the indicative role of the highlights in certain locations, leading to wrong keyphrases extraction.
Approach:	They propose a Highlight-Guided Unsupervised Keyphrase Extraction model that models phrase-document relevance via the highlights of documents and calculates cross-phrase relevance between all candidate phrases.
Outcome:	The proposed model outperforms the state-of-the-art unsupervised keyphrase extraction models on three benchmarks.

Copied to clipboard

Delai Qiu, Yuanzhe Zhang, Xinwei Feng, Xiangwen Liao, Wenbin Jiang, Yajuan Lyu, Kang Liu, Jun Zhao

Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups (2026.findings-acl)

Challenge:	Recent large-scale datasets specify that external knowledge is required to answer questions.
Approach:	They propose a model that leverages external knowledge to construct sub-graphs for entities in machine comprehension context.
Outcome:	The proposed model achieves state-of-the-art performance on the ReCoRD dataset.

Copied to clipboard

Geng Liu, Li Feng, Junjie Mu, Mengxiao Zhu, Francesco Pierri

Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning (2026.acl-long)

Challenge:	Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they reflect and amplify social biases.
Approach:	They propose a Mandarin-specific evaluation framework to examine social identity biases in Chinese LLMs using Mandarin-based prompts.
Outcome:	The proposed framework compares ingroup (“We”) and outgroup (“They”) framings across 240 social groups salient in the Chinese context, using a two-tiered measurement framework that assesses both sentiment and toxicity.

Copied to clipboard

YongKang Liu, Xingle Xu, Ercong Nie, Zijing Wang, Shi Feng, Daling Wang, Qian Li, Hinrich Schuetze

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

Challenge:	Parameter-Efficient Fine-Tuning (PEFT) is an alternative to Full-Parameter Fine-tuning, but its effectiveness on complex tasks such as reasoning and instruction-following remains unclear.
Approach:	They propose to use PEFT to reduce the number of trainable parameters while freezing the weights of LLMs.
Outcome:	The proposed methods perform well on standard tasks, but weaknesses on complex and adversarial settings call for new directions beyond current paradigms.

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

TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation (2024.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

Yujie Feng, Xu Chu, Yongxin Xu, Guangyuan Shi, Bo Liu, Xiao-Ming Wu

Dynamic Graph Navigation via Triplet Chains for Structure-Aware Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Current methods for Continual Dialogue State Tracking (DST) struggle with catastrophic forgetting and knowledge transfer between tasks.
Approach:	They propose a framework for task skill localization and consolidation that enables effective knowledge transfer without relying on memory replay.
Outcome:	The proposed framework shows a 7.6% increase in Avg. JGA and 11% rise in BWT metrics over existing state-of-the-art methods.

Copied to clipboard

Feng Zhao, Yufei Wu, Xianggan Liu, Ruilin Zhao

LLaMA-Rider: Spurring Large Language Models to Explore the Open World (2024.findings-naacl)

Challenge:	Retrieval-Augmented Generation (RAG) is a strategy to mitigate hallucination and factual errors in large language models (LLMs).
Approach:	They propose a structure-aware RAG which achieves noise removal in retrieval through multi-chain graph navigation reasoning.
Outcome:	The proposed method achieves noise removal in retrieval through multi-chain graph navigation reasoning (Trig-Nav) compared to baseline methods, it significantly improves the model’s performance, validating the effectiveness of this approach.

Copied to clipboard

Yicheng Feng, Yuxuan Wang, Jiazheng Liu, Sipeng Zheng, Zongqing Lu

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)

Challenge:	Recent studies have used Large Language Models to help decision-making and planning in environments, but their capacity to acquire environmental knowledge and adapt in an open world remains uncertain.
Approach:	They propose an approach to spur LLMs to explore the open world, gather experiences, and learn to improve their task-solving capabilities by using a feedback-revision mechanism.
Outcome:	The proposed model enhances the efficiency of the LLM in exploring the open world and improves its ability to accomplish more tasks through fine-tuning with merely 1.3k instances of collected data, showing minimal training costs compared to baseline using reinforcement learning.

Copied to clipboard

Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

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

Challenge:	Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references.
Approach:	They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings.
Outcome:	The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading.

Copied to clipboard

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

Learning Dynamic Representations for Discourse Dependency Parsing (2023.findings-emnlp)

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

Tianyi Liu, Yansong Feng, Dongyan Zhao

Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling (2025.acl-long)

Challenge:	Existing models characterize transition states by examining a certain number of elementary discourse units (EDUs) Existing work neglects the arcs obtained from the transition history.
Approach:	They propose to employ GAT-based encoder to learn dynamic representations for sub-trees constructed in previous transition steps.
Outcome:	The proposed model retains access to parsed EDUs through the obtained arcs, especially when handling lengthy text spans with complex structures.

Copied to clipboard

Jiayi Zeng, Yizhe Feng, Mengliang He, Wenhui Lei, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou

Trust Within? Seek Beyond? Knowledge Boundary Aware Policy Optimization for Agentic Search (2026.acl-long)

Challenge:	Current error-handling works are performed in a passive manner, with explicit error- handling instructions.
Approach:	They propose a new benchmark to analyze LLMs' performance on a mis-prompt benchmark and a dataset to promote further research.
Outcome:	The proposed benchmark shows that current LLMs show poor performance on proactive error handling, and that SFT improves on error handling instances.

Copied to clipboard

Tao Feng, Xinke Jiang, Xinyan Hu, Yonggang Zhang, Zhen Tao, Wentao Zhang, Boyang Liu, Wenhao Jiang, Chao Wu

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

Challenge:	Existing approaches to augment large language models with external knowledge suffer from a lack of calibration regarding the model’s knowledge boundary.
Approach:	They propose a reinforcement learning framework that explicitly aligns retrieval decisions with quantified knowledge states.
Outcome:	The proposed framework outperforms strong baselines while exhibiting reduced hallucination rates.

Copied to clipboard

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

CoAug: Combining Augmentation of Labels and Labelling Rules (2023.findings-acl)

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

Rakesh R. Menon, Bingqing Wang, Jun Araki, Zhengyu Zhou, Zhe Feng, Liu Ren

Teaching Large Language Models an Unseen Language on the Fly (2024.findings-acl)

Challenge:	Named Entity Recognition (NER) tasks require large labeled datasets to perform well.
Approach:	They propose a co-augmentation framework that bootstraps predictions from each model to improve few-shot models and rule-augmentation models by bootstrapping them.
Outcome:	The proposed model outperforms strong weak-supervision-based models by 6.5 F1 points . the proposed model can learn from limited labeled data and perform better on small datasets .

Copied to clipboard

Chen Zhang, Xiao Liu, Jiuheng Lin, Yansong Feng

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

Challenge:	Existing large language models struggle to support numerous low-resource languages . Existing models lack sufficient training data for effective parameter updating .
Approach:	They propose a framework for adapting LLMs to unseen languages by in-context learning.
Outcome:	The proposed framework improves Chinese-to-Zhuang translation performance and Zhuan-to Chinese translation performance.

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

Jointly Learning Entity and Relation Representations for Entity Alignment (D19-1)

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

Yuting Wu, Xiao Liu, Yansong Feng, Zheng Wang, Dongyan Zhao

Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection (2026.acl-long)

Challenge:	Entity alignment is a viable method for integrating heterogeneous knowledge among different knowledge graphs (KGs).
Approach:	They propose a Graph Convolutional Network-based framework for learning relation representations by embedding relation seeds into entities and incorporating relation approximation into entities to iteratively improve alignment.
Outcome:	The proposed approach outperforms state-of-the-art methods on three real-world cross-lingual datasets.

Copied to clipboard

Yuwei Zhang, Wenhao Yu, Shangbin Feng, Yifan Zhu, Letian Peng, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang

LGA: LLM-GNN Aggregation for Temporal Evolution Attribute Graph Prediction (2025.emnlp-main)

Challenge:	Existing knowledge injection benchmarks for large language models lack standardized testing grounds.
Approach:	They propose a knowledge injection benchmark that leverages recently-added and expert-curated facts from Wikipedia’s “Did You Know...” entries.
Outcome:	The proposed framework improves reliability accuracy by 29.1%.

Copied to clipboard

Feng Zhao, Ruoyu Chai, Kangzheng Liu, Xianggan Liu

Representation Learning

Challenge:	Current methods focus on 1-hop neighborhood aggregation, lacking capability to capture complex structural interactions.
Approach:	They propose a framework that integrates structural information into attribute embeddings through an attribute embedded loss.
Outcome:	The proposed framework shows significant improvements over existing methods on real-world datasets.

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

Copied to clipboard

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

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment (2026.findings-acl)

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

Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xinyun Liu, Yulia Tsvetkov

Multi-Modal Multi-Granularity Tokenizer for Chu Bamboo Slips (2025.coling-main)

Challenge:	Existing research has focused on enhancing graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data.
Approach:	They propose to unlock generalizable learning of graph with post-training alignment with synthetic graph data by aligning off-the-shelf LLMs and LLM fine-tuned on synthetic graphs.
Outcome:	The proposed algorithm improves on synthetic graph problems and out-of-domain tasks with implicit graph structures.

Copied to clipboard

Yingfa Chen, Chenlong Hu, Cong Feng, Chenyang Song, Shi Yu, Xu Han, Zhiyuan Liu, Maosong Sun

Syntactic Text Processing

Challenge:	Using a multi-modal multi-granularity tokenizer, we analyze ancient Chinese scripts . a large proportion of the characters in ancient Chinese are rare or undeciphered .
Approach:	They propose a multi-modal multi-granularity tokenizer specifically designed for ancient Chinese scripts.
Outcome:	The proposed tokenizer improves on the part-of-speech tagging task on the Chu bamboo slip script.

PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism (2023.acl-long)

Copied to clipboard

Yongkang Liu, Shi Feng, Daling Wang, Yifei Zhang, Hinrich Schütze

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

Challenge:	Existing generative models for dialogue use the last hidden state to summarize the history of the dialogue.
Approach:	They propose a Pseudo-Variational Gated Recurrent Unit (PVGRU) that summarises the accumulated distribution variations of subsequences and builds a model based on it.
Outcome:	The proposed model can improve diversity and relevance of responses on two benchmark datasets.

Copied to clipboard

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

Things not Written in Text: Exploring Spatial Commonsense from Visual Signals (2022.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

Xiao Liu, Da Yin, Yansong Feng, Dongyan Zhao

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

Challenge:	Pretrained language models fail in many NLP tasks, but are ineffective in spatial commonsense reasoning.
Approach:	They propose a spatial commonsense benchmark that focuses on relative scales of objects and the positional relationship between people and objects under different actions.
Outcome:	The proposed framework outperforms pretrained models in answering spatial questions.

Copied to clipboard

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

PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction (2025.findings-naacl)

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

Hammad Ayyubi, Xuande Feng, Junzhang Liu, Xudong Lin, Zhecan Wang, Shih-Fu Chang

JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning (2025.emnlp-main)

Challenge:	PuzzleGPT is a modular and iterative puzzlesolving method for predicting time and location from images.
Approach:	They propose to formalize this ability into core skills and implement it using different modules in an expert pipeline called PuzzleGPT.
Outcome:	The proposed method outperforms large VLMs and finetuned models on TARA and WikiTilo and rivals or surpasses finetuned models.

Copied to clipboard

Huanghai Liu, Quzhe Huang, Qingjing Chen, Yiran Hu, Jiayu Ma, Yun Liu, Weixing Shen, Yansong Feng

Knowledge Representation

Challenge:	Recent studies have introduced legal theories into LLM workflows to improve their understanding of legal texts and reasoning accuracy.
Approach:	They evaluate an expert-annotated four-element knowledge base covering 155 criminal charges.
Outcome:	The proposed model can be used to analyze criminal charges and retrieve them in legal cases.

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

Copied to clipboard

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

OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics (2021.acl-long)

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

Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang

How Good Are LLMs at Out-of-Distribution Detection? (2024.lrec-main)

Challenge:	Existing automatic metrics are observed to correlate poorly with human evaluation.
Approach:	They propose to use OpenMEVA to evaluate open-ended story generation metrics.
Outcome:	The proposed test suite assesses the capabilities of open-ended story generation metrics on annotated stories and auto-constructed test examples.

Copied to clipboard

Bo Liu, Li-Ming Zhan, Zexin Lu, Yujie Feng, Lei Xue, Xiao-Ming Wu

Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models (2024.findings-acl)

Challenge:	Out-of-distribution (OOD) detection is crucial for ensuring AI safety . large language models (LLMs) are becoming more prevalent due to their scale, pre-training objectives, and paradigms used for inference.
Approach:	They propose to use large language models to investigate out-of-distribution (OOD) detection in machine learning.
Outcome:	The proposed method outperforms other OOD detectors in zero-grad and fine-tuning scenarios.

Copied to clipboard

Zehui Chen, Kuikun Liu, Qiuchen Wang, Wenwei Zhang, Jiangning Liu, Dahua Lin, Kai Chen, Feng Zhao

xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)

Challenge:	Existing studies focus on prompt engineering or framework scheduling of one/multiple LLMs.
Approach:	They propose to integrate LLMs as agents into their training corpus by decomposition and redesigning the training corpu . they propose to use LLM-FLAN to effectively fine-tune LANguage models for Agents by reducing hallucinations.
Outcome:	The proposed model outperforms prior best models by 3.5% across agent evaluation datasets.

Copied to clipboard

Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning (2025.emnlp-main)

Challenge:	Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks.
Approach:	They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance.
Outcome:	The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks.

Copied to clipboard

Kaiwen Zhou, Xuandong Zhao, Jayanth Srinivasa, Gaowen Liu, Aosong Feng, Dawn Song, Xin Eric Wang

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

Challenge:	Large Reasoning Models (LRMs) introduce a new paradigm of explicitly reasoning before answering, but they pose great safety risks against harmful queries and adversarial attacks.
Approach:	They propose a safety aha moment that activates safety reasoning and leads to a safe response.
Outcome:	The proposed model can generalize to unseen jailbreak prompts while maintaining general abilities.

Copied to clipboard

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

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

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

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

A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base (2021.findings-emnlp)

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

Yu Feng, Jing Zhang, Gaole He, Wayne Xin Zhao, Lemao Liu, Quan Liu, Cuiping Li, Hong Chen

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

Challenge:	Existing knowledge bases (KBs) can explicitly facilitate the QA process.
Approach:	They propose a numerical reasoning model pretraining NumGNN and NumTransformer, guided by explicit self-supervision signals, to enhance numerical reasoning ability for IR-based KBQA models.
Outcome:	Extensive experiments on two KBQA benchmarks confirm the effectiveness of the proposed model.

Copied to clipboard

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

AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)

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

Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu

Programming Languages in NLP

Challenge:	Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias.
Approach:	They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints.
Outcome:	The proposed benchmarks show that the models fail under causal, structural, or functional constraints.

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

STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (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

Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu

MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation (2025.acl-industry)

Challenge:	Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence.
Approach:	They propose a hierarchical group-based RL framework that leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a mechanism of trajectory-aware reward and trajectory-independent penalty.
Outcome:	Experiments on ALFWorld, WebShop, and Search-Augmented QA show that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect.

Copied to clipboard

Hsin-Ling Hsu, Cong-Tinh Dao, Luning Wang, Zitao Shuai, Thao Nguyen Minh Phan, Jun-En Ding, Chun-Chieh Liao, Pengfei Hu, Xiaoxue Han, Chih-Ho Hsu, Dongsheng Luo, Wen-Chih Peng, Feng Liu, Fang-Ming Hung, Chenwei Wu

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning (2025.emnlp-industry)

Challenge:	Existing systems focus primarily on assessment rather than treatment planning.
Approach:	They propose a framework that structures LLM reasoning to align with real-life workflows.
Outcome:	The proposed framework outperforms baseline approaches in assessment accuracy and treatment plan quality.

Copied to clipboard

Ruizhe Chen, Tianze Luo, Zhiting Fan, Heqing Zou, Zhaopeng Feng, Guiyang Xie, Hansheng Zhang, Zhuochen Wang, Zuozhu Liu, Zhang Huaijian

Visual Data in NLP

Challenge:	Existing methods for video temporal grounding suffer from limited temporal awareness and poor generalization.
Approach:	They propose a two-stage training framework that integrates supervised fine-tuning with reinforcement learning to improve both the accuracy and robustness of VTG models.
Outcome:	The proposed training framework outperforms existing models on multiple benchmarks on open-domain and challenging scenarios.

GraphMR: Graph Neural Network for Mathematical Reasoning (2021.emnlp-main)

Copied to clipboard

Weijie Feng, Binbin Liu, Dongpeng Xu, Qilong Zheng, Yun Xu

Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them (2025.findings-emnlp)

Challenge:	Existing studies have shown the effectiveness of sequence-to-sequence (Seq2Seque) on mathematics solving.
Approach:	They propose a graph-to-sequence neural network which can learn hierarchical information of graphs inputs to solve mathematical problems and speculate answers.
Outcome:	The proposed neural network outperforms other neural networks in hidden information learning and mathematics resolving.

Copied to clipboard

Guanyu Chen, Peiyang Wang, Yizhou Jiang, Yuqian Liu, Chujie Zhao, Ying Fang, Tianren Zhang, Feng Chen

Attend, Select and Eliminate: Accelerating Multi-turn Response Selection with Dual-attention-based Content Elimination (2023.findings-acl)

Challenge:	Existing large language models can perform abstract reasoning tasks but are they actually engaging in rule-based reasoning beyond mere memorization?
Approach:	They propose a method to examine whether large language models perform abstract reasoning . they fine-tune the model to learn those contradictory rules and assess its generalization ability .
Outcome:	The proposed approach examines whether large language models perform abstract reasoning by altering their original understanding of fundamental rules.

Copied to clipboard

Jianxin Liang, Chang Liu, Chongyang Tao, Jiazhan Feng, Dongyan Zhao

Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models (2025.findings-naacl)

Challenge:	Pre-trained language models can be used to perform multi-turn response selection, but they can be expensive.
Approach:	They propose a framework and a strategy that progressively selects and eliminates unimportant content under context-response dual-attention.
Outcome:	The proposed method can effectively speed-up SOTA models without much performance degradation and shows a better trade-off between speed and performance than previous methods.

Copied to clipboard

Weidi Luo, He Cao, Zijing Liu, Yu Wang, Aidan Wong, Bin Feng, Yuan Yao, Yu Li

LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence (2026.findings-acl)

Challenge:	Existing defense methods struggle with two key issues: inadequate defense capabilities and over-defensiveness.
Approach:	They propose a multi-agents-based framework that leverages accurate external information to provide an unbiased summary of user intentions and safety response guidance.
Outcome:	Experiments on popular jailbreak attacks and benign datasets show that the proposed framework can enhance LLM's robustness against jailbreaks without compromising its general functionality.

Copied to clipboard

Wenjin Liu, Haoran Luo, Xin Feng, Xiang Ji, Lijuan Zhou, Rui Mao, Jiapu Wang, Shirui Pan, Erik Cambria

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

Challenge:	Existing benchmarks for legal general intelligence (GI) are result-oriented and do not evaluate the legal intelligence of large language models (LLMs).
Approach:	They propose a Chinese legal benchmark for evaluating legal GI in large language models . they use recent legal cases and exam questions to create multiple-choice questions .
Outcome:	The proposed benchmarks lack a systematic evaluation of the legal intelligence of large language models (LLMs) the results show that even the best LLMs lagging behind human legal professionals.

Copied to clipboard

Ruizhe Chen, Tianxiang Hu, Yang Feng, Zuozhu Liu

Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification (2020.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

Heng Gong, Wei Bi, Xiaocheng Feng, Bing Qin, Xiaojiang Liu, Ting Liu

Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data (2024.findings-acl)

Challenge:	Table-to-text models that select and order salient data and verbalize them fluently are lacking in content planning stage.
Approach:	They propose to enhance neural content planning by understanding data values with contextual numerical value representations that bring the sense of value comparison into content planning.
Outcome:	The proposed model outperforms existing systems with respect to content planning metrics on ROTOWIRE and MLB datasets.

Copied to clipboard

Xiao Liu, Zirui Wu, Xueqing Wu, Pan Lu, Kai-Wei Chang, Yansong Feng

SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification (2024.findings-acl)

Challenge:	Quantitative reasoning with data is a critical skill to analyze data, yet the assessment of such ability remains limited.
Approach:	They propose a quantitative reasoning with data benchmark to evaluate Large Language Models' ability in statistical and causal reasoning with real-world data.
Outcome:	The proposed model GPT-4 achieves an accuracy of 58%, while open-source model Deepseek-coder-instruct gets the highest accuracy of 37%.

Copied to clipboard

Wenxin Liang, Tingyu Zhang, Han Liu, Feng Zhang

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)

Challenge:	Existing methods for few-shot text classification focus on enhancing separation of prototypes without taking semantic relationships into account.
Approach:	They propose to utilize semantically enhanced labels to calibrate class Prototypes . they propose a center loss method to enhance intra-class compactness .
Outcome:	The proposed method outperforms baseline methods on eight few-shot text classification datasets.

Copied to clipboard

Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang

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

Challenge:	Current document image parsing solutions rely on specialized models or generate content autoregressively.
Approach:	They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation.
Outcome:	The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency.

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.

FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging (2025.findings-emnlp)

Copied to clipboard

Zijian Li, Xiaocheng Feng, Huixin Liu, Yichong Huang, Ting Liu, Bing Qin

Misleading Relation Classifiers by Substituting Words in Texts (2023.findings-acl)

Challenge:	a new adaptive merging method is proposed to improve fine-tuning performance . traditional methods often encounter task interference when merging full fine-uning models .
Approach:	They propose an adaptive merging method that directly measures model parameters using the Frobenius norm .
Outcome:	The proposed method outperforms baseline methods in various fine-tuning scenarios.

Copied to clipboard

Tian Jiang, Yunqi Liu, Yan Feng, Yuqing Li, Xiaohui Cui

Crab: A Novel Configurable Role-Playing LLM with Assessing Benchmark (2025.acl-long)

Challenge:	Existing methods to generate adversarial examples for relation classification are vulnerable to adversarials.
Approach:	They propose a method that uses most important parts of speech to substitute words with synonyms or hyponyms to generate adversarial texts of high quality.
Outcome:	The proposed method can generate adversarial texts of high quality and most relationships can be correctly identified in the process of human evaluation.

Copied to clipboard

Kai He, Yucheng Huang, Wenqing Wang, Delong Ran, Dongming Sheng, Junxuan Huang, Qika Lin, Jiaxing Xu, Wenqiang Liu, Mengling Feng

Knowledge-guided Open Attribute Value Extraction with Reinforcement Learning (2020.emnlp-main)

Challenge:	Existing RP-LLMs employ only a single role with numerous dialogues, but Crab enables dynamic configuration of desired roles, thereby enhancing related flexibility and adaptability.
Approach:	They propose a Configurable Role-Playing LLM with Assessing Benchmark that combines a Role dataset curation, persona-emodying Llm construction, and comprehensive benchmark creation for RP dialogue generation.
Outcome:	The proposed model outperforms existing LLMs in performing fine-grained evaluations of RP while keeping dialogue per role minimal.

Copied to clipboard

Ye Liu, Sheng Zhang, Rui Song, Suo Feng, Yanghua Xiao

TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards (2026.acl-long)

Challenge:	Existing methods for open attribute value extraction for emerging entities are noisy or incomplete, even missing.
Approach:	They propose a knowledge-guided reinforcement learning framework for open attribute value extraction for emerging entities.
Outcome:	The proposed framework outperforms baselines by 16.5 - 27.8%.

Copied to clipboard

Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng

Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models (2021.naacl-main)

Challenge:	Existing approaches to training multi-turn attackers to probe model safety vulnerabilities rely on turn-level optimization, which is insufficient for learning long-term attack strategies.
Approach:	They propose a multi-turn reinforcement learning problem that optimizes the harmfulness of the final-turn response as the outcome reward.
Outcome:	The proposed approach improves attack success rates across multiple models and benchmarks, highlighting the effectiveness of the proposed approach.

Copied to clipboard

Yuxuan Lai, Yijia Liu, Yansong Feng, Songfang Huang, Dongyan Zhao

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

Challenge:	Pre-trained language models process text as a sequence of characters, ignoring more coarse granularity, e.g., words.
Approach:	They propose a new pre-training paradigm for Chinese that incorporates word representations along with characters and can model a sentence in a multi-granular manner.
Outcome:	The proposed model can bring an average increase of 1.5% under the 12-layer setting, which achieves new state-of-the-art among base-size models on the CLUE benchmarks.

Copied to clipboard

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

DiNeR: A Large Realistic Dataset for Evaluating Compositional Generalization (2023.emnlp-main)

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

Chengang Hu, Xiao Liu, Yansong Feng

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models (2025.emnlp-main)

Challenge:	Existing compositional generalization datasets lack natural language variation due to limited data scale or lack of diversity.
Approach:	They propose a compositional generalization task to evaluate natural language understanding ability under compositional settings.
Outcome:	The proposed method outperforms the plain seq2seq trained version by a large margin . it uses two strong baseline methods and large language models to tackle the task .

Copied to clipboard

Jiaxuan Zhao, Naibin Gu, Yuchen Feng, Xiyu Liu, Peng Fu, Zheng Lin, Weiping Wang

M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)

Challenge:	Customized black-box prompt tuning is a new approach to customize large language models . however, as models grow, the resources required for training and deployment become increasingly expensive .
Approach:	They propose a framework that facilitates efficient local customization while preserving bidirectional privacy.
Outcome:	The proposed framework facilitates efficient local customization while preserving bidirectional privacy.

Copied to clipboard

Zhaopeng Feng, Jiayuan Su, Jiamei Zheng, Jiahan Ren, Yan Zhang, Jian Wu, Hongwei Wang, Zuozhu Liu

T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step (2024.acl-long)

Challenge:	Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments.
Approach:	They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment.
Outcome:	The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini.

Copied to clipboard

Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao

Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models (2024.findings-acl)

Challenge:	Existing studies evaluate the tool utilization ability of large language models based on the final output or only consider the single-step tool calling.
Approach:	They propose a new approach to evaluate the tool utilization capability of large language models (LLMs) they decompose the tool usage into multiple sub-processes, including instruction following, planning, reasoning, retrieval, understanding, and review.
Outcome:	The proposed model exhibits consistency with the outcome-oriented evaluation and provides a more fine-grained analysis of the capabilities of LLMs.

Copied to clipboard

Wenxuan Ding, Shangbin Feng, Yuhan Liu, Zhaoxuan Tan, Vidhisha Balachandran, Tianxing He, Yulia Tsvetkov