Papers by Yuan Wang

Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context (2026.acl-long)

Challenge:	Autoregressive (AR) decoding in large language models is latency-bounded by strictly sequential token generation.
Approach:	They propose a diffusion-based drafter that proposes multi-token candidates and then verifies them in parallel by the target model.
Outcome:	The proposed drafter generates multi-token proposals in a single forward pass while remaining compatible with standard AR verifiers.

Copied to clipboard

Yilun Zhu, Yuan Zhuang, Nikhita Vedula, Dushyanta Dhyani, Shaoyuan Xu, Mohsen Bayati, Bryan Wang, Shervin Malmasi

Challenge:	Existing methods for text regression lack local grounding and rely on shared representations.
Approach:	They propose a distributional regression model with quantile tokens that insert dedicated quantiles into the input sequence.
Outcome:	The proposed method outperforms baseline models on the inside Airbnb and StackSample datasets.

Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models (2025.emnlp-main)

Copied to clipboard

Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, JingBo Zhu

AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering (2025.findings-emnlp)

Challenge:	Recent training-based TTS methods, such as continued reinforcement learning, have surged in popularity, while training-free TTS approaches are gradually fading from prominence.
Approach:	They propose a fine-grained sequential scaling method guided by process verification that integrates training-free TTS methods with other classical parallel scaling methods at the step level.
Outcome:	Experiments on five instruction-tuned large language models (LLMs) show that training-free TTS methods can extend reasoning performance boundaries.

Copied to clipboard

Ziqing Wang, Chengsheng Mao, Xiaole Wen, Yuan Luo, Kaize Ding

FISTAPruner: Layer-wise Post-training Pruning for Large Language Models (2025.emnlp-main)

Challenge:	Existing Med-MLLMs fail when deployed in low-resource settings where abundant labeled data is unavailable.
Approach:	They propose a training-free agentic framework that performs medical knowledge augmentation via LLM agents.
Outcome:	The proposed framework performs medical knowledge augmentation via LLM agents.

Copied to clipboard

Pengxiang Zhao, Hanyu Hu, Ping Li, Yi Zheng, Zhefeng Wang, Xiaoming Yuan

Syntax-guided Localized Self-attention by Constituency Syntactic Distance (2022.findings-emnlp)

Challenge:	Existing pruning methods require inefficient retraining for billion-scale LLMs or rely on heuristicically designed metrics to determine pruning masks, leading to performance degradation.
Approach:	They propose a convex optimization model that induces sparsity in large language models by leveraging FISTA.
Outcome:	The proposed method can remove 50% of model parameters while retaining 98.6% and 95.6% of the zero-shot performance.

Copied to clipboard

Shengyuan Hou, Jushi Kai, Haotian Xue, Bingyu Zhu, Bo Yuan, Longtao Huang, Xinbing Wang, Zhouhan Lin

A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation (2024.lrec-main)

Challenge:	Recent studies have shown that Transformers is implicitly learning syntactic information from data, albeit is highly dependent on the quality and scale of the training data.
Approach:	They propose a syntax-guided localized self-attention model that allows directly incorporating grammar structures from an external constituency parser.
Outcome:	The proposed model improves translation performance on a variety of datasets, from small to large datasets and with different source languages.

Copied to clipboard

Li Yuan, Yi Cai, Haopeng Ren, Jiexin Wang

A Survey of LLM-based Agents in Medicine: How far are we from Baymax? (2025.findings-acl)

Challenge:	Existing models overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees.
Approach:	They propose a model that utilizes logical entailment patterns to generate coherent explanations by leveraging logical patterns.
Outcome:	The proposed model produces more coherent and reasonable conclusions that closely align with the underlying premises.

Copied to clipboard

Wenxuan Wang, Zizhan Ma, Zheng Wang, Chenghan Wu, Jiaming Ji, Wenting Chen, Xiang Li, Yixuan Yuan

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification (2025.acl-long)

Challenge:	Large Language Models (LLMs) are transforming healthcare through their ability to understand and assist with medical tasks.
Approach:	They analyze system profiles, clinical planning, medical reasoning frameworks, and external capacity enhancement.
Outcome:	The findings highlight the future directions in medical reasoning, physical system integration, and training simulations.

Copied to clipboard

Chengwu Liu, Ye Yuan, Yichun Yin, Yan Xu, Xin Xu, Zaoyu Chen, Yasheng Wang, Lifeng Shang, Qun Liu, Ming Zhang

An In-depth Study on Internal Structure of Chinese Words (2021.acl-long)

Challenge:	Chain-of-Thought prompting is a de facto method to elicit reasoning capabilities from large language models (LLMs).
Approach:	They propose a step-aware formal verification framework Safe to address hallucinations in CoT prompting . they propose 'formal step' as a benchmark for step correctness theorem proving with 30,809 formal statements.
Outcome:	The proposed framework shows significant performance improvement while offering interpretable and verifiable evidence.

Copied to clipboard

Chen Gong, Saihao Huang, Houquan Zhou, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan

Syntactic Text Processing

Challenge:	Unlike English letters, Chinese characters have rich and specific meanings.
Approach:	They propose to model Chinese words' internal structures as dependency trees with 11 labels for distinguishing syntactic relationships.
Outcome:	The proposed model of Chinese word-internal structures shows it can be used to parse sentences . it shows that the model can be applied to a sentence-level task with a competitive dependency parser.

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

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

Detoxifying Large Language Models via the Diversity of Toxic Samples (2025.emnlp-main)

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

Ying Zhao, Yuanzhao Guo, Xuemeng Weng, Yuan Tian, Wei Wang, Yi Chang

Incorporating Circumstances into Narrative Event Prediction (2021.findings-emnlp)

Challenge:	Existing methods for analyzing and utilizing toxic samples are limited . current methods fail to fully harness their potential .
Approach:	They propose a diverse detoxification framework that leverages toxic samples' diversity . they propose MPSG strategy and SC-DPO approach to elicit personalized toxic responses .
Outcome:	The proposed framework could be used to optimize large language models for user safety . it incorporates two components: MPSG strategy and SC-DPO approach .

Copied to clipboard

Shichao Wang, Xiangrui Cai, HongBin Wang, Xiaojie Yuan

Challenge:	Existing studies focus on mining the inter-events relationships while ignoring how the events happened.
Approach:	They propose to incorporate event circumstances into the narrative event prediction by combining two multi-head attention modules and regularizing attention weights.
Outcome:	The proposed model outperforms baseline models by 12.2%.

MAGIC: Deep Geometric Evolution with Structural Consensus for Temporal Knowledge Graph Reasoning (2026.acl-long)

Copied to clipboard

Chengao Liu, Yuan Li, Yingze Wang, Jianbin Jiao

Unity in Diversity: Collaborative Pre-training Across Multimodal Medical Sources (2024.acl-long)

Challenge:	Existing multi-geometry approaches face two key bottlenecks: Riemannian depth barrier and gate collapse.
Approach:	They propose a framework for Temporal Knowledge Graph reasoning that integrates a Tangent-Residual Engine into multi-geometric spaces to regulate gradient flow and prevent collapse.
Outcome:	The proposed framework improves state-of-the-art in TKG reasoning by up to 2.9 points.

Copied to clipboard

Xiaochen Wang, Junyu Luo, Jiaqi Wang, Yuan Zhong, Xiaokun Zhang, Yaqing Wang, Parminder Bhatia, Cao Xiao, Fenglong Ma

Direct Multi-Turn Preference Optimization for Language Agents (2024.emnlp-main)

Challenge:	Current pre-training techniques rely on a limited scope of medical data, limiting the range of downstream tasks.
Approach:	They propose a pre-training strategy that unifies patient data within individual sources and captures explicit and implicit correlations between patients across different sources.
Outcome:	The proposed strategy bridges the gap between multimodal medical sources by aggregating patient data within individual sources and capturing explicit and implicit correlations between patients across sources.

Copied to clipboard

Wentao Shi, Mengqi Yuan, Junkang Wu, Qifan Wang, Fuli Feng

Challenge:	Extensive experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the DMPO loss function.
Approach:	They propose a novel loss function for multi-turn agent tasks that replaces the policy constraint with the state-action occupancy measure constraint and adds length normalization to the Bradley-Terry model.
Outcome:	Experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the proposed loss function.

Exploring the Impact of Personality Traits on LLM Toxicity and Bias (2025.emnlp-main)

Copied to clipboard

Shuo Wang, Renhao Li, Xi Chen, Yulin Yuan, Min Yang, Derek F. Wong

Sentiment Analysis

Challenge:	anthropomorphic LLMs are being developed to serve diversified roles, but content safety concerns remain regarding their toxicity and toxicity.
Approach:	They propose to assign personality traits to large language models (LLMs) to reduce toxic language and social biases in their outputs by using the widely accepted HEXACO personality framework developed in social psychology.
Outcome:	The proposed model is able to perform on three toxic and bias benchmarks and shows that assigning personality traits reduces bias and toxicity similar to humans’ correlations between personality traits and toxic behaviors.

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Kai Yao, Penglei Gao, Lichun Li, Yuan Zhao, Xiaofeng Wang, Wei Wang, Jianke Zhu

ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool Invocations (2025.emnlp-main)

Challenge:	Parameter-Efficient Fine-Tuning (PEFT) methods have gained popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks.
Approach:	They propose a method to optimize the importance of full layers with layer-wise importance scoring by leveraging the estimated importance scores.
Outcome:	The proposed method is compatible with PEFT methods that operate on a per-layer basis and achieves better performance.

Copied to clipboard

Yuejin Xie, Youliang Yuan, Wenxuan Wang, Fan Mo, Jianmin Guo, Pinjia He

Challenge:	Current models exhibit notable vulnerabilities in maintaining safety during multi-step tool interactions and in indirect harm scenarios.
Approach:	They propose a safety fine-tuning dataset to fine- tune LLMs into assistants . they propose to use synthesized trajectories and realistic, context-aware sample generation .
Outcome:	The proposed model maintains safety in multi-step and indirect harm scenarios with little impact on helpfulness.

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models (2026.acl-long)

Copied to clipboard

Jincheng Liu, Sijun He, Jingjing Wu, Xiangsen Wang, Yang Chen, Zhaoqi Kuang, Siqi Bao, Yuan Yao

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions (2025.naacl-industry)

Challenge:	Existing evaluation frameworks focus on isolated question-answering tasks that may not capture the essential aspects of strategic reasoning.
Approach:	They evaluate 13 large language models across over 800 games in chess . they use a chessian-based framework to test strategic reasoning and pattern recognition .
Outcome:	The proposed framework improves performance and basic understanding of large language models.

Copied to clipboard

Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance (2025.emnlp-main)

Challenge:	Streaming automatic speech recognition models use high power consumption to improve usability and accuracy.
Approach:	They propose to optimize on-device speech recognition models by adjusting component energy sensitivities based on their specific energy sensitities to reduce power consumption.
Outcome:	The proposed approach achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.

Copied to clipboard

Songsheng Wang, Rucheng Yu, Zhihang Yuan, Chao Yu, Feng Gao, Yu Wang, Derek F. Wong

ImaRA: An Imaginative Frame Augmented Method for Low-Resource Multimodal Metaphor Detection and Explanation (2025.findings-naacl)

Challenge:	Visual Language Models (VLMs) have significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models.
Approach:	They propose a framework to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model.
Outcome:	Empirical results show that the proposed framework improves the speed of the prediction task by 44%.

Copied to clipboard

Yuan Tian, Minzheng Wang, Nan Xu, Wenji Mao

Few-shot Query-Focused Summarization with Prefix-Merging (2022.emnlp-main)

Challenge:	Existing methods for multimodal metaphor detection neglect cross-domain and attribute similarity characteristics underlying multimodal understanding.
Approach:	They propose an Imaginative FRame Augmented method for multimodal metaphor detection and explanation . they use a cross-modal imagination dataset rich in multimodal multimodal expressions .
Outcome:	The proposed method outperforms existing methods with training data on two datasets.

Copied to clipboard

Ruifeng Yuan, Zili Wang, Ziqiang Cao, Wenjie Li

Summarization

Challenge:	Query-focused summarization has been considered as an important extension for text summarizing . lack of large-scale datasets hinders its development .
Approach:	They propose to integrate text summarization and question answering into a prefix-based pretraining strategy for few-shot learning in query-focused summarizing.
Outcome:	The proposed prefix-based pretraining outperforms fine-tuning on query-focused summarization.

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning (2021.emnlp-main)

Challenge:	Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach:	They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome:	The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.

Copied to clipboard

Wei Zhu, Xiaoling Wang, Yuan Ni, Guotong Xie

AdDriftBench: A Benchmark for Detecting Data Drift and Label Drift in Short Video Advertising (2025.findings-emnlp)

Challenge:	Existing approaches to improve the early exiting of natural language processing (NLP) are notoriously gigantic and slow in both training and inference.
Approach:	They propose a framework for improving the early exiting of BERT by asking each exit to distill knowledge from each other.
Outcome:	The proposed framework outperforms the state-of-the-art (SOTA) BERT early exiting methods on the GLUE benchmark.

Copied to clipboard

Yinghao Song, Xiangji Zeng, Shuai Cui, Lu Sun, Zhaowei Liu, Yuan Yuan, Yulu Wang, Hai Zhou, Zhaohan Gong

Adaptive Hyper-parameter Learning for Deep Semantic Retrieval (2023.emnlp-industry)

Challenge:	Short video advertising scenarios present unique challenges due to data drift (DD) and label drift (LD).
Approach:	They propose to use data drift and label drift to evaluate models under rapidly shifting content distributions and labeling scenarios to assess their generalization capabilities.
Outcome:	The proposed model performs moderately in short video advertising contexts, particularly in handling fine-grained semantics and adapting to shifting instructions.

Copied to clipboard

Mingming Li, Chunyuan Yuan, Huimu Wang, Peng Wang, Jingwei Zhuo, Binbin Wang, Lin Liu, Sulong Xu

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning (2025.findings-naacl)

Challenge:	Existing methods for deep semantic retrieval are highly sensitive to hyper-parameters . a novel adaptive metric learning method is proposed to overcome this limitation .
Approach:	They propose a method that adaptively obtains hyper-parameters without fixed or extra-trainable hyper-parmeters . they adopt a symmetric metric learning method to mitigate model collapse issues .
Outcome:	The proposed method outperforms existing methods on a real-world dataset and brings economic benefits.

Copied to clipboard

Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)

Challenge:	Existing decoding strategies for chain-of-thought reasoning do not exploit prior information about question difficulty.
Approach:	They propose a decoding strategy called self-consistency to improve reasoning performance by adjusting the number of samples based on the posterior distribution of a set of pre-samples.
Outcome:	The proposed method outperforms baseline methods on arithmetic, commonsense and symbolic reasoning tasks while achieving comparable performance.

Copied to clipboard

Qiao Cheng, Juntao Liu, Xiaoye Qu, Jin Zhao, Jiaqing Liang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Yanghua Xiao

Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use (2026.findings-eacl)

Challenge:	Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention.
Approach:	They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents.
Outcome:	The proposed model achieves a high 96% F1 score on data quality and is far lower than humans.

Copied to clipboard

Yiyang Li, Zehong Wang, Zhengqing Yuan, Zheyuan Zhang, Keerthiram Murugesan, Chuxu Zhang, Yanfang Ye

Evaluating Text Generation Quality Using Spectral Distances of Surprisal (2025.findings-emnlp)

Challenge:	Illicit drug use among teens and young adults remains a public health concern . existing models ignore latent and interconnected structures among survey variables .
Approach:	They propose a joint graph-language modeling framework to detect illicit drug use among TYAs . they use large-scale surveys such as the Youth Risk Behavior Survey and the National Survey on Drug Use and Health to analyze data .
Outcome:	The proposed framework outperforms baseline models on YRBS and NSDUH datasets in predictive accuracy.

Copied to clipboard

Zhichen Liu, Yongyuan Li, Yang Xu, Yu Wang, Yingfang Yuan, Zuhao Yang

On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)

Challenge:	Existing metric fails to capture text surprisal, but FACE-2 produces stronger agreement with human preferences.
Approach:	They propose a new automatic evaluation metric for open-ended text generation . they propose metric that extracts the dynamic patterns (spectrum) of text surprisal .
Outcome:	The proposed metric outperforms existing methods in revealing the model scaling effect . it produces stronger agreement with human preferences from a large human-annotated dataset .

Copied to clipboard

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training (2025.acl-long)

Challenge:	Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios.
Approach:	They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments.
Outcome:	The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings.

Copied to clipboard

Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Jiahao Xu, Tian Liang, Pinjia He, Zhaopeng Tu

Chain-of-Jailbreak Attack for Image Generation Models via Step by Step Editing (2025.findings-acl)

Challenge:	Large Language Models exhibit a level of intelligence that is both impressive and everevolving, but their ability to refuse generating unsafe content is a double-edged sword.
Approach:	They propose a method to tackle a refusal position bias within safety tuning data that compromises the models’ ability to appropriately refuse generating unsafe content.
Outcome:	The proposed method significantly improves model safety without compromising performance and surpasses baseline methods in defending against attacks.

Copied to clipboard

Wenxuan Wang, Kuiyi Gao, Youliang Yuan, Jen-tse Huang, Qiuzhi Liu, Shuai Wang, Wenxiang Jiao, Zhaopeng Tu

A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots (2022.findings-acl)

Challenge:	Text-based image generation models, such as Stable Diffusion and DALL-E 3, hold significant potential in content creation and publishing workflows . however, considerable efforts are being made to prevent the generation of harmful content, such abusive, violent, or pornographic material.
Approach:	They propose a chain-of-jailbreak method which decomposes malicious queries into multiple sub-queries and iteratively edits images based on these sub-questions.
Outcome:	The proposed method can bypass safeguards of image generation models for over 60% cases, significantly outperforms other jailbreaking methods (14%)

Copied to clipboard

Sai Zhang, Yuwei Hu, Yuchuan Wu, Jiaman Wu, Yongbin Li, Jian Sun, Caixia Yuan, Xiaojie Wang

Unified Demonstration Retriever for In-Context Learning (2023.acl-long)

Challenge:	Sub-Slot based task-oriented dialogs provide slot values segment by segment over multiple turns.
Approach:	They define a task called Sub-Slot based Task-Oriented Dialog (SSTOD) they build a Chinese dialog dataset SSD for boosting research on SSTOD.
Outcome:	The proposed task is called Sub-Slot based Task-Oriented Dialog (SSTOD) it includes 40K dialogs and 500K utterances from Chinese names, phone numbers, ID numbers and license plate numbers . the dataset is well annotated with sub-slot values, slot values, dialog states and actions .

Copied to clipboard

Xiaonan Li, Kai Lv, Hang Yan, Tianyang Lin, Wei Zhu, Yuan Ni, Guotong Xie, Xiaoling Wang, Xipeng Qiu

EventRAG: Enhancing LLM Generation with Event Knowledge Graphs (2025.acl-long)

Challenge:	In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction.
Approach:	They propose a single model to retrieve demonstrations for a wide range of tasks by combining training signals from various tasks into a unified list-wise ranking formulation by language model’s feedback.
Outcome:	The proposed model outperforms baselines on 30+ tasks across 13 task families and multiple data domains.

Copied to clipboard

Zairun Yang, Yilin Wang, Zhengyan Shi, Yuan Yao, Lei Liang, Keyan Ding, Emine Yilmaz, Huajun Chen, Qiang Zhang

Incentivizing Strong Reasoning from Weak Supervision (2026.eacl-long)

Challenge:	Existing approaches to text generation often neglect event structures that shape real-world narratives.
Approach:	They propose a framework that integrates structured event semantics with iterative retrieval and inference to enhance text generation.
Outcome:	Experiments on UltraDomain and MultiHopRAG show that the proposed framework outperforms baseline RAG systems in generation effectiveness, logical consistency, and multi-hop reasoning accuracy.

Copied to clipboard

Yige Yuan, Teng Xiao, Shuchang Tao, Xue Wang, Jinyang Gao, Bolin Ding, Bingbing Xu

Can’t See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs (2025.acl-long)

Challenge:	Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on expensive high-quality demonstrations and reinforcement learning.
Approach:	They propose to incentivize reasoning abilities of large language models without expensive demonstrations and reinforcement learning.
Outcome:	The proposed model can recover 94% of the gains of expensive RL at a fraction of the cost.

Copied to clipboard

Wenxuan Wang, Xiaoyuan Liu, Kuiyi Gao, Jen-tse Huang, Youliang Yuan, Pinjia He, Shuai Wang, Zhaopeng Tu

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

Challenge:	Multimodal Large Language Models (MLLMs) have expanded the capabilities of traditional language models by enabling interaction through both text and images.
Approach:	They propose a multimodal safety awareness benchmark to evaluate MLLMs across 29 safety scenarios with 1,500 carefully curated image-prompt pairs.
Outcome:	The proposed model is able to identify unsafe content and avoid over-sensitivity that can hinder helpfulness.

Copied to clipboard

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

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives (P19-1)

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

Copied to clipboard

Yi Tay, Shuohang Wang, Anh Tuan Luu, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang

Machine Reading Comprehension

Challenge:	Using a pointer-generator framework for reading/sampling over large documents, we propose a framework for learning over long narratives where documents easily span over thousands of tokens.
Approach:	They propose a curriculum learning (CL) based pointer-generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty.
Outcome:	The proposed framework improves on the NarrativeQA reading comprehension benchmark and reaches state-of-the-art performance.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

Explainability & Interpretability in NLP

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding (2026.findings-acl)

Copied to clipboard

Lin Zhong, Siyu Zhu, Zizhen Yuan, Jinhao Cui, Xinyang Zhao, Lingzhi Wang, Hao Chen, Qing Liao

GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models (2025.coling-main)

Challenge:	Existing Large Language Models (LLMs) mainly address isolated tasks such as emotion analysis or stance detection.
Approach:	They propose a large-scale model that combines large-level annotations with hyperbolic space to model human cognitive states.
Outcome:	The proposed model outperforms baseline models on cognitive dimensions on single dimension tasks while retaining strong hierarchical structure.

Copied to clipboard

Zike Yuan, Ming Liu, Hui Wang, Bing Qin

MCIL: Multimodal Counterfactual Instance Learning for Low-resource Entity-based Multimodal Information Extraction (2024.lrec-main)

Challenge:	Existing benchmarks focus primarily on pure graph understanding, lacking a comprehensive evaluation across all graph types and detailed capability definitions.
Approach:	They propose a benchmark to evaluate LLMs' graph comprehension and reasoning abilities using a three-tier hierarchical taxonomy and a granular taxonomies.
Outcome:	The proposed model includes 11 datasets with 5,140 graphs of varying complexity.

Copied to clipboard

Baohang Zhou, Ying Zhang, Kehui Song, Hongru Wang, Yu Zhao, Xuhui Sui, Xiaojie Yuan

Towards Proactive Personalization through Profile Customization for Individual Users in Dialogues (2026.findings-acl)

Challenge:	Existing methods to perform multimodal information extraction only investigated entity-based tasks under supervised learning with adequate labeled data.
Approach:	They propose to investigate the entity-based MIE tasks under the low-resource settings by decomposing the features into image, entity, and context factors.
Outcome:	The proposed method is able to perform on two public MIE benchmark datasets and the experimental results confirm it.

Copied to clipboard

Xiaotian Zhang, Yuan Wang, Ruizhe Chen, Zeya Wang, Runchen Hou, Zuozhu Liu

Towards Rationality in Language and Multimodal Agents: A Survey (2025.naacl-long)

Challenge:	Existing alignment methods focus on universal human values or static, single-turn preferences, thereby failing to address the critical needs of long-term personalization and the initial user cold-start problem.
Approach:	They propose a user-centric lifelong agent that continuously infers and adapts to user preferences.
Outcome:	The proposed agent achieves superior performance over strong prompt-based and policy optimization baselines, not only in idealized but also in noisy conversational contexts.

Copied to clipboard

Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Yuan Yuan, Zhuoqun Hao, Xinyi Bai, Weijie J Su, Camillo Jose Taylor, Tanwi Mallick

GrocLM: Grocery Category Recommendation in E-Commerce with Large Language Models (2026.acl-industry)

Challenge:	despite advances in language and multimodal agents, large language models lack rationality . despite their progress, large-scale models lack real-world grounding and feedback mechanisms .
Approach:	They propose to build more rational language and multimodal agents . they also examine what criteria define rationality in intelligent systems .
Outcome:	This paper assesses the state-of-the-art in language and multimodal agents . it also outlines open challenges and future research directions .

Copied to clipboard

Yuan Zhong, Chuanwei Ruan, Moein Hasani, Tejaswi Tenneti, Haixun Wang, Fenglong Ma

Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts (2025.findings-emnlp)

Challenge:	a growing number of online grocery shoppers are using category-level recommendation systems . traditional item-level methods face scalability and accuracy challenges .
Approach:	a new language model is developed to encode cyclical purchasing patterns into model parameters . the model is scalable and more business-aligned than traditional item-level methods .
Outcome:	a new language model outperforms standard methods in a live production environment . the proposed model achieves a 7.5% relative improvement in cart-adds per impression .

Copied to clipboard

Xuyang Wu, Yuan Wang, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

A Neural-Symbolic Approach to Natural Language Understanding (2022.findings-emnlp)

Challenge:	Large vision-language models have demonstrated strong capabilities in open-world visual understanding, but it is not clear how they address demographic biases in real life.
Approach:	They propose a method to assess visual fairness in LVLMs by question-answering/classification tasks.
Outcome:	The proposed approach improves transparency and offers a scalable solution for fairness mitigation.

Copied to clipboard

Zhixuan Liu, Zihao Wang, Yuan Lin, Hang Li

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Pre-trained language models have enabled deep neural networks to perform natural language understanding tasks, but their performance can drastically deteriorate when logical reasoning is needed.
Approach:	They propose a framework for NLU based on analogical reasoning based upon neural processing and logical reasoning using both neural and symbolic processing.
Outcome:	The proposed framework outperforms state-of-the-art methods on two NLU tasks, question answering (QA) and natural language inference (NLI).

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Data Efficient RLVR via Off-Policy Influence Guidance (2026.acl-long)

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Copied to clipboard

Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang

Personalized Large Language Model Assistant with Evolving Conditional Memory (2025.coling-main)

Challenge:	Existing data selection methods for RLVR are heuristic-based, lacking theoretical guarantees and generalizability.
Approach:	They propose an off-policy influence estimation method that approximates data influence using offline trajectories.
Outcome:	The proposed method reduces the computational cost of policy rollouts and improves storage and computation efficiency.

Copied to clipboard

Ruifeng Yuan, Shichao Sun, Yongqi Li, Zili Wang, Ziqiang Cao, Wenjie Li

Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset (2026.findings-acl)

Challenge:	With the rapid development of large language models, personalized large language model assistants like ChatGPT are limited in personalized services.
Approach:	They propose a plug-and-play framework that could facilitate personalized large language model assistants with evolving conditional memory.
Outcome:	The proposed framework can preserve the knowledge and experience from the history dialogue with the user, which can be applied to future tailored responses that better align with the users' preferences.

Copied to clipboard

Baode Wang, Biao Wu, Weizhen Li, Meng Fang, Zuming Huang, Jun Huang, Yanjie Liang, Haozhe Wang, Ling Chen, Wei Chu, Yuan Qi

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing supervised fine-tuning methods struggle to generalize across document types, leading to poor performance.
Approach:	They propose layoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation.
Outcome:	The proposed model outperforms specialized document parsing systems and general-purpose vision-language models on a broad range of document types, languages, and structural complexities.

Copied to clipboard

Zixu Wang, Bingbing Xu, Yige Yuan, Huawei Shen, Xueqi Cheng

Challenge:	Existing approaches generate workflows either at task level or query level, but their relative costs and benefits remain unclear.
Approach:	They propose a query-level workflow generation framework that generates tasks at task level and query level.
Outcome:	The proposed framework reduces token usage by up to 83% compared to existing approaches . it maintains competitive performance with an average degradation of just 0.61% compared with existing approaches across multiple datasets .

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion (2024.emnlp-main)

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

Copied to clipboard

Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang, Shaochen Zhong, Jiayi Yuan, Hongye Jin, Zirui Liu, Vipin Chaudhary, Shuai Xu, James Caverlee, Xia Hu

FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification (2022.emnlp-main)

Challenge:	Existing mechanisms compromise ownership rights or raise data privacy concerns . existing mechanisms compromise security of released large language models .
Approach:	They propose a TaylorMLP to preserve the ownership of large language models by transforming the weights of LLMs into Taylor-series parameters instead of releasing original weights .
Outcome:	The proposed model preserves ownership of large language models and prevents their abuse by adjusting the generation speed and causing low-speed token generation.

Copied to clipboard

Tingyu Xia, Yue Wang, Yuan Tian, Yi Chang

Focused Large Language Models are Stable Many-Shot Learners (2024.emnlp-main)

Challenge:	Recent research shows keyword-driven methods can achieve state-of-the-art performance on various tasks.
Approach:	They propose an efficient weakly-supervised text classification approach using unlabeled data . they use dense text representation to retrieve class-relevant documents from unlabed corpus .
Outcome:	The proposed weakly-supervised classification method outperforms keyword-driven models on a wide range of classification tasks.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)

Challenge:	In-Context Learning (ICL) enables large language models to achieve rapid task adaptation by learning from demonstrations.
Approach:	They propose a training-free method that disperses model attention from the query . they propose 'focus' search strategy that uses model perplexity to ensure sufficient attention .
Outcome:	The proposed method achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations.

Copied to clipboard

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrieval (2025.emnlp-main)

Challenge:	Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs.
Approach:	They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time.
Outcome:	The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets.

Copied to clipboard

Jian Zhang, Junyi Guo, Junyi Yuan, Huanda Lu, Yanlin Zhou, Fangyu Wu, Qiufeng Wang, Dongming Lu

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Challenge:	Cross-modal retrieval is essential for interpreting cultural heritage data, but its effectiveness is limited by incomplete or inconsistent textual descriptions.
Approach:	They propose a data augmentation framework that enhances cross-modal retrieval performance by improving the completeness and consistency of LLM-generated descriptions.
Outcome:	The proposed framework improves cross-modal retrieval performance by improving completeness and consistency of LLM-generated descriptions.

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering (2026.acl-long)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Zheyuan Zhang, Kaiwen Shi, Zhengqing Yuan, Zehong Wang, Tianyi Ma, Keerthiram Murugesan, Vincent Galassi, Chuxu Zhang, Yanfang Ye

VocabTailor: Dynamic Vocabulary Selection for Downstream Tasks in Small Language Models (2026.findings-acl)

Challenge:	Existing approaches to agent routing emphasize cost efficiency while overlooking the fine-grained contextual and relational structure inherent in QA tasks.
Approach:	They propose a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.
Outcome:	The proposed framework outperforms single-agent and ensemble baselines while generalizing across benchmarks and LLM backbones.

Copied to clipboard

Hanling Zhang, Yayu Zhou, Tongcheng Fang, Zhihang Yuan, Guohao Dai, Wanli Ouyang, Yu Wang

Measuring Large Language Models’ Adversarial Behavior in Social Deduction Games (2026.findings-acl)

Challenge:	Existing static vocabulary pruning designs that reduce memory usage suffer from rigid, one-size-fits-all designs that cause information loss during the prefill stage and lack flexibility.
Approach:	They propose a decoupled dynamic vocabulary selection framework that addresses memory constraints through offloading embedding and implements a hybrid static-dynamic vocabulary selection strategy for LM Head.
Outcome:	The proposed framework reduces memory usage by 99% with minimal or no degradation in performance.

Copied to clipboard

Marissa Zhao Li, Esha Shivakumar, Peiran Wang, Ying Li, Yuan Tian

CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge (2022.acl-demo)

Challenge:	Existing safety evaluations focus on refusal-based methods that test whether models avoid responding to inappropriate or violent requests, leaving open questions about how models behave in interactive social settings.
Approach:	They propose to use a meta-LLM to construct a closed behavioral taxonomy from a multi-agent simulation to examine adversarial behavior of large language models.
Outcome:	The proposed model-based model-driven model-model-based taxonomy shows that the model-led model-learning model exhibits distinct behavioral profiles and influences social stability and competitive success.

Copied to clipboard

Zhuoran Jin, Tianyi Men, Hongbang Yuan, Zhitao He, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Yubo Chen, Jun Zhao

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation (2025.findings-emnlp)

Challenge:	Existing methods focus on entity-centric knowledge, but CogKGE supports heterogeneous knowledge.
Approach:	They propose a knowledge graph embedding toolkit to represent multi-source and heterogeneous knowledge.
Outcome:	The proposed toolkit provides a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks.

Copied to clipboard

Wen Ye, Zhaocheng Liu, Gui Yuwei, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang

FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems (2026.findings-acl)

Challenge:	Existing methods for text-to-image synthesis lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness.
Approach:	They propose a plug-and-play multi-agent system called GenPilot that integrates error analysis, clustering-based adaptive exploration, fine-grained verification and a memory module for iterative optimization.
Outcome:	The proposed method improves text consistency and structural coherence on images with a plug-and-play system.

Copied to clipboard

WenHao Wang, Haoting Shi, Mengying Yuan, Yiquan Lin, Panrong Tong, Hanzhang Zhou, Guangyi Liu, Pengxiang Zhao, Yue Wang, Siheng Chen

Can Public Large Language Models Help Private Cross-device Federated Learning? (2024.findings-naacl)

Challenge:	a lack of benchmarks capture real-world, cross-platform heterogeneity in GUI training . traditional methods to train GUI agents rely on centralized data collection and manual labeling .
Approach:	They propose a benchmark for developing and evaluating federated GUI agents across mobile, web and desktop platforms.
Outcome:	The proposed benchmarks show that cross-platform collaboration improves performance and identify platform and OS as the most influential factors.

Copied to clipboard

Boxin Wang, Yibo Zhang, Yuan Cao, Bo Li, Hugh McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation (2024.acl-long)

Challenge:	Recent studies have shown that public data can be used to improve privacy-utility trade-offs for large and small language models.
Approach:	They propose to use large-scale public data to help differentially private FL training . they propose a distribution matching algorithm with theoretical grounding to sample public data close to private data distribution .
Outcome:	The proposed method is efficient and effective for training private models by taking advantage of public data.

Copied to clipboard

Xinglin Wang, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition (2022.findings-naacl)

Challenge:	Existing methods to improve output quality without aggregating input tokens are limited by the complexity of aggregation of responses.
Approach:	They propose to extract and integrate segment-level commonalities from candidate samples to enhance performance of LLMs in open-ended and reasoning tasks.
Outcome:	The proposed method improves performance on reasoning, code generation and mathematical reasoning tasks without requiring additional models and overlooking the knowledge present among the candidates.

Copied to clipboard

Yingjie Gu, Xiaoye Qu, Zhefeng Wang, Yi Zheng, Baoxing Huai, Nicholas Jing Yuan

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation (2025.findings-emnlp)

Challenge:	Named entity recognition (NER) is a system for identifying text spans pertaining to specific entity types.
Approach:	They propose a method to investigate the regularity of Chinese NER's entity mentions by a regularity-aware module and a periodicity-gnostic module.
Outcome:	The proposed model significantly outperforms previous state-of-the-art methods on three benchmark datasets and a practical medical dataset.

Copied to clipboard

Wenkai Guo, Xuefeng Liu, Haolin Wang, Jianwei Niu, Shaojie Tang, Jing Yuan

Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation (2025.findings-emnlp)

Challenge:	federated learning (FL) fine-tunes large language models with local data, but organizations are reluctant to share local data.
Approach:	They propose a framework for fine-tuning large language models with local data . they propose centralized fine- tuning with local datasets is a good idea .
Outcome:	The proposed framework allows clients to retain local data while sharing only model parameters for training.

Copied to clipboard

Qingsong Wang, Tao Wu, Wang Lin, Yueying Feng, Gongsheng Yuan, Chang Yao, Jingyuan Chen

Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts (2026.acl-long)

Challenge:	Large Language Models struggle to adapt content to users with differing cognitive capacities, leading to cognitive misalignment.
Approach:	They propose a cognitive-level alignment framework that aligns both knowledge complexity and presentation style with user cognition.
Outcome:	The proposed framework aligns knowledge complexity and presentation style with user cognition.

Copied to clipboard

Xiaowei Yuan, Ziyang Huang, Zhao Yang, Yequan Wang, Jun Zhao, Kang Liu

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models (2026.acl-long)

Challenge:	Retrieval-Augmented Generation (RAG) has become a standard paradigm for grounding Large Language Models (LLMs) however, performance degrades substantially when faced with noisy, outdated, or conflicting retrieved information.
Approach:	They propose a framework that explicitly elicits the model’s parametric knowledge as prior information to guide reasoning on retrieved documents.
Outcome:	The proposed framework achieves robust performance across varying degrees of external inconsistency and noise.

Copied to clipboard

Zixuan Weng, Jinghuai Zhang, Kunlin Cai, Ying Li, Peiran Wang, Yuan Tian

Separating Context and Pattern: Learning Disentangled Sentence Representations for Low-Resource Extractive Summarization (2023.findings-acl)

Challenge:	Existing methods for inference-time steering fail to be effective, utility-preserving and training-efficient due to rigid, one-size-fits-all designs and limited adaptability.
Approach:	They propose a steering framework that decomposes inference-time steering into two stages . they propose 'conditional steering' mechanism that preserves model utility by avoiding unnecessary steering . a 'mixture-of-Steering-Experts' mechanism captures multimodal nature of desired steering behaviors .
Outcome:	The proposed framework outperforms the state-of-the-art methods on safety and truthfulness benchmarks.

Copied to clipboard

Ruifeng Yuan, Shichao Sun, Zili Wang, Ziqiang Cao, Wenjie Li

Prompt Tuning for Discriminative Pre-trained Language Models (2022.findings-acl)

Challenge:	Context information is one of the key factors for extractive summarization, but other factors can be used to identify sentence importance.
Approach:	They propose to disentangle context and pattern factors for extractive summarization . they separate context and patterns for a better generalization ability in low-resource setting .
Outcome:	The proposed model can be used in the zero-shot setting or fine-tuned in the few-shot settings.

Copied to clipboard

Yuan Yao, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, Jianyong Wang

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning (2025.findings-emnlp)

Challenge:	Recent studies have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing tasks.
Approach:	They propose a prompt tuning framework that reformulates NLP tasks into a discriminative language modeling problem.
Outcome:	The proposed framework improves on text classification and question answering tasks and prevents unstable tuning problems in low-resource settings.

Copied to clipboard

Yue Xin, Chen Shen, Shaotian Yan, Xiaosong Yuan, Yaoming Wang, Xiaofeng Zhang, Chenxi Huang, Jieping Ye

Construction of the Literature Graph in Semantic Scholar (N18-3)

Challenge:	Chain-of-Thought prompting improves the math reasoning capability of large language models.
Approach:	They propose a method for attribution of component-level contributions in CoT reasoning using Shapley value and a stratified sampling algorithm that significantly reduces computational complexity.
Outcome:	The proposed method reduces computational complexity and provides robust correlations with model performance.

Copied to clipboard

Waleed Ammar, Dirk Groeneveld, Chandra Bhagavatula, Iz Beltagy, Miles Crawford, Doug Downey, Jason Dunkelberger, Ahmed Elgohary, Sergey Feldman, Vu Ha, Rodney Kinney, Sebastian Kohlmeier, Kyle Lo, Tyler Murray, Hsu-Han Ooi, Matthew Peters, Joanna Power, Sam Skjonsberg, Lucy Lu Wang, Chris Wilhelm, Zheng Yuan, Madeleine van Zuylen, Oren Etzioni

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models (2024.emnlp-main)

Challenge:	Fig. 1 summarizes a scalable system for organizing published scientific literature into a heterogeneous graph . authors describe methods used to enable semantic features in www.semanticscholar.org .
Approach:	They describe a scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery.
Outcome:	The proposed system can be deployed on a scalable platform and report empirical results for each task.

Copied to clipboard

Yuxuan Wan, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He, Wenxiang Jiao, Michael Lyu

Beyond Single View: A Comprehensive Benchmark for Medical Multimodal Large Language Models on Multi-Image Understanding (2026.acl-long)

Challenge:	LogicAsker examines and improves the reasoning abilities of large language models such as ChatGPT and GPT-4.
Approach:	They propose a set of atomic reasoning skills grounded in propositional and predicate logic to examine and improve the reasoning abilities of large language models such as ChatGPT and GPT-4.
Outcome:	The proposed approach improves reasoning abilities in large language models such as ChatGPT and GPT-4 by up to 5%.

Copied to clipboard

Dexuan Xu, Yuan Jiayin, Jianing Wang, Yanyuan Chen, Hanpin Wang, Yu Huang

MUX-PLMs: Data Multiplexing for High-throughput Language Models (2023.findings-emnlp)

Challenge:	Existing benchmarks for multimodal large language models are limited to multiview diagnostics.
Approach:	They propose a benchmark specifically designed for medical multi-image understanding that evaluates MLLMs across four dimensions.
Outcome:	The proposed model performs better in multi-image contexts than open-source models . the model perform better when processing increased visual loads than closed-source ones .

Copied to clipboard

Vishvak Murahari, Ameet Deshpande, Carlos Jimenez, Izhak Shafran, Mingqiu Wang, Yuan Cao, Karthik Narasimhan

K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce (2021.findings-emnlp)

Challenge:	MUX-PLMs are high-throughput pre-trained language models that can be fine-tuned for any downstream task to yield high-performance.
Approach:	They propose to train language models with data multiplexing to achieve 2x/5x inference speedup . they use multiplexers to entangle and disentangle inputs to achieve the same performance .
Outcome:	MUX-PLMs achieve 2x/5x inference speedup with 1-4 % drop on broad suite of tasks.

Copied to clipboard

Song Xu, Haoran Li, Peng Yuan, Yujia Wang, Youzheng Wu, Xiaodong He, Ying Liu, Bowen Zhou

Memp: Exploring Agent Procedural Memory (2026.findings-acl)

Challenge:	Existing pre-trained language models are not explicitly aware of domain-specific knowledge, which is essential for downstream tasks in many domains, such as tasks in e-commerce scenarios.
Approach:	They propose a knowledge-injected pre-trained language model that can be transferred to both natural language understanding and generation tasks.
Outcome:	The proposed model significantly outperforms baselines across the board in e-commerce scenarios.

Copied to clipboard

Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Challenge:	Large Language Models (LLMs) based agents suffer from brittle procedural memory that is manually engineered or entangled in static parameters.
Approach:	They propose a procedural-memory repository that distills past agent trajectories into fine-grained, step-by-step instructions and higher-level, script-like abstractions.
Outcome:	The proposed repository can be used to improve agents' performance on travelplanner and Alfworld.

Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation (2022.acl-long)

Copied to clipboard

Yong Cheng, Ankur Bapna, Orhan Firat, Yuan Cao, Pidong Wang, Wolfgang Macherey

Multilinguality

Challenge:	Existing approaches to train multilingual models to learn the inductive bias of a shared vocabulary and set of parameters across languages.
Approach:	They propose to use a multilingual crossover encoder-decoder to fuse language pairs at an instance level to encourage sharing of input and output spaces.
Outcome:	The proposed approach improves quality on English-to-Many, Many-to English and zero-shot translation tasks from +0.5 BLEU up to +5.5 BLUE points.

RBPtool: A Deep Language Model Framework for Multi-Resolution RBP-RNA Binding Prediction and RNA Molecule Design (2025.emnlp-main)

Copied to clipboard

Jiyue Jiang, Yitao Xu, Zikang Wang, Yihan Ye, Yanruisheng Shao, Yuheng Shan, Jiuming Wang, Xiaodan Fan, Jiao Yuan, Yu Li

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety (2026.acl-long)

Challenge:	RNA-binding proteins play key roles in post-transcriptional gene regulation . existing methods focus on shallow sequence features or coarse structural representations . large language models allow for precise modeling and biologically informed de novo RNA design .
Approach:	They extend RPI15223 into a multi-resolution, structure-level RBP-RNA dataset and introduce RBPtool, a framework that fuses sequence and structural information.
Outcome:	The proposed framework achieves state-of-the-art performance on public benchmarks and the RPI15223 dataset while supporting fine-grained level predictions.

Copied to clipboard

Can Jin, Rui Wu, Tong Che, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N. Metaxas

SOLAR: Serendipity Optimized Language Model Aligned for Recommendation (2025.findings-emnlp)

Challenge:	OpenAI introduces deliberative alignment (DA) to enhance safety of its o-series models, but effectiveness of this approach in open-source LLMs is understudied.
Approach:	They propose a case-augmented deliberative alignment method for large language models . they propose to use reinforcement learning on self-generated safety reasoning chains .
Outcome:	The proposed method avoids narrowly enumerated rules and allows broader adaptability.

Copied to clipboard

Zichen Yuan, Lifan Sun, Yucen Zhuang, Yue Wang, Xinyuan Song, Tianqi Xu, Siyuan Li, Junchen Fu, Youhua Li, Sirui Hong, Jiaqi Chen, Joemon M. Jose, Yongxin Ni

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization (2026.findings-acl)

Challenge:	Large Language Models have shown strong potential in recommendation tasks . however, their application to serendipity-oriented recommendations remains challenging .
Approach:	They propose a domain-adaptive instruction tuning method that aligns Large Language Models with recommendation tasks.
Outcome:	The proposed framework bridges the domain gap between LLMs and recommendation tasks.

Copied to clipboard

Mengyi Deng, Zhiwei Li, Xin Li, Tingyu Zhu, Yulan Yuan, Zhijiang Guo, Wei Wang

Accelerating LLM Fine-Tuning via Embedding Knowledge Transfer (2026.findings-acl)

Challenge:	Existing methods for directional consistency alignment of large language models are limited . a recent study suggests reverse supervision as a complement to forward reasoning .
Approach:	They propose a framework that aggregates supervision signals at the group level and explicitly models direction-aware alignment through multi-candidate comparisons.
Outcome:	The proposed framework achieves 3.2% accuracy improvement across five benchmarks and multiple datasets.

Copied to clipboard

Meishu Peng, Ziyue Zhang, Yi Zhang, Pengyang Wang, Zixuan Yuan, Denghui Zhang

Mulan: A Multi-Level Alignment Model for Video Question Answering (2023.findings-emnlp)

Challenge:	Existing studies on parameter-efficient fine-tuning (PEFT) have produced many state-of-the-art results by adapting LLMs to new tasks, but it requires substantial training data and time to enhance model performance.
Approach:	They propose a parameter-efficient fine-tuning framework which efficiently transfers knowledge from a small expert model to a target large model via embedding layers.
Outcome:	The proposed framework accelerates domain-specific fine-tuning, improves model performance and remains robust across diverse model families and PEFT methods.

Copied to clipboard

Yu Fu, Cong Cao, Yuling Yang, Yuhai Lu, Fangfang Yuan, Dakui Wang, Yanbing Liu

VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models (2026.acl-long)

Challenge:	Existing methods focus on visual-language alignment at the video level, but they do not account for fine-grained semantic interaction between video and text.
Approach:	They propose a multi-level Alignment Model for Video Question Answering that establishes alignment between visual and textual modalities at the object-level, frame-level and video-level.
Outcome:	The proposed model outperforms state-of-the-art methods even with a small amount of extra visual-language pre-training data and a reduced number of trainable parameters.

Copied to clipboard

Huawei Ji, Yuanhao Sun, Yuan Jin, Cheng Deng, Jiaxin Ding, Luoyi Fu, Xinbing Wang

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection (2023.acl-long)

Challenge:	Existing methods for visual token pruning rely on predefined configurations without determining whether they achieve optimal performance.
Approach:	They propose a framework that formulates visual token pruning as a Pareto configuration optimization problem to automatically identify optimal configurations.
Outcome:	The proposed framework approximates the empirical Pareto frontier obtained through grid search and generalizes well across pruning methods and VLM architectures.

Copied to clipboard

Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, Meng Chen

Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)

Challenge:	Existing studies focus on fusing different features but ignore the challenge of modality heterogeneity.
Approach:	They propose a text-guided fusion module with novel Sparse-Attention to reduce the negative impacts of redundant visual elements and a sentiment-based congruity constraint task to calibrate the feature shift in the representation space.
Outcome:	The proposed model is competitive against existing methods and achieves state-of-the-art results on two public benchmark datasets.

Copied to clipboard

Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)

Challenge:	Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning.
Approach:	They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning.
Outcome:	The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.

Copied to clipboard

Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou

PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion (2022.findings-emnlp)

Challenge:	Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support.
Approach:	They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims .
Outcome:	The proposed benchmark evaluates behavioral biases of large language models across economic scenarios.

Copied to clipboard

Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Challenge:	Pretrained language models (LMs) are a powerful transfer learning approach for knowledge graph (KG) completion.
Approach:	They propose a parameter-lite transfer learning approach for pretrained language models for knowledge graph (KG) completion.
Outcome:	The proposed model outperforms the state-of-the-art models on a knowledge graph completion benchmark by tuning 1% of the parameters.

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models (2025.naacl-long)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Yimu Wang, Shuai Yuan, Bo Xue, Xiangru Jian, Wei Pang, Mushi Wang, Ning Yu

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning (2026.findings-acl)

Challenge:	Recent advances in video-text retrieval models have limited training data annotations.
Approach:	They propose a Video-Text Retrieval Paradigm with Relevance-based Augmentation which enhances video and text data using large foundation models to learn more generalized features.
Outcome:	The proposed method improves video-text retrieval performance over existing methods.

Copied to clipboard

Xiaoyun Zhang, Xiaojian Yuan, Di Huang, Wang You, Chen Hu, Jingqing Ruan, Kejiang Chen, Xing Hu

CRSLab: An Open-Source Toolkit for Building Conversational Recommender System (2021.acl-demo)

Challenge:	Reasoning ability is a defining capability of Large Language Models (LLMs), but RLVR training suffers from policy entropy collapse, hindering exploration and limiting reasoning performance.
Approach:	They propose a framework that dynamically balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.
Outcome:	The proposed framework outperforms baselines on multiple mathematical reasoning benchmarks.

Copied to clipboard

Kun Zhou, Xiaolei Wang, Yuanhang Zhou, Chenzhan Shang, Yuan Cheng, Wayne Xin Zhao, Yaliang Li, Ji-Rong Wen

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks (2025.naacl-long)

Challenge:	Existing studies on conversational recommender systems lack a unified and standardized implementation or comparison.
Approach:	They propose to use a unified framework and highly-decoupled modules to develop CRSs.
Outcome:	The proposed framework collects 6 commonly used human-annotated CRS datasets and implements 19 models that include advanced techniques such as graph neural networks and pre-training models.

Copied to clipboard

Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Challenge:	Large visionlanguage models (LVLMs) are a powerful visual-language reasoning tool.
Approach:	They propose to integrate attention analysis with LLaVA-CAM to determine interactions between visual representations.
Outcome:	The proposed approach can be used to determine interactions between visual representations.

Copied to clipboard

Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)

Challenge:	Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach:	They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome:	The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.

Copied to clipboard

Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang

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

Challenge:	Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis.
Approach:	They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy.
Outcome:	The proposed method surpasses existing OT methods in privacy protection and model performance.

Copied to clipboard

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

ReMamba: Equip Mamba with Effective Long-Sequence Modeling (2025.findings-emnlp)

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

Copied to clipboard

Danlong Yuan, Jiahao Liu, Bei Li, Huishuai Zhang, Jingang Wang, Xunliang Cai, Dongyan Zhao

An Empirical Study on Neural Keyphrase Generation (2021.naacl-main)

Challenge:	Mamba models demonstrate superior inference efficiency and competitive performance on short-context tasks, but their capacity to comprehend long contexts is limited compared to transformer-based models.
Approach:	They propose a model which incorporates selective compression and adaptation techniques within a two-stage re-forward process, incurring minimal additional inference costs overhead.
Outcome:	The proposed model improves on the LongBench and L-Eval benchmarks by 3.2 and 1.6 points and attains performance almost on par with same-size transformer models.

Copied to clipboard

Rui Meng, Xingdi Yuan, Tong Wang, Sanqiang Zhao, Adam Trischler, Daqing He

Training-Free Adaptive Speculative Decoding via Linguistic Priors (2026.findings-acl)

Challenge:	Recent years have seen a flourishing of neural keyphrase generation (KPG) works, including the release of several large-scale datasets and a host of new models to tackle them.
Approach:	They propose to compare the generalizability of KPG models with other models by analyzing the most crucial factors that may affect their generalizarability.
Outcome:	The proposed model can be used to predict keyphrases from a set of input sequences, and it can be compared with existing models.

Copied to clipboard

Jingyi Wang, Jiaqi Huang, Zunnan Xu, Jun Zhou, Kehong Yuan, Xiang Qian

Syntactic Text Processing

Challenge:	Speculative decoding (SPD) is a promising technique to accelerate Large Language Models (LLMs). current approaches neglect the inherent heterogeneity of natural language and fail to distinguish between semantically-rich content and structurally-predictable syntax.
Approach:	They propose a training-free framework that leverages linguistic priors to enable adaptive drafting and verification.
Outcome:	The proposed framework significantly accelerates inference without additional training.

Dr. Assistant: Enhancing Clinical Diagnostic Inquiry via Structured Diagnostic Reasoning Data and Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Yue Guo, Fanfu Wang, Jianwei Lv, Xincheng Shi, Yuchen Li, Youya Wang, Yunsheng Zeng, Yujing Liu, Yunhao Qiao, Gen Li, Junfeng Wang, Bo Yuan

Bypassing Neural Evaluations for Fast Audio Editing via Adaptive Trajectory Extrapolation (2026.findings-acl)

Challenge:	Clinical Decision Support Systems (CDSSs) provide reasoning and inquiry guidance for physicians, yet they face high maintenance costs and low generalization capability.
Approach:	They propose a clinical diagnostic model with clinical reasoning and inquiry skills, the Dr. Assistant, and a pipeline to capture abstract reasoning logic.
Outcome:	The proposed model outperforms open-source models and achieves competitive performance to closed-source model.

Copied to clipboard

Xiaoqian Liu, Zhengkun Ge, Jianjin Wang, Haoran Zhang, Yuan Ge, Kaiyan Chang, Chen Xu, Tong Xiao, Zhengtao Yu, Linfeng Zhang, JingBo Zhu

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing (2026.acl-long)

Challenge:	Recent advances in audio diffusion models have significantly improved text-to-audio editing via inversion techniques, but these models typically rely on dense, fixed-step sampling trajectories to maintain structural integrity.
Approach:	They propose a model-agnostic Adaptive Trajectory Extrapolation framework that accelerates inversion-based editing process by dynamically evaluating only the most critical generative phases.
Outcome:	The proposed framework achieves a 3.9 speedup with negligible loss in fidelity.

Copied to clipboard

Wenhao Yuan, Chenchen Lin, Jian Chen, Jinfeng Xu, Xuehe Wang, Edith Cheuk-Han Ngai

VisCGEC: Benchmarking the Visual Chinese Grammatical Error Correction (2025.naacl-long)

Challenge:	Existing approaches to reasoning faithfulness violate constraints, authors say . a science fantasy series and companion books are among the books .
Approach:	They propose a framework that enforces verification over internal belief states within the agent before action commitment, achieving faithful reasoning.
Outcome:	The proposed framework improves reasoning faithfulness while preserving competitive end-task performance.

Copied to clipboard

Xiaoman Wang, Dan Yuan, Xin Liu, Yike Zhao, Xiaoxiao Zhang, Xizhi Chen, Yunshi Lan

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)

Challenge:	Existing studies on Chinese grammatical error correction ignore multi-modality and faked errors, which pushes techniques far away from real-world scenarios.
Approach:	They propose to benchmark Chinese grammatical error correction for Chinese as a foreign language learner (CFL) using a dataset, they propose to use two CGEC frameworks to conduct experiments .
Outcome:	The proposed approach achieves an F 0.5 score of only 28.9%.

Copied to clipboard

Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, Maosong Sun

Low-Resource NLP

Challenge:	Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans.
Approach:	They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers.
Outcome:	The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans.

Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)

Copied to clipboard

Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Li Linwei, Yilin Yue, Shiqiang Wang, Jiayan Li, Wu Yihang, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Hamid Alinejad-Rokny, Chengming Li, Shiwen Ni, Yuan Lin, Min Yang

How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models (2025.emnlp-main)

Challenge:	Existing datasets and benchmarks focus only on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios.
Approach:	They propose a bilingual IP task taxonomy and a large-scale bilingual benchmark to evaluate LLMs in real-world IP practice.
Outcome:	The proposed model achieves only 75.8% accuracy, indicating room for improvement . open-source IP and law-oriented models lag behind closed-source general-purpose models .

Copied to clipboard

Kangtao Lv, Haibin Chen, Yujin Yuan, Langming Liu, Shilei Liu, Yongwei Wang, Wenbo Su, Bo Zheng

On the Emotion Understanding of Synthesized Speech (2026.acl-long)

Challenge:	Recent studies show that strategically infusing domain knowledge during pretraining can substantially improve downstream performance.
Approach:	They propose a knowledge infusion scaling law that predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.
Outcome:	The proposed model predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.

Copied to clipboard

Yuan Ge, Haishu Zhao, AoKai Hao, Junxiang Zhang, Bei Li, Xiaoqian Liu, Chenglong Wang, Jianjin Wang, Bingsen Zhou, Bingyu Liu, JingBo Zhu, Zhengtao Yu, Tong Xiao

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

Challenge:	Existing models for emotion understanding do not capture fundamental features of synthesized speech.
Approach:	They evaluate emotion recognition models on synthesized speech using SER models and generative models.
Outcome:	The proposed model can't generalize to synthesized speech because of speech token prediction . generative models tend to infer emotion from textual semantics while ignoring paralinguistic cues.

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

StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following (2025.findings-acl)

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

Copied to clipboard

Jinnan Li, Jinzhe Li, Yue Wang, Yi Chang, Yuan Wu

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)

Challenge:	Existing evaluation benchmarks focus on fine-grained constraint satisfaction and domain-specific capability assessment, yet overlook the crucial structural dependencies between dialogue turns that distinguish multi-turn from single-turn interactions.
Approach:	They propose a multi-turn instruction following benchmark with structural flow modeling that defines an innovative structural flow framework with six fundamental inter-turn relationships.
Outcome:	The proposed model is based on a framework with six fundamental inter-turn relationships and is able to analyze and generate specific dialogue flows tailored to specific scenarios.

Copied to clipboard

Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System (2022.findings-emnlp)

Challenge:	Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models.
Approach:	They propose a method that conducts customized evaluation tailored to each target model.
Outcome:	The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models.

Copied to clipboard

Tong Zhang, Yong Liu, Boyang Li, Zhiwei Zeng, Pengwei Wang, Yuan You, Chunyan Miao, Lizhen Cui

Slot Transferability for Cross-domain Slot Filling (2021.findings-acl)

Challenge:	Existing open-domain dialogue systems conduct one-session conversations, but multi-session MSCs are under-investigated.
Approach:	They propose a History-Aware Hierarchical Transformer for multi-session open-domain dialogue . they propose to encode history conversations into a history memory and leverage historical information to generate well-informed responses.
Outcome:	The proposed model outperforms baseline models on a large-scale MSC dataset.

Copied to clipboard

Hengtong Lu, Zhuoxin Han, Caixia Yuan, Xiaojie Wang, Shuyu Lei, Huixing Jiang, Wei Wu

Semantic Parsing

Challenge:	Existing work on slot filling uses labeled data from source domains to train a model for target domains.
Approach:	They propose a model-agnostic Slot Transferability Measure (STM) to evaluate the transferability from a source slot to a target slot.
Outcome:	The proposed method outperforms state-of-the-art models on multiple datasets and models.

BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications (2026.findings-acl)

Copied to clipboard

Jianing Hao, Yuhe Wu, Yuanjian Xu, Shichang Meng, Shuai Yuan, Wei Zeng, Zixuan Wang, Guang Zhang

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization (2025.emnlp-main)

Challenge:	Existing benchmarks focus on narrow tasks and leave a fundamental question unanswered . Existing models only focus on specific tasks, requiring rigorous reasoning and knowledge .
Approach:	They propose a benchmark to connect theoretical foundations with practical business knowledge and applications.
Outcome:	The benchmark systematically evaluates both open-source and commercial LLMs . it reveals how theoretical knowledge translates into practical performance in business .

Copied to clipboard

Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Ranjie Duan, Xiaoshuang Jia, Shaowei Yuan, Simeng Qin, Zhiqiang Wang, Xiaojun Jia

Assessing the Efficacy of Grammar Error Correction: A Human Evaluation Approach in the Japanese Context (2024.lrec-main)

Challenge:	Existing methods to jailbreak Large Vision Language Models do not consider interaction between images and text.
Approach:	They propose a prior-guided bimodal interactive black-box jailbreak attack for toxicity maximization that exploits the interaction of images and text.
Outcome:	The proposed method outperforms state-of-the-art jailbreak methods in black box scenarios and in closed-source LVLMs.

Copied to clipboard

Qiao Wang, Zheng Yuan

Syntactic Text Processing

Challenge:	Using an automatic annotation toolkit, we evaluated the performance of the sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students’ writing samples.
Approach:	They evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model using Japanese university students’ writing samples.
Outcome:	The proposed model shows a high precision but conservativeness in error detection and correction.

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)

Copied to clipboard

Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu

ACRM: Multi-Agent Trajectory Learning for Automated Credit Risk Model Refreshing in Production (2026.acl-industry)

Challenge:	a recent study shows that large language models have limited generalization in low-resource languages like Chinese.
Approach:	They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private .
Outcome:	The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language.

Copied to clipboard

Liangzu Liu, Mengzhe Ruan, Xiaotian Chen, null HaonanChen, null XudongNiu, Wendi Yuan, null YuechenLi, Yang Liu, Guanjun Wang

Challenge:	Credit risk models suffer from rapid performance decay due to distribution shifts, requiring frequent updates to meet strict operational guardrails.
Approach:	They propose a multi-agent framework that treats model refreshing as a learnable trajectory of agent interactions.
Outcome:	The proposed framework reduces the average model refresh cycle from weeks to 1.1 days and iteration rounds by 65% while maintaining superior stability metrics.

Event Graph based Sentence Fusion (2021.emnlp-main)

Copied to clipboard

Ruifeng Yuan, Zili Wang, Wenjie Li

FineRAG: Fine-grained Retrieval-Augmented Text-to-Image Generation (2025.coling-main)

Challenge:	Sentence fusion is a conditional generation task that merges related sentences into a coherent text.
Approach:	They propose to build an event graph from the input sentences to capture related events in a structured way and use the constructed event graph to guide sentence fusion.
Outcome:	The proposed method achieves state-of-the-art on two datasets . it is based on the input sentences and shows that it is effective .

Copied to clipboard

Huaying Yuan, Ziliang Zhao, Shuting Wang, Shitao Xiao, Minheng Ni, Zheng Liu, Zhicheng Dou

MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applications (2025.emnlp-main)

Challenge:	Recent advances in text-to-image generation still exhibit limitations in terms of knowledge access.
Approach:	They propose a fine-grained retrieval-augmented image generation model that breaks down the retrieval task into four critical stages: query decomposition, candidate selection, retrieval augmented diffusion, and self-reflection.
Outcome:	The proposed method significantly reduces noise associated with retrieval-augmented image generation and performs better in complex, open-world scenarios.

Copied to clipboard

Zike Yuan, Ming Liu, Hui Wang, Bing Qin

Linguistic Theories

Challenge:	Existing methods for solving complex problems are expensive and inefficient when handling large-scale, high-complexity problems.
Approach:	They propose a multi-agent framework that decomposes complex problems through agent collaboration by mapping implicitly expressed graph data into clear, structured graph representations and dynamically selecting the most suitable algorithm based on problem constraints and graph structure scale.
Outcome:	The proposed framework outperforms state-of-the-art methods on multiple benchmarks with robust performance on both closed- and open-source models.

Identifying the Achilles’ Heel: An Iterative Method for Uncovering Factual Errors in Large Language Models (2026.findings-acl)

Copied to clipboard

Wenxuan Wang, Yuk-Kit Chan, Zixuan Ling, Shi Juluan, Youliang Yuan, Jen-tse Huang, Yifei Zhang, Wenxiang Jiao, Zhaopeng Tu, Michael R. Lyu

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)

Challenge:	Current methods for evaluating LLMs’ veracity are limited by the need for extensive human labor, test data contamination, or limited scope, hindering efficient and effective exposure of errors.
Approach:	They propose a framework that extracts fact triplets to generate diverse question types using rule-based natural language processing techniques.
Outcome:	The proposed framework can trigger factual errors in up to 55% of questions in large LLMs while maintaining coverage of questions.

Copied to clipboard

Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu

BADGE: Speeding Up BERT Inference after Deployment via Block-wise Bypasses and Divergence-based Early Exiting (2023.acl-industry)

Challenge:	Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts.
Approach:	They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs.
Outcome:	The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks.

Copied to clipboard

Wei Zhu, Peng Wang, Yuan Ni, Guotong Xie, Xiaoling Wang

InfiMM: Advancing Multimodal Understanding with an Open-Sourced Visual Language Model (2024.findings-acl)

Challenge:	Recent years have witnessed the rise of many pre-trained language models (PLMs) such as GPT (Radford et al., 2019) and XLNet (Yang e.t al, 2019).
Approach:	They propose a framework which consists of two off-the-shelf methods for improving PLMs’ early exiting.
Outcome:	The proposed method can reduce the average latency of pre-trained language models and work with other inference speed-up methods like model pruning.

Copied to clipboard

Haogeng Liu, Quanzeng You, Yiqi Wang, Xiaotian Han, Bohan Zhai, Yongfei Liu, Wentao Chen, Yiren Jian, Yunzhe Tao, Jianbo Yuan, Ran He, Hongxia Yang

LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following (2023.emnlp-main)

Challenge:	InfiMM is a multimodal large language model that adapts to complex vision-language tasks.
Approach:	They present a Multimodal Large Language Model that adapts to intricate vision-language tasks using large-scale training data and comprehensive training strategies.
Outcome:	Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding.

Copied to clipboard

Cheng-Fu Yang, Yen-Chun Chen, Jianwei Yang, Xiyang Dai, Lu Yuan, Yu-Chiang Wang, Kai-Wei Chang

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)

Challenge:	Embodied Instruction Following has shown an impressive success rate when the environment has been seen in training, but when deployed in an unseen environment, it tends to struggle when deployed with an unsightly environment.
Approach:	They propose to explicitly align the agent’s hidden states with the instructions via contrastive learning to bridge the semantic gap between high-level language instructions and the agent's low-level action space.
Outcome:	The proposed meta-actions achieve a 4.5% success rate in unseen environments compared to a strong multi-modal Transformer baseline .

Copied to clipboard

Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)

Challenge:	Current outcome-centric verification paradigms neglect potential errors in the derivation process.
Approach:	They propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
Outcome:	The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models.

Copied to clipboard

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction (2025.emnlp-main)

Challenge:	Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities.
Approach:	They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments.
Outcome:	The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments.

Copied to clipboard

Mengying Yuan, WenHao Wang, Zixuan Wang, Yujie Huang, Kangli Wei, Fei Li, Chong Teng, Donghong Ji

Explainability & Interpretability in NLP

Challenge:	Despite the development of many subdirections, Cross-Document Cross-Lingual NLI remains largely unexplored.
Approach:	They propose a novel paradigm that extends traditional NLI capabilities to multi-document, multilingual scenarios by integrating RST-enhanced graph fusion with interpretability-aware prediction.
Outcome:	The proposed method improves on existing models and document-level NLI to multi-document, multilingual scenarios.

Improving Zero-shot LLM Re-Ranker with Risk Minimization (2024.emnlp-main)

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Yequan Wang, Jun Zhao, Kang Liu

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

Challenge:	Large Language Models (LLMs) are effective Query Likelihood Models, but their estimation is biased and the model's accuracy is poor.
Approach:	They propose a framework which leverages Bayesian decision theory to quantify and mitigate this bias.
Outcome:	The proposed framework improves re-ranking, especially in improving the Top-1 accuracy.

Copied to clipboard

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

A Speaker-Aware Co-Attention Framework for Medical Dialogue Information Extraction (2022.emnlp-main)

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

Copied to clipboard

Yuan Xia, Zhenhui Shi, Jingbo Zhou, Jiayu Xu, Chao Lu, Yehui Yang, Lei Wang, Haifeng Huang, Xia Zhang, Junwei Liu

Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents (2025.emnlp-main)

Challenge:	With the development of medical digitization, the extraction and structuring of electronic medical records (EMRs) have become challenging but fundamental tasks.
Approach:	They propose a speaker-aware dialogue encoder with multi-task learning which takes the speaker's identity into account and a co-attention fusion network to aggregate the utterance information.
Outcome:	The proposed framework outperforms the state-of-the-art methods on the public medical dialogue extraction datasets to demonstrate its superiority.

Copied to clipboard

Haochen Sun, Shuwen Zhang, Lujie Niu, Lei Ren, Hao Xu, Hao Fu, Fangkun Zhao, Caixia Yuan, Xiaojie Wang

Does ChatGPT Know That It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT (2024.lrec-main)

Challenge:	Large Language Models (LLMs) based agent systems have made great strides in real-world applications beyond traditional NLP tasks.
Approach:	They propose a new LLM-based Multi-Agent System benchmark, Collab-Overcooked, built on the popular Overcooked-AI game with more applicable and challenging tasks in interactive environments.
Outcome:	The proposed benchmark provides a multi-agent framework supporting diverse tasks and objectives and encourages collaboration through natural language communication.

Copied to clipboard

Youliang Yuan, Wenxuan Wang, Qingshuo Guo, Yiming Xiong, Chihao Shen, Pinjia He

Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading (2023.findings-emnlp)

Challenge:	Recent performance of ChatGPT in downstream tasks is questionable, but does it know that it does not know?
Approach:	They propose to use three types of proxy confidence to evaluate ChatGPT's black-box calibration ability.
Outcome:	The proposed model exhibits a positive correlation with accuracy in TruthfulQA and a negative correlation in the ModAr dataset.

Copied to clipboard

Yangyang Luo, Shiyu Tian, Caixia Yuan, Xiaojie Wang

A Novel Two-step Fine-tuning Framework for Transfer Learning in Low-Resource Neural Machine Translation (2024.findings-naacl)

Challenge:	Recent research has explored how to improve the abilities of decision-making and question generation.
Approach:	They propose a pipeline framework that aligns the document and user-provided information in an explicit way, makes decisions using a lightweight many-to-many entailment reasoning module and generates follow-up questions based on the document.
Outcome:	The proposed framework achieves state-of-the-art in micro-accuracy and ranks the first place on the public leaderboard of the CMR benchmark dataset ShARC.

Copied to clipboard

Yuan Gao, Feng Hou, Ruili Wang

SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing (2025.acl-long)

Challenge:	Existing transfer learning methods for neural machine translation use a well-trained translation model to initialize a child model with corresponding datasets.
Approach:	They propose a two-step fine-tuning framework for transfer learning in low-resource neural machine translation that adjusts the parent model to fit the child language by using the child source data.
Outcome:	The proposed framework improves on five low-resource translations on high-resolution languages.

Copied to clipboard

Xiangchao Yan, Shiyang Feng, Jiakang Yuan, Renqiu Xia, Bin Wang, Lei Bai, Bo Zhang

Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement (2025.acl-long)

Challenge:	SURVEYFORGE automates survey paper writing, but quality gap between LLM-generated and human-written surveys remains significant.
Approach:	They propose a survey tool that automatically generates and refines human-written surveys.
Outcome:	Experiments show that SURVEYFORGE outperforms previous work such as AutoSurvey in outline quality and content quality.

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Ziyang Huang, Yequan Wang, Siqi Fan, Yiming Ju, Jun Zhao, Kang Liu

Challenge:	Existing approaches to enhance the context-faithfulness of Large Language Models (LLMs) ignore the fundamental mechanism of how contextual information is processed within LLMs’ internal states.
Approach:	They propose a method that enhances the utilization of contextual knowledge within LLMs’ internal representations by employing V-usable information analysis.
Outcome:	The proposed method improves context-faithfulness generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge.

Learning to Ask: When LLM Agents Meet Unclear Instruction (2025.emnlp-main)

Copied to clipboard

Wenxuan Wang, Shi Juluan, Zixuan Ling, Yuk-Kit Chan, Chaozheng Wang, Cheryl Lee, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, Michael R. Lyu

Challenge:	Despite their impressive capabilities, LLMs struggle with complex computations and delivering accurate, timely information.
Approach:	They propose a framework that prompts LLM agents to ask questions when they encounter obstacles due to unclear instructions and an automated evaluation tool called ToolEvaluator.
Outcome:	The proposed framework outperforms existing frameworks for tool learning in the Noisy ToolBench.

Paraphrase Makes Perfect: Leveraging Expression Paraphrase to Improve Implicit Sentiment Learning (2025.coling-main)

Copied to clipboard

Xia Li, Junlang Wang, Yongqiang Zheng, Yuan Chen, Yangjia Zheng

Sentiment Analysis

Challenge:	Existing implicit sentiment learning methods focus on capturing implicit sentiment knowledge individually, without considering the potential connection between implicit and explicit sentiment.
Approach:	They propose an expression paraphrase strategy and a sentiment-consistent contrastive learning mechanism to learn the connections between implicit and explicit sentiment expressions and integrate them into the model.
Outcome:	The proposed method is effective on implicit sentiment analysis on public datasets.

Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment (2025.emnlp-main)

Copied to clipboard

Ahmed Karim, Qiao Wang, Zheng Yuan

Challenge:	Automated Essay Scoring (AES) systems attain near–human agreement on some public benchmarks, but real-world adoption is limited.
Approach:	They propose a distribution-free wrapper that equips any classifier with set-valued outputs enjoying formal coverage guarantees.
Outcome:	The proposed model achieves coverage targets while keeping prediction sets compact.

Exploring Representation-level Augmentation for Code Search (2022.emnlp-main)

Copied to clipboard

Haochen Li, Chunyan Miao, Cyril Leung, Yanxian Huang, Yuan Huang, Hongyu Zhang, Yanlin Wang

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Recent data augmentations for code search are at the raw-data level, which requires additional code analysis and training cost.
Approach:	They propose a general format of representation-level augmentation that unifies existing methods.
Outcome:	The proposed methods can boost the performance of code search models on a large-scale dataset.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data (2024.findings-emnlp)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Yiting Ran, Xintao Wang, Rui Xu, Xinfeng Yuan, Jiaqing Liang, Yanghua Xiao, Deqing Yang

Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs (2025.acl-long)

Challenge:	Existing role-playing models focus on character knowledge and tones, but lack personality-indicative data to capture characters' minds.
Approach:	They propose to enhance role-playing agents (RPAs) via personality-indicative data by asking psychological scales to capture broad aspects of personality traits in individuals.
Outcome:	The proposed model exhibits advanced role-playing capabilities for both general and personality-related evaluations.

Copied to clipboard

Jingcheng Niu, Xingdi Yuan, Tong Wang, Hamidreza Saghir, Amir H. Abdi

Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Models (2026.acl-long)

Challenge:	contextual entrainment occurs across a wide range of language models (LMs) and prompt settings.
Approach:	They hypothesize that there is a circuit of attention heads that corresponds to the phenomenon contextual entrainment . when they "turn off" these heads, the effect of contextual entraining is significantly attenuated.
Outcome:	The proposed method shows that LMs assign higher logits to tokens that have previously appeared in the context prompt, even for random tokens.

Copied to clipboard

Xinyuan Wang, Luozhijie Jin, Bo Wang, Yuan Li, Zhangyue Yin, Xipeng Qiu

Graph Attention Network with Memory Fusion for Aspect-level Sentiment Analysis (2020.aacl-main)

Challenge:	Existing methods for estimating KL divergence using only top-k tokens suffer from high variance or systematic bias.
Approach:	They propose a top-k Importance-weighted KL Estimator that exploits the Zipfian structure of language model distributions by integrating only the top-K tokens.
Outcome:	The proposed estimator outperforms existing estimators on multiple benchmarks while exhibiting lower variance.

Copied to clipboard

Li Yuan, Jin Wang, Liang-Chih Yu, Xuejie Zhang

Sentiment Analysis

Challenge:	Recent studies ignored the syntactic relationship between the aspect and its corresponding context words, leading the model to focus on syntaktically unrelated words mistakenly.
Approach:	They propose to extend the graph convolutional network by assigning different weights to edges of connected words.
Outcome:	The proposed method can improve on five datasets showing that it learns and exploits multiword relations and draws different weights of words to improve performance.

What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge (2026.eacl-long)

Copied to clipboard

Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Steffen Staab, Evgeny Kharlamov

ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games (2023.emnlp-main)

Challenge:	Existing evaluation metrics and lenient answer matching criteria obscure meaningful comparisons.
Approach:	They propose a general method for constructing benchmarks and a method to assess KG-RAG methods under incomplete knowledge.
Outcome:	The proposed method systematically assesses KG-RAG methods under incomplete knowledge.

Copied to clipboard

Ruoyao Wang, Graham Todd, Xingdi Yuan, Ziang Xiao, Marc-Alexandre Côté, Peter Jansen

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards (2026.acl-long)

Challenge:	We show that language models can generate explicit, interpretable, and interactive world models of scientific and common-sense reasoning tasks.
Approach:	They propose a corpus of 32 reasoning-focused text games expressed as hundreds of lines of Python code to facilitate this task.
Outcome:	The proposed games can generate runnable games on unseen topics in 28% of cases.

Copied to clipboard

Youliang Yuan, Qiuyang Mang, Jingbang Chen, Hong Wan, Xiaoyuan Liu, Junjielong Xu, Jen-tse Huang, Wenxuan Wang, Wenxiang Jiao, Pinjia He

PsyMem: Fine-grained Psychological Alignment and Explicit Memory Control for Advanced Role-Playing LLMs (2026.tacl-1)

Challenge:	Existing models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning ability.
Approach:	They propose a Rubric Reward Model that rewards the entire reasoning trajectory against problem-specific rubrics.
Outcome:	The proposed model outperforms outcome-only supervision on four math benchmarks and boosts Verified Pass@1024 from 26.7% to 62.6% and reduces the incidence of Miracle Steps by 71%.

Copied to clipboard

Xilong Cheng, Yunxiao Qin, Yuting Tan, Zhengnan Li, Ye Wang, Hongjiang Xiao, Yuan Zhang

Challenge:	Existing role-playing models rely on superficial textual descriptions or simplistic metrics, inadequately modeling both intrinsic and extrinsic character dimensions.
Approach:	They propose a framework that integrates fine-grained psychological attributes and explicit memory control for role-playing.
Outcome:	The proposed framework outperforms baseline models in human-likeness and character fidelity.

Global Attention Decoder for Chinese Spelling Error Correction (2021.findings-acl)

Copied to clipboard

Zhao Guo, Yuan Ni, Keqiang Wang, Wei Zhu, Guotong Xie

MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning (2024.acl-long)

Challenge:	Existing methods for Chinese spelling error correction focus on local contextual information, thus misleading the user and reducing performance.
Approach:	They propose a global attention decoder that learns the global relationship of correct input characters and candidates of potential error characters.
Outcome:	The proposed method outperforms all competitor models by a large margin of up to 6.2% on three human-annotated datasets.

Copied to clipboard

Chengpeng Li, Zheng Yuan, Hongyi Yuan, Guanting Dong, Keming Lu, Jiancan Wu, Chuanqi Tan, Xiang Wang, Chang Zhou

Curse of Knowledge: Your Guidance and Provided Knowledge are biasing LLM Judges in Complex Evaluation (2025.findings-emnlp)

Challenge:	In math reasoning with large language models, fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective.
Approach:	They propose to fine-tune data augmentation by query evolution and diverse reasoning paths.
Outcome:	The proposed model achieves new state-of-the-art on GSM8K and MATH.

Copied to clipboard

Weiyuan Li, Xintao Wang, Siyu Yuan, Rui Xu, Jiangjie Chen, Qingqing Dong, Yanghua Xiao, Deqing Yang

Challenge:	a recent study has focused on simple settings, but their reliability in complex tasks remains understudied.
Approach:	They propose to use large language models as judges to evaluate reliability in complex tasks . they use a challenge benchmark to expose and quantify Auxiliary Information Induced Biases .
Outcome:	The proposed benchmark exposes and quantifies Auxiliary Information Induced Biases across 12 basic and 3 advanced scenarios.

Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods (2026.acl-long)

Copied to clipboard

Hanzhang Yuan, Mengxuan Hu, Wenhao Zhang, Tianlong Wang, Zhongliang Zhou, Jiasen Lu, Sheng Li

CoTD-PO: Chain-of-Thought Distillation with Preference Optimization (2025.findings-emnlp)

Challenge:	Large Vision-Language Models (LVLMs) excel at visual understanding but face severe computational bottlenecks when processing high-resolution images and long videos due to massive visual token counts.
Approach:	They propose a taxonomy categorizing methods into vision-side, LLM-side and hybrid paradigms and analyze token selection mechanisms and pruning strategy.
Outcome:	The proposed method selectively removes less informative tokens while maintaining performance.

Copied to clipboard

Lujie Niu, Haochen Sun, Fangkun Zhao, Sheng Chen, Zimeng Bai, Jiawei Zhang, Caixia Yuan, Xiaojie Wang

InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (2024.acl-long)

Challenge:	Existing methods for chain-of-thought distillation suffer from a distribution mismatch between teacher-generated training trajectories and the student model's own generative distribution.
Approach:	They propose a framework that shifts the training paradigm from passive imitation to active trajectory exploration by allowing students to sample their own answer paths.
Outcome:	The proposed method outperforms standard CoT distillation baselines while mitigating mode collapse and preserving semantic diversity.

Copied to clipboard

Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, Yanghua Xiao

Challenge:	Existing methods focus on knowledge and linguistic patterns of characters.
Approach:	They propose to evaluate character fidelity of role-playing agents with psychological scales . they propose to use psychological scale to measure personality traits of RPAs based on personality traits.
Outcome:	The proposed model reproduces character fidelity with psychological scales and shows that it is effective in measuring personality traits.

GCIG: GraphRAG-based Cross-document Instruction Generation for Boosting LLM Reasoning (2026.findings-acl)

Copied to clipboard

Xiaoliang Xu, Huang Yuan, Junmei Wang, Can Xu

DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)

Challenge:	Existing methods for fine-tuning large language models struggle in knowledge-intensive domains and complex reasoning tasks due to their limited coverage of single-document knowledge and repetitive content.
Approach:	They propose a GraphRAG-based cross-document instruction generation framework that generates diverse questions through task-aware prompts and context-sensitive retrieval.
Outcome:	The proposed framework outperforms existing methods on knowledge-intensive and multi-hop question-answering tasks.

Copied to clipboard

Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang

Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains (2026.acl-long)

Challenge:	Recent advances in neural theorem-proving resort to large language models and tree searches.
Approach:	They propose a Dynamic-Tree Driven Theorem Solver to accommodate general theoremes by guiding the search procedure with state confidence and proof-level values.
Outcome:	The proposed method outperforms state-of-the-art methods on two popular theorem-proving datasets with a 6.65% improvement on average in terms of success rate.

Copied to clipboard

Zhonghang Yuan, Zhefan Wang, Fang Hu, Zihong Chen, Jinzhe Li, Gang Li, Jie Ying, Huanjun Kong, Songyang Zhang, Nanqing Dong

Do Large Language Models Rank Fairly? An Empirical Study on the Fairness of LLMs as Rankers (2024.naacl-long)

Challenge:	Recent large language models (LLMs) have demonstrated remarkable progress in reasoning, but their applications on knowledge-intensive domains have not been explored due to the scarcity of high-quality verifiable data.
Approach:	They propose a framework that extends reinforcement learning with verifiable rewards (RLVR) to knowledge-intensive domains through automated verififiability data synthesis while enabling verification of the LLM's reasoning process.
Outcome:	Extensive experiments show that the proposed framework enhances the reasoning of large language models in knowledge-intensive domains without significantly compromising the model’s general capabilities.

Copied to clipboard

Yuan Wang, Xuyang Wu, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang

Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs (2026.findings-acl)

Challenge:	Recent studies have shown that Large Language Models (LLMs) are more efficient in natural language understanding tasks.
Approach:	They evaluate large language models (LLMs) using a TREC Fair Ranking dataset . they assess fairness from both user and content perspectives .
Outcome:	The proposed model outperforms the existing models in the fair ranking task.

Copied to clipboard

Linhao Zhang, Yuhan Song, Aiwei Liu, Chuhan Wu, Sijun Zhang, Wei Jia, Yuan Liu, Houfeng Wang, Zhou Xiao

VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (2025.findings-emnlp)

Challenge:	Recent Audio Large Language Models (AudioLLMs) excel at reasoning tasks, but struggle at elementary auditory perception.
Approach:	They propose a framework that organizes audio information into three explicit components in a unified JSON format.
Outcome:	The proposed framework boosts fine-grained perception by 10.9% on MMSU over state-of-the-art models while preserving robust reasoning capabilities.

Copied to clipboard

Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu

Challenge:	Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery.
Approach:	They propose a state-based function call approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions.
Outcome:	The proposed approach outperforms traditional function calling approaches, achieving superior execution accuracy and reduced latency.

McQueen: a Benchmark for Multimodal Conversational Query Rewrite (2022.emnlp-main)

Copied to clipboard

Yifei Yuan, Chen Shi, Runze Wang, Liyi Chen, Feijun Jiang, Yuan You, Wai Lam

CtrlNews: LLM-based Multi-Agent Controllable News Writing via Knowledge Gravitational Field (2025.findings-emnlp)

Challenge:	Recent studies have focused on conversational-related tasks that involve drawing information from more than one modality.
Approach:	They propose a task of multimodal conversational query rewrite which performs query . they collect a large-scale visual conversation dataset and benchmark it against other tasks .
Outcome:	The proposed task performs on a large-scale visual conversation dataset . it eliminates coreference and ellipsis in the original query without changing its semantic information.

Copied to clipboard

Yifei Xu, Yingjie Zong, Wang Zhonghua, Sirui Wu, Yuan Rao, Dan Zhang, Shuiguang Deng

Challenge:	Current approaches to news writing rely on superficially retrieved information and oversimplified knowledge enumeration resulting in shallow, repetitive, and unordered outputs.
Approach:	They propose an LLM-based multi-agent controllable news writing framework called CtrlNews . they propose a fine-grained viewpoint control mechanism to regulate bias, emotion, and exaggeration attributes.
Outcome:	The proposed framework simulates expert questioning through automated role assignment and question generation followed by a three-layer hierarchical gravitational graph iteratively refined via expansion-reflection cycles.

On the Step Length Confounding in LLM Reasoning Data Selection (2026.findings-acl)

Copied to clipboard

Bing Wang, Rui Miao, Chen Shen, Shaotian Yan, Kaiyuan Liu, Ximing Li, Xiaosong Yuan, Sinan Fan, Jun Zhang, Jieping Ye

Alpha-GPT: Human-AI Interactive Alpha Mining for Quantitative Investment (2025.emnlp-demos)

Challenge:	Existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Approach:	They propose to use supervised fine-tuning to generate long reasoning data from more capable Large Language Models and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Outcome:	Experiments on four LLMs and five evaluation benchmarks show that the proposed approach is effective in mitigating step length confounding problem.

Copied to clipboard

Saizhuo Wang, Hang Yuan, Leon Zhou, Lionel Ni, Heung-Yeung Shum, Jian Guo

Act as you think: Reinforcing Consistent Reasoning in Medical Visual Question Answering (2026.acl-long)

Challenge:	Traditional methods of alpha mining have inherent limitations, especially in implementing the ideas of quant researchers.
Approach:	They propose a new alpha mining paradigm by introducing human-AI interaction and a prompt engineering algorithmic framework to implement this paradigm by using large language models.
Outcome:	The proposed framework is based on human-AI interaction and large language models and is comparable to human participants in the WorldQuant International Quant Championship.

Copied to clipboard

Songtao Jiang, Yuan Wang, Ruizhe Chen, Yan Zhang, Ruilin Luo, Bohan Lei, Yeying Jin, Sibo Song, ZhiBo Yang, Jimeng Sun, Jian Wu, Zuozhu Liu

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

Challenge:	Recent advances have improved the accuracy of medical visual question answering (Med-VQA) however, the high stakes nature of the medical domain has precipitated a shift towards interpretability and transparency of reasoning processes.
Approach:	They propose a reinforcement learning from verifiable rewards framework that rewards internal consistency and logical coherence.
Outcome:	The proposed framework rewards internal consistency and logical coherence, and is highly versatile, the authors show.

Copied to clipboard

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

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2025.findings-acl)

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

Copied to clipboard

Xin Men, Mingyu Xu, Qingyu Zhang, Qianhao Yuan, Bingning Wang, Hongyu Lin, Yaojie Lu, Xianpei Han, Weipeng Chen

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Challenge:	Recent studies have identified significant redundancy in large language models . quantization and pruning are two methods that reduce computational resources .
Approach:	They propose simple pruning methods that prune redundant layers based on their BI scores.
Outcome:	The proposed pruning methods demonstrate superior performance over previous pruning methods.

Copied to clipboard

Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

CogLM: Tracking Cognitive Development of Large Language Models (2025.naacl-long)

Challenge:	supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach:	They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome:	The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.

Copied to clipboard

Xinglin Wang, Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have recently shown remarkable abilities across a wide variety of tasks, but few studies have explored the reasons behind the evolutionary relationship among various abilities.
Approach:	They construct a benchmark CogLM based on Piaget's Theory of Cognitive Development (PTC) which measures the cognitive levels of Large Language Models (LLMs) using 1,220 questions spanning 10 cognitive abilities crafted by more than 20 human experts.
Outcome:	The proposed framework provides a comprehensive testbed for the cognitive levels of LLMs.

Copied to clipboard

Han Bao, Penghao Zhang, Yue Huang, Zhengqing Yuan, Yanchi Ru, SU Rui, Yujun Zhou, Xiangqi Wang, Kehan Guo, Nitesh V Chawla, Yanfang Ye, Xiangliang Zhang

FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are increasingly integrated into real-world decision-making, but their ability to comprehend and reason about policy-related content remains underexplored.
Approach:	They propose a bilingual benchmark evaluating policy comprehension comprising 21K cases across a broad spectrum of policy areas.
Outcome:	The proposed model shows stronger performance on application-oriented policy tasks than on memorization or conceptual understanding, and yields the highest accuracy on structured reasoning tasks.

Copied to clipboard

Zengyi Gao, Yukun Cao, Hairu Wang, Ao Ke, Yuan Feng, S Kevin Zhou, Xike Xie

Question Directed Graph Attention Network for Numerical Reasoning over Text (2020.emnlp-main)

Challenge:	Existing methods for retrieval-augmented generation struggle with a trade-off between flexibility and retrieval quality.
Approach:	They propose a flexible modular KG-RAG framework that uses query text instead of KGs . they propose to use query text to infer the structural information of reasoning paths .
Outcome:	The proposed method achieves state-of-the-art performance with high efficiency and low resource consumption.

Copied to clipboard

Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu

GUICourse: From General Vision Language Model to Versatile GUI Agent (2025.acl-long)

Challenge:	Numerical reasoning requires both natural language understanding and arithmetic computation.
Approach:	They propose a graph representation for the context of the passage and question needed for numerical reasoning.
Outcome:	The proposed model achieves remarkable results in benchmark datasets such as DROP.

Copied to clipboard

Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan Yao, Yankai Lin, Zhiyuan Liu, Maosong Sun

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

Challenge:	Graphical User Interfaces (GUIs) are a pivotal medium for human-computer interaction.
Approach:	They propose a series of datasets for training visual-based GUI agents using general VLMs.
Outcome:	The proposed GUICourse datasets show that even a small-sized GUI agent performs better on GUI tasks.

Copied to clipboard

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

LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review (2025.acl-demo)

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

Copied to clipboard

Cheng Yuan, Xinkai Rui, Yongqi Fan, Yawei Fan, Boyang Zhong, Jiacheng Wang, Weiyan Zhang, Tong Ruan

Challenge:	Large language models (LLMs) are capable of generating inaccurate discharge summary content or fabricating information without valid sources.
Approach:	They propose a tool for empowering LLMs with Logic-Controlled Discharge Summary generation.
Outcome:	The proposed tool identifies the writing logic of discharge summaries and integrates it with EMRs to generate silver discharge summararies.

Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in Dialogue Generation (D19-1)

Copied to clipboard

Min Zeng, Yisen Wang, Yuan Luo

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning (2025.findings-emnlp)

Challenge:	Existing work assumes the Gaussian priors of the latent variable, which are incapable of representing complex latent variables effectively.
Approach:	They propose to use the Dirichlet distribution with flexible structures to characterize latent variables in place of the Gaussian priors.
Outcome:	The proposed model outperforms existing models on the dialogue generation task.

Copied to clipboard

Yuan Li, Qi Luo, Xiaonan Li, Bufan Li, Qinyuan Cheng, Bo Wang, Yining Zheng, Yuxin Wang, Zhangyue Yin, Xipeng Qiu

LegalAgentBench: Evaluating LLM Agents in Legal Domain (2025.acl-long)

Challenge:	RAG systems that integrate external knowledge with Large Language Models often become bottlenecks due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning.
Approach:	They propose a model that integrates external knowledge with Large Language Models to enhance factual correctness and mitigate hallucination.
Outcome:	The proposed model outperforms baselines and can transfer well to different retrievers.

Copied to clipboard

Haitao Li, Junjie Chen, Jingli Yang, Qingyao Ai, Wei Jia, Youfeng Liu, Kai Lin, Yueyue Wu, Guozhi Yuan, Yiran Hu, Wuyue Wang, Yiqun Liu, Minlie Huang

Challenge:	Existing general-domain benchmarks do not capture complexity of real-world judicial cognition and decision-making.
Approach:	They propose a benchmark specifically designed to evaluate LLM Agents in the legal domain.
Outcome:	The proposed benchmark includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge.

Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint (2024.findings-acl)

Copied to clipboard

Xiaowei Yuan, Zhao Yang, Yequan Wang, Shengping Liu, Jun Zhao, Kang Liu

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference (2024.findings-emnlp)

Challenge:	Existing decoding methods for large language models (LLMs) are specialized in resolving knowledge conflicts and could inadvertently deteriorate performance in absence of conflicts.
Approach:	They propose an adaptive decoding method to discern whether knowledge conflicts occur and resolve them by a contextual information-entropy constraint decoding technique.
Outcome:	The proposed method improves the model’s faithfulness to conflicting context and maintains high performance among non-conflicting contexts.

Copied to clipboard

Zhongwei Wan, Ziang Wu, Che Liu, Jinfa Huang, Zhihong Zhu, Peng Jin, Longyue Wang, Li Yuan

DHP Benchmark: Are LLMs Good NLG Evaluators? (2025.findings-naacl)

Challenge:	Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources for inference . the growth of their multimodal Key-Value (KV) cache challenges memory and time efficiency.
Approach:	They propose a fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache.
Outcome:	The proposed method reduces the multimodal KV cache size while maintaining performance comparable to a full cache.

Copied to clipboard

Yicheng Wang, Jiayi Yuan, Yu-Neng Chuang, Zhuoer Wang, Yingchi Liu, Mark Cusick, Param Kulkarni, Zhengping Ji, Yasser Ibrahim, Xia Hu

NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks (2026.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks.
Approach:	They propose a framework that measures the discernment of Large Language Models (LLMs) across diverse NLG tasks.
Outcome:	The proposed framework provides quantitative discernment scores for LLMs across four NLG tasks.

Copied to clipboard

Zhihao Luo, Wentao Yan, Jingyu Gong, Min Wang, Zhizhong Zhang, Xuhong Wang, Yuan Xie, Xin Tan

Challenge:	Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and training paradigms.
Approach:	They propose a visual-target trajectory collection pipeline that generates trajectories for GUI and embodied tasks using a single formulation.
Outcome:	The proposed agent outperforms state-of-the-art agents in GUI navigation, spatial affordance prediction, and embodied navigation.

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

KG-Adapter: Enabling Knowledge Graph Integration in Large Language Models through Parameter-Efficient Fine-Tuning (2024.findings-acl)

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

Copied to clipboard

Shiyu Tian, Yangyang Luo, Tianze Xu, Caixia Yuan, Huixing Jiang, Chen Wei, Xiaojie Wang

KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment (2023.acl-long)

Challenge:	Large language models (LLMs) are criticized for lack of expertise and knowledge conflict . KG-Adapter is a parameter-level KG integration method for decoder-only LLMs .
Approach:	They propose a parameter-level KG integration method based on parameter-efficient fine-tuning . they use KG-Adapter to integrate knowledge graphs with LLMs and perform joint reasoning .
Outcome:	The proposed method outperforms the current state-of-the-art method on four datasets for two different tasks.

Copied to clipboard

Lingzhi Wang, Tong Chen, Wei Yuan, Xingshan Zeng, Kam-Fai Wong, Hongzhi Yin

Challenge:	Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning . MU can be used to forget specific training instances as if they have never existed .
Approach:	They propose a general unlearning framework called KGA to induce forgetfulness . they propose several unlearning evaluation metrics with pertinence .
Outcome:	The proposed framework improves on large-scale datasets and provides insight into unlearning for NLP tasks.

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (2025.acl-long)

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Copied to clipboard

Jinglong Luo, Guanzhong Chen, Yehong Zhang, Shiyu Liu, Hui Wang, Yue Yu, Xun Zhou, Yuan Qi, Zenglin Xu

Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Challenge:	Existing privacy-preserving Transformer Inference frameworks suffer from high computational overhead and performance losses.
Approach:	They propose a framework that integrates random permutations and SMPC to address the "impossible trinity" CENTAUR resists diverse data reconstruction attacks and boosts inference speed by 5.030.4 times .
Outcome:	CENTAUR achieves an unprecedented balance between privacy, efficiency, and performance.

Copied to clipboard

Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Bringing Structure into Summaries: a Faceted Summarization Dataset for Long Scientific Documents (2021.acl-short)

Challenge:	Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach:	They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome:	The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.

Copied to clipboard

Rui Meng, Khushboo Thaker, Lei Zhang, Yue Dong, Xingdi Yuan, Tong Wang, Daqing He

DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search (2026.acl-long)

Challenge:	Faceted summarization provides briefings of a document from different perspectives.
Approach:	They propose a faceted summarization benchmark built on Emerald journal articles . they propose faceted models that bring structure into faceted documents .
Outcome:	The proposed benchmark is based on Emerald journal articles and covers a diverse range of domains.

Copied to clipboard

Guangming Qin, Yuhao Deng, Yukun Zhao, Zhenyang Li, Junfeng Wang, Dawei Yin, Ye Yuan, Guoren Wang, Yizhou Yan, Chengliang Chai, Lei Cao

Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Challenge:	Existing methods to train large language models overlook quality of intermediate search results . existing methods often invoke search calls during reasoning, making inference inefficient .
Approach:	They propose a dual-objective reinforcement learning framework to improve search strategies of MLLMs . DORA outperforms state-of-the-art methods, achieving up to 8.4% higher accuracy .
Outcome:	The proposed model outperforms state-of-the-art methods while reducing search calls by 9.7%.

Copied to clipboard

Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (2024.findings-emnlp)

Challenge:	Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach:	They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome:	The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.

Copied to clipboard

Tongxin Yuan, Zhiwei He, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, Rui Wang, Gongshen Liu

Challenge:	Large language models (LLMs) have shown compelling abilities in reasoning, decision-making, and instruction following.
Approach:	They propose a benchmark to evaluate the proficiency of large language models (LLMs) in judging and identifying safety risks given agent interaction records.
Outcome:	The proposed model outperforms the best-performing model, GPT-4o, while no other models significantly exceed the random.

Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models (2025.acl-long)

Copied to clipboard

Yuheng Lu, Bingshuo Qian, Caixia Yuan, Huixing Jiang, Xiaojie Wang

Improving Role-Oriented Dialogue Summarization with Interaction-Aware Contrastive Learning (2024.lrec-main)

Challenge:	Existing approaches to mitigate catastrophic forgetting can be broadly categorized into data-based, architecture-based and learning-based methods.
Approach:	They propose a subspace regularization method on LoRA structure that imposes constraints on direction of updating matrix’s null space.
Outcome:	The proposed method reduces scale of output change while introducing minimal constraint on model capacity.

Copied to clipboard

Weihong Guan, Shi Feng, Daling Wang, Faliang Huang, Yifei Zhang, Yuan Cui

Evaluating Character Understanding of Large Language Models via Character Profiling from Fictional Works (2024.emnlp-main)

Challenge:	Existing methods for encoding dialogues do not capture interaction information between roles, thus ignore interaction-related key information.
Approach:	They propose a contrastive learning based interaction-aware model for the role-oriented dialogue summarization namely CIAM and use it to train the decoder to learn role-level interaction.
Outcome:	The proposed model captures interaction information between different roles and produces informative summaries on two public datasets.

Copied to clipboard

Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin, Xintao Wang, Rui Xu, Jiangjie Chen, Deqing Yang

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have catalyzed numerous AI applications, among which role-playing agents (RPAs) are particularly popular.
Approach:	They propose to evaluate LLMs' character understanding capability via the character profiling task, i.e., summarizing character profiles from corresponding materials, a widely adopted yet understudied practice for RPA development.
Outcome:	The proposed model outperforms existing models and literature summarization methods and proves its ability to understand fictional characters in downstream tasks.

Copied to clipboard

Yuan Xiao, Jiaming Wang, Yuchen Chen, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang, Jin Song Dong, Zhenyu Chen

Programming Languages in NLP

Challenge:	Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach:	They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome:	The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.

Unsupervised Slot Schema Induction for Task-oriented Dialog (2022.naacl-main)

Copied to clipboard

Dian Yu, Mingqiu Wang, Yuan Cao, Izhak Shafran, Laurent Shafey, Hagen Soltau

MedCoT: Medical Chain of Thought via Hierarchical Expert (2024.emnlp-main)

Challenge:	Defining task-specific schemas is the first step of building a task-oriented dialog system.
Approach:	They propose an unsupervised approach for slot schema induction from unlabeled dialog corpora using in-domain language models and unsupervised parsing structures.
Outcome:	The proposed method shows significant performance improvement on multi-domain and SGD datasets.

Copied to clipboard

Jiaxiang Liu, Yuan Wang, Jiawei Du, Joey Zhou, Zuozhu Liu

SOAR: Supervision from Observation for Agentic Reinforcement Learning (2026.acl-long)

Challenge:	Existing methods for medical visual question answering lack robustness and reasoning paths for real-world medical diagnostics.
Approach:	They propose a hierarchical expert verification reasoning chain method to enhance interpretability and accuracy in medical visual question answering.
Outcome:	The proposed method outperforms existing methods on four standard Med-VQA datasets.

Copied to clipboard

Meng Li, Lei Li, Xiting Wang, Yi Yuan, Zheng Wei, null Brucebian, Zang Li

Dunhuang-Bench: How Well Do MLLMs Understand Cultural Heritage? (2026.findings-acl)

Challenge:	Prior work assigns supervision based on outcome rewards or external reward models, but ignores environment observations, a critical source of learning.
Approach:	They propose a supervision-based agentic reinforcement learning system that integrates environment observations as an explicit supervision signal.
Outcome:	The proposed model improves performance on reasoning and deep research tasks while reducing erroneous and inefficient tool usage.

Copied to clipboard

Junyi Yuan, Jian Zhang, Tianxiu Yu, Yanlin Zhou, Xiaobo Jin, Qiufeng Wang, Fangyu Wu

DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models (2024.naacl-demo)

Challenge:	Recent advances in Multimodal Large Language Models (MLLMs) have led to extensive evaluations on Chinese cultural benchmarks.
Approach:	They construct a large-scale benchmark comprising 486 images and 22,970 QA pairs to evaluate MLLMs' cultural understanding.
Outcome:	The proposed benchmark incorporates three task formats to evaluate MLLMs’ cultural understanding: Question Answering with Text Description, Multi-turn Dialogue, and Question Answers with Choices.

Copied to clipboard

Songbo Hu, Xiaobin Wang, Moy Yuan, Anna Korhonen, Ivan Vulić

Diversity in Unity, Theory in Practice: Hierarchical Multitask Benchmarks for Chinese Minority Languages (2026.acl-long)

Challenge:	DIALIGHT is a toolkit for developing and evaluating multilingual Task-Oriented Dialogue systems.
Approach:	They propose a toolkit for developing and evaluating multilingual Task-Oriented Dialogue systems which facilitates systematic evaluations and comparisons between ToD systems using pretrained language models and those utilising the zero-shot and in-context learning capabilities of Large Language Models.
Outcome:	The toolkit enables systematic evaluations between ToD systems using pretrained language models and those utilising the zero-shot and in-context learning capabilities of Large Language Models (LLMs).

Copied to clipboard

Yijie Li, Xi Cao, Yuan Sun, Quulgan Minggad, Abdulla Ablikim, Jia Qing Cai Wang

Machine Translation

Challenge:	CMiLBench is a framework to evaluate linguistically and culturally diverse minority languages . rapid evolution of LLMs has revolutionized NLP, but progress is unevenly distributed .
Approach:	They propose a framework to translate a theoretical notion of "diversity in unity" into practical evaluation for three minority languages . CMiLBench comprises 24,663 instances across 5 difficulty levels and 17 tasks .
Outcome:	The proposed framework evaluates 14 state-of-the-art LLMs with a hybrid framework . it integrates automatic metrics and LLM-as-a-Judge scoring .

Knowledge-grounded Dialog State Tracking (2022.findings-emnlp)

Copied to clipboard

Dian Yu, Mingqiu Wang, Yuan Cao, Laurent El Shafey, Izhak Shafran, Hagen Soltau

IAPT: Instance-Aware Prompt Tuning for Large Language Models (2024.acl-long)

Challenge:	Structured knowledge is encoded implicitly into model parameters for downstream tasks, making training inefficient.
Approach:	They propose to perform dialog state tracking grounded on knowledge encoded externally.
Outcome:	The proposed method outperforms baseline models in the few-shot learning setting.

Copied to clipboard

Wei Zhu, Aaron Tian, Congrui Yin, Yuan Ni, Xiaoling Wang, Guotong Xie

AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Challenge:	Existing methods for prompt tuning require many soft tokens to guarantee performance . large language models still require a large amount of GPU memory and computations to fine-tune .
Approach:	They propose to use a parameter-efficient soft prompt generator to generate idiosyncratic soft prompts for each input instruction.
Outcome:	The proposed method outperforms the baselines with comparable tunable parameters and is more efficient than LoRA under the single-backbone multi-tenant setting.

Copied to clipboard

Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)

Challenge:	AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach:	They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome:	AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.

Copied to clipboard

Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Challenge:	Large language models suffer from factual hallucinations where they generate verifiable falsehoods.
Approach:	They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge.
Outcome:	The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods.

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement (2026.acl-long)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

ZhenChun Xu, Yi Cai, Dajun Zheng, li Yuan, Mengchen Zhao, Qixiang Wang, Jiexin Wang

Programming Languages in NLP

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced automated program synthesis.
Approach:	They propose a model-adaptive and verification–enhanced framework for competition-level code generation that leverages adaptive assessment aligned with the model’s capabilities to select planning strategies while providing timely feedback and correction via multi-perspective verification.
Outcome:	The proposed framework outperforms existing state-of-the-art approaches on livecodebench, humanEval+, MBPP+, and codecontests, and achieves pass@1 results exceeding 3%–40%.

Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs (2025.acl-long)

Copied to clipboard

Yijie Jin, Junjie Peng, Xuanchao Lin, Haochen Yuan, Lan Wang, Cangzhi Zheng

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)

Challenge:	Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments.
Approach:	They propose a multimodal fusion model that integrates multimodal information to recognize sentiments using multimodal transformers.
Outcome:	The proposed model achieves significantly higher performance than MulTs and the existing model is robust.

Copied to clipboard

Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang

CorefQA: Coreference Resolution as Query-based Span Prediction (2020.acl-main)

Challenge:	Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence.
Approach:	They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included .
Outcome:	The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model.

Copied to clipboard

Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li

Learn to Adapt for Generalized Zero-Shot Text Classification (2022.acl-long)

Challenge:	Existing coreference resolution models suffer from mention proposal.
Approach:	They propose a query-based span prediction task that can retrieve mentions left out at the mention proposal stage.
Outcome:	The proposed model can retrieve mentions left out at the mention proposal stage and improve generalization capability using existing question answering datasets.

Copied to clipboard

Yiwen Zhang, Caixia Yuan, Xiaojie Wang, Ziwei Bai, Yongbin Liu

U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents (2026.findings-acl)

Challenge:	Existing methods for generalized zero-shot text classification generalize poorly since the learned parameters are only optimal for seen classes rather than for both classes.
Approach:	They propose a network that trains an adaptive classifier by using both seen and virtual unseen classes to simulate a generalized zero-shot learning scenario.
Outcome:	The proposed model outperforms several previous approaches on five text classification datasets.

Copied to clipboard

Jin Su, Runnan Fang, Yeqiu Li, Xiaobin Wang, Shihao Cai, Pengjun Xie, Ningyu Zhang, Fajie Yuan

VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models (2025.emnlp-main)

Challenge:	Existing context-folding methods are designed for single-query or single-intent scenarios.
Approach:	They propose a dynamic context-folding framework tailored to user-centric tasks that preserves fine-grained information through dynamic context folding.
Outcome:	The proposed framework outperforms ReAct and previous folding frameworks on long, noisy tasks.

Copied to clipboard

Jen-tse Huang, Jiantong Qin, Jianping Zhang, Youliang Yuan, Wenxuan Wang, Jieyu Zhao

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Challenge:	Identifying and addressing potential social biases is essential to prevent harm to users.
Approach:	They examine explicit and implicit biases exhibited by Vision-Language Models . they pose questions related to gender and racial differences to test their models .
Outcome:	The proposed models are used in image description tasks, form completion tasks and medical applications.

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science (2025.acl-long)

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

Copied to clipboard

Jie Ying, Zihong Chen, Zhefan Wang, Wanli Jiang, Chenyang Wang, Zhonghang Yuan, Haoyang Su, Huanjun Kong, Fan Yang, Nanqing Dong

LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025.acl-long)

Challenge:	Seed science is essential for modern agriculture, but its application in seed science remains limited due to a shortage of experts and limited availability of online resources.
Approach:	They evaluate 26 leading large language models and compare them against a set of benchmarks . they find that there is a gap between the power of LLMs and real-world seed science problems .
Outcome:	The new seed benchmark highlights the gap between the power of large language models and real-world seed science problems.

Copied to clipboard

Chao Deng, Jiale Yuan, Pi Bu, Peijie Wang, Zhong-Zhi Li, Jian Xu, Xiao-Hui Li, Yuan Gao, Jun Song, Bo Zheng, Cheng-Lin Liu

SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check (2020.acl-main)

Challenge:	Existing document understanding benchmarks only handle a small number of pages . existing models are limited to handling only a limited number of documents .
Approach:	They propose a long document understanding benchmark that integrates three primary tasks and 20 sub-tasks based on different primary tasks.
Outcome:	The proposed model outperforms existing benchmarks on open-source and closed-source models . the model outpersforms other models on more than 33,000 pages of documents .

Copied to clipboard

Xingyi Cheng, Weidi Xu, Kunlong Chen, Shaohua Jiang, Feng Wang, Taifeng Wang, Wei Chu, Yuan Qi

An Effective and Efficient Entity Alignment Decoding Algorithm via Third-Order Tensor Isomorphism (2022.acl-long)

Challenge:	Existing methods to detect and correct spelling errors in Chinese take external input or just heuristic rules.
Approach:	They propose to incorporate phonological and visual similarity knowledge into Chinese language models by using a specialized graph convolutional network.
Outcome:	The proposed method outperforms existing models on three human-annotated datasets.

Copied to clipboard

Xin Mao, Meirong Ma, Hao Yuan, Jianchao Zhu, ZongYu Wang, Rui Xie, Wei Wu, Man Lan

ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry (2025.acl-industry)

Challenge:	Existing methods focus on graph representation learning, but decoding is a key part of the process.
Approach:	They propose an EA Decoding Algorithm via Third-order Tensor Isomorphism (DATTI) they combine two sets of isomorphic equations to enhance the decoding process .
Outcome:	The proposed algorithm can deliver significant performance improvements even on the most advanced methods while the extra required time is less than 3 seconds.

Copied to clipboard

Qinwen Chen, Wenbiao Tao, Zhiwei Zhu, Mingfan Xi, Liangzhong Guo, Yuan Wang, Wei Wang, Yunshi Lan

Learn to Copy from the Copying History: Correlational Copy Network for Abstractive Summarization (2021.emnlp-main)

Challenge:	Existing methods for Community Question Answering (CQA) focus on static knowledge, limiting their applicability to real-world scenarios.
Approach:	They propose a retrieval-augmented generation framework for real-time industrial CQA that integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism.
Outcome:	The proposed framework outperforms baselines on three industrial CQA datasets and achieves 25.9% improvement in vector similarity, reducing latency by 8.7%–23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.

Copied to clipboard

Haoran Li, Song Xu, Peng Yuan, Yujia Wang, Youzheng Wu, Xiaodong He, Bowen Zhou

FinChart-Bench: Benchmarking Financial Chart Comprehension in Vision-Language Models (2026.acl-long)

Challenge:	Existing methods for abstractive summarization use encoder-decoder attention, but this leads to incomplete copying.
Approach:	They propose a copying scheme that takes advantage of prior copying distributions and explicitly encourages the model to copy the input word that is relevant to the previously copied one.
Outcome:	The proposed scheme achieves state-of-the-art on summarization benchmarks . it takes advantage of prior copying distributions and explicitly encourages copying .

Copied to clipboard

Dong Shu, Haoyang Yuan, Yuchen Wang, Yanguang Liu, Huopu Zhang, Mengnan Du

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)

Challenge:	FinChart-Bench is the first benchmark specifically focused on real-world financial charts.
Approach:	They propose a benchmark specifically focused on real-world financial charts.
Outcome:	The proposed benchmark evaluates 26 state-of-the-art LVLMs on FinChart-Bench.

Copied to clipboard

Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li

Challenge:	Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications.
Approach:	They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis.
Outcome:	The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.

APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing (2021.findings-emnlp)

Copied to clipboard

Ying Li, Meishan Zhang, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan

Ro-SLM: Onboard Small Language Models for Robot Task Planning and Operation Code Generation (2026.findings-acl)

Challenge:	Existing models for dependency parsing use labeled training data for several fixed domains, but performance drops when labeles only exist for several out-domains.
Approach:	They propose a model for multi-source cross-domain dependency parsing that uses a parameter generation network and adversarial network for learning domain-invariant representations.
Outcome:	The proposed model improves cross-domain parsing performance by about 2 points over strong BERT-enhanced baselines over a recently released dataset for multi-domain dependency parse.

Copied to clipboard

Wenhao Wang, Yanyan Li, Long Jiao, Jiawei Yuan

Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)

Challenge:	Recent advances in large language models (LLMs) provide robots with contextual reasoning abilities to comprehend human instructions.
Approach:	They propose a framework that enables reliable SLM-driven robot operation by distilling LLMs’ knowledge and reasoning.
Outcome:	The proposed framework enables reliable SLM-driven robot operation by distilling LLMs’ knowledge and reasoning.

Copied to clipboard

Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang

Recognizing Social Cues in Crisis Situations (2024.lrec-main)

Challenge:	Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB).
Approach:	They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view.
Outcome:	The proposed framework achieves state-of-the-art on several entity linking benchmarks.

Copied to clipboard

Di Wang, Yuan Zhuang, Ellen Riloff, Marina Kogan

Text Classification

Challenge:	During natural disasters, observations of other people's behavior can play an essential role in a person's decision-making.
Approach:	They propose a task to categorize social cues in tweets during crisis situations using an annotated dataset of 6,000 tweets.
Outcome:	The proposed task is challenging for existing systems and a manual task is based on a dataset of 6,000 tweets labeled with eight social cue categories.

Exploring Dual Encoder Architectures for Question Answering (2022.emnlp-main)

Copied to clipboard

Zhe Dong, Jianmo Ni, Dan Bikel, Enrique Alfonseca, Yuan Wang, Chen Qu, Imed Zitouni

HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025.emnlp-main)

Challenge:	Dual encoders have been used for question-answering and information retrieval tasks with good results.
Approach:	They propose to use two different versions of dual encoders for QA retrieval tasks . they propose to share parameters in projection layers between two encoder towers .
Outcome:	The proposed architectures outperform SDE and ADE on QA retrieval tasks.

Copied to clipboard

Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang

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

Challenge:	Current RAG system retrieves evidence from knowledge graphs and text documents but has limitations in multi-hop reasoning, multi-entity questions, and source verification.
Approach:	They propose a training-free framework that unifies graph topology, document semantics, and source reliability to support deep, faithful reasoning in large language models.
Outcome:	The proposed framework outperforms the current hybrid model-based model-driven system by 20.3% and 30.1% on seven benchmark datasets.

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

Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models (2024.findings-acl)

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

Yikai Zhang, Qianyu He, Xintao Wang, Siyu Yuan, Jiaqing Liang, Yanghua Xiao

CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks (2026.acl-long)

Challenge:	Multi-Modal Knowledge Graphs (MMKGs) are knowledge graphs that integrate and align information from diverse modalities (e.g., text and images).
Approach:	They propose a framework that integrates image-text pairs of long-tailed entities and a concept guidance module that offers explainability and enables human verification.
Outcome:	The proposed framework improves the accuracy of recognizing long-tailed image-text pairs compared to baselines and also offers flexibility and explainability.

Copied to clipboard

Lingyue Fu, Hao Guan, Bolun Zhang, Haowei Yuan, Yaoming Zhu, Lin Qiu, ZongYu Wang, Xuezhi Cao, Xunliang Cai, Weiwen Liu, Weinan Zhang, Yong Yu

Challenge:	Existing large language models for software engineering rely on coarse-grained pass rates obscuring specific cognitive bottlenecks.
Approach:	They propose a repository-level benchmark that dissects coding capabilities through atomized tasks.
Outcome:	The proposed framework achieves a 78.55% validity yield, surpassing the 31.7% retention rate of SWE-bench-Verified.

CryptoTrade: A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading (2024.emnlp-main)

Copied to clipboard

Yuan Li, Bingqiao Luo, Qian Wang, Nuo Chen, Xu Liu, Bingsheng He

POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have been used for financial decision-making and stock market prediction for years.
Approach:	They propose to use Large Language Models to analyze on-chain and off-chain data to provide a comprehensive overview of the cryptocurrency market.
Outcome:	The proposed trading agent leverages the transparency and immutability of on-chain data, as well as the timeliness and influence of off-chain signals, providing a comprehensive overview of the cryptocurrency market.

Copied to clipboard

Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Zhou Xiao, Yang Yu, Jie Zhou

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Challenge:	Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications.
Approach:	They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts.
Outcome:	The proposed model outperforms existing models and improves on annotated documents.

Copied to clipboard

Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

FiDeLiS: Faithful Reasoning in Large Language Models for Knowledge Graph Question Answering (2025.findings-acl)

Challenge:	Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach:	They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome:	The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.

Copied to clipboard

Yuan Sui, Yufei He, Nian Liu, Xiaoxin He, Kun Wang, Bryan Hooi

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service (2025.findings-acl)

Challenge:	Existing retrieval-based or agent-based methods are prone to generating erroneous or hallucinated outputs.
Approach:	They propose a framework to leverage knowledge graphs as external knowledge sources to improve the factuality of LLM responses by anchoring answers to verifiable reasoning steps retrieved from KGs.
Outcome:	The proposed framework improves factuality and interpretability across benchmarks and reduces computational costs.

Copied to clipboard

Yihang Cheng, Lan Zhang, Junyang Wang, Mu Yuan, Yunhao Yao

Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT (2020.coling-main)

Challenge:	Large language models (LLMs) have a tendency to generate factually incorrect or purely fictional responses, a phenomenon known as hallucination.
Approach:	They propose to use remote RAG to protect user query from privacy leakage . they introduce (n,)-DistanceDP to characterize privacy leakages of user query .
Outcome:	The proposed solution can resist embedding inversion attacks while achieving no loss in retrieval under various settings.

Copied to clipboard

Ruifeng Yuan, Zili Wang, Wenjie Li

GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models (2025.emnlp-demos)

Challenge:	Existing extractive summarization models generate summaries by selecting salient sentences, but there is a gap between the human-written gold summary and oracle sentence labels.
Approach:	They propose to extract fact-level semantic units for better extractive summarization by incorporating a hierarchical structure into the model and incorporate it with BERT using a Hierarchical graph mask.
Outcome:	The proposed model achieves state-of-the-art on the CNN/DaliyMail dataset.

Copied to clipboard

Hengyu Luo, Zihao Li, Joseph Attieh, Sawal Devkota, Ona de Gibert, Xu Huang, Shaoxiong Ji, Peiqin Lin, Bhavani Sai Praneeth Varma Mantina, Ananda Sreenidhi, Raúl Vázquez, Mengjie Wang, Samea Yusofi, Fei Yuan, Jörg Tiedemann

Multilinguality

Challenge:	Existing evaluation frameworks focus on English and a handful of high-resource languages, thereby overlooking the realistic performance of large language models in multilingual and lower-resourced scenarios.
Approach:	They propose a unified and lightweight framework that integrates 27 benchmarks under a standard ISO 639-3 language identifier system to enable seamless incorporation of new benchmarks.
Outcome:	The proposed framework integrates 27 benchmarks under a standard ISO 639-3 language identifier system, allowing for seamless incorporation of new benchmarks.

Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions (2025.acl-long)

Copied to clipboard

Xinbei Ma, Yiting Wang, Yao Yao, Tongxin Yuan, Aston Zhang, Zhuosheng Zhang, Hai Zhao

Demystifying Uncertainty in LLMs: Active Calibration between Concepts and Human Evaluations (2026.acl-long)

Challenge:	Experimental results show that multimodal GUI agents are susceptible to environmental distractions.
Approach:	They propose a scenario where both user and agent are benign and environment is not malicious . they implement an adversarial environment injection and analyze the approach to improve faithfulness .
Outcome:	The proposed approach improves faithfulness of multimodal large language model agents in a graphical user interface environment.

Copied to clipboard

Pengqi Li, Lizhong Ding, Zhehao Zhou, Chunhui Zhang, Jiarun Fu, Hao Li, Ye Yuan, Guoren Wang

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)

Challenge:	Existing static strategies for mitigating hallucinations do not explicitly model the information gain from interacting with the external environment.
Approach:	They propose a calibration-driven interactive learning strategy that selects clarification queries by optimizing calibration error.
Outcome:	The proposed method provides theoretical guarantees and empirical gains for reliability.

Copied to clipboard

Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu

Low-Resource NLP

Challenge:	Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints.
Approach:	They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking .
Outcome:	The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints.

MAXS: Meta-Adaptive Exploration with LLM Agents (2026.findings-acl)

Copied to clipboard

Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Yu He, Haoran Luo, li Yuan, Lingling Zhang, Rui Mao, Qika Lin, Jun Liu

Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens (2025.emnlp-main)

Challenge:	Existing methods for inference are often myopic and have divergent reasoning paths . a meta-adaptive reasoning framework is proposed to improve the efficiency of LLM agents .
Approach:	They propose a meta-adaptive reasoning framework that integrates tool execution and reasoning planning.
Outcome:	The proposed framework outperforms existing methods in performance and inference efficiency.

Copied to clipboard

Ziyang Ma, Qingyue Yuan, Zhenglin Wang, Deyu Zhou

Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks (2025.emnlp-main)

Challenge:	Existing studies have focused on the cognitive error detection capabilities of Large Language Models (LLMs), but few studies have examined the meta-cognitive abilities of LLMs.
Approach:	They propose an automated meta-cognition evaluation framework for evaluation of LLMs and a Markovian Intrinsic Reward Adjustment strategy to boost current lenses.
Outcome:	The proposed framework can be used to evaluate the meta-cognition abilities of LLMs and improve them.

Copied to clipboard

Gaurav Bagwe, Saket Sanjeev Chaturvedi, Xiaolong Ma, Xiaoyong Yuan, Kuang-Ching Wang, Lan Emily Zhang

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation (2025.findings-emnlp)

Challenge:	Retrieval-augmented generation (RAG) enhances factual grounding but introduces new attack surfaces, particularly through backdoor attacks.
Approach:	They propose a framework that exposes fairness vulnerabilities in RAG through a two-phase backdoor attack.
Outcome:	Empirical results show that BiasRAG achieves high attack success rates while remaining undetectable under standard fairness evaluations.

Copied to clipboard

Yiqun Shen, Song Yuan, Zhengze Zhang, Xiaoliang Wang, Daxin Jiang, Nguyen Cam-Tu

Challenge:	Existing methods for cache compression are heuristic and lack dynamic budget allocation . cnn's john mccartney and johnny mccain present a new approach for cache eviction and dynamic budgets .
Approach:	They propose a unified framework for cache compression that minimizes information loss in transformer residual streams.
Outcome:	The proposed method consistently maintains top performance across task types.

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning (2026.acl-long)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Bowen Ding, Yuhan Chen, Jiayang Lyu, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service (2025.acl-long)

Challenge:	evolving generic Large Language Models into specialized Large Reasoning Models requires effective post-training.
Approach:	They propose a plasticity-ceiling framework to harness expert trajectories . they establish the Sequential SFT-then-RL pipeline as the superior standard .
Outcome:	The proposed framework overcomes stability and premature convergence deficits in synchronized approaches.

Copied to clipboard

Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei Ye, Kuofeng Gao, Yi Huang, Yuan Yao

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

Challenge:	Existing studies evaluate efficiency robustness of vision-language models under unrealistic assumptions, requiring access to model architecture and parameters.
Approach:	They propose a novel approach to evaluate VLM efficiency robustness in a realistic black-box setting.
Outcome:	The proposed approach generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%.

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

GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing (2025.naacl-long)

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

Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang, Eunhye Grace Ko, Lily Boddy, Chenan Wang, Tianhao Li, Alexander Rasgon, Junyuan Hong, Min Kyung Lee, Chenxi Yuan, Qi Long, Ying Ding, Tianlong Chen, Kaidi Xu

Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth (2026.eacl-long)

Challenge:	Large Language Models (LLMs) have demonstrated their effectiveness in human-guided dialogues, but tasks in the real world are more complex and require greater autonomy from LLMs.
Approach:	They propose to characterize LLM-guided conversation into three fundamental components: Goal Navigation, Context Management, Empathetic Engagement and implement an interviewing environment for the evaluation of LLMs.
Outcome:	The proposed LLM outperforms baseline LLMs in interviewing quality and autobiography generation quality.

Copied to clipboard

Michelle Yuan, Weiyi Sun, Amir H. Rezaeian, Jyotika Singh, Sandip Ghoshal, Yao-Ting Wang, Miguel Ballesteros, Yassine Benajiba

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Challenge:	despite advances in transformers, their theoretical limitations in discrete reasoning remain a critical open problem.
Approach:	They synthesize recent advances from three theoretical perspectives to clarify structural and computational barriers transformers face when performing symbolic computations.
Outcome:	The proposed models excel at pattern matching and interpolation, but they face bottlenecks in communication and depth constraints.

Copied to clipboard

Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement (2025.acl-short)

Challenge:	Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach:	They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome:	The proposed model achieves 49.04% accuracy across five model families.

Copied to clipboard

Runnan Fang, Xiaobin Wang, Yuan Liang, Shuofei Qiao, Jialong Wu, Zekun Xi, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

Challenge:	Using Large Language Models (LLMs)-based agents can enhance their understanding of environments and tasks.
Approach:	They propose a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search exploration to refine their action knowledge in the current environment.
Outcome:	The proposed framework synthesizes possible scenarios with multi-step action invocation within the action space and performs Monte Carlo Tree Search exploration to refine action knowledge in the current environment.

Growing Through Experience: Scaling Episodic Grounding in Language Models (2025.acl-long)

Copied to clipboard

Chunhui Zhang, Sirui Wang, Zhongyu Ouyang, Xiangchi Yuan, Soroush Vosoughi

AnyTOD: A Programmable Task-Oriented Dialog System (2023.emnlp-main)

Challenge:	Language models (LMs) require effective episodic grounding to perform well at physical planning tasks due to their limited ability to learn from and apply past experiences.
Approach:	They propose a weak-to-strong episodic learning framework that integrates episodic memory into hierarchical representations and pre-trained knowledge to unlock larger LMs' potential for grounding.
Outcome:	The proposed framework outperforms top proprietary LMs by 3.45% across diverse planning and question-answering tasks.

Copied to clipboard

Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, Yonghui Wu

A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2020.acl-main)

Challenge:	a neuro-symbolic approach allows zero-shot adaptation to unseen tasks and domains . a neural LM keeps track of events that occur during a conversation and a symbolic program implements dialog policy is executed to recommend actions.
Approach:	They propose an end-to-end, zero-shot task-oriented dialog system . it is designed to adapt to unseen tasks or domains without prior training .
Outcome:	The proposed system can be programmed to adapt to unseen tasks without training . it reduces data collection and training requirements for enabling new TOD 1 16189 tasks .

Copied to clipboard

Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)

Challenge:	Existing approaches to extract relational triples from unstructured text are inadequate to solve the overlapping triple problem.
Approach:	They propose a cascade binary tagging framework that models relations as functions that map subjects to objects in a sentence.
Outcome:	The proposed framework outperforms state-of-the-art methods on two datasets . it outperformed baseline methods by 17.5 and 30.2 absolute gains .

Copied to clipboard

Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router (2026.acl-long)

Challenge:	Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows.
Approach:	They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system.
Outcome:	Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Ruibin Yuan, Xueqi Cheng

One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases (2020.acl-main)

Challenge:	Current alignment approaches rely on refusal alignment to avoid harmful content . large language models are often overly cautious or overlook subtle harmful content.
Approach:	They propose a framework for fine-grained safe generation in Large Language Models that enables real-time, token-level harmfulness detection and redaction without loss in capability.
Outcome:	The proposed framework achieves over 90% in F1 score for detecting and redacting harmful content while preserving overall utility and informativeness of the model’s responses.

Copied to clipboard

Xingdi Yuan, Tong Wang, Rui Meng, Khushboo Thaker, Peter Brusilovsky, Daqing He, Adam Trischler

Can Language Models Serve as Text-Based World Simulators? (2024.acl-short)

Challenge:	Existing models for keyphrase generation do not provide a desideratum for the number of keyphrases in texts.
Approach:	They propose a recurrent generative model that generates multiple keyphrases as delimiter-separated sequences.
Outcome:	The proposed model outperforms baseline models on all datasets.

Copied to clipboard

Ruoyao Wang, Graham Todd, Ziang Xiao, Xingdi Yuan, Marc-Alexandre Côté, Peter Clark, Peter Jansen

CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search (2025.naacl-industry)

Challenge:	Recent advances in large language models (LLMs) have pointed towards an alternative approach by leveraging the huge amount of knowledge contained in their pre-training datasets.
Approach:	They build and use a benchmark to quantify how well text-based simulators can serve as text-driven world simulators.
Outcome:	The proposed benchmark aims to quantify how well language models can serve as world simulators.

Copied to clipboard

Kaixin Wu, Yixin Ji, Zeyuan Chen, Qiang Wang, Cunxiang Wang, Hong Liu, Baijun Ji, Xu Jia, Zhongyi Liu, Jinjie Gu, Yuan Zhou, Linjian Mo

CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite (2024.lrec-main)

Challenge:	Relevance modeling between queries and items is a key component of commercial search engines.
Approach:	They propose a framework for continual pre-training of LLMs to enhance domain knowledge . they employ queries and multi-field item to jointly pre-train for enhancing domain knowledge.
Outcome:	The proposed model achieves convincing performance compared to strong baselines.

Copied to clipboard

Yifei Yuan, Chen Shi, Wang Runze, Liyi Chen, Renjun Hu, Zengming Zhang, Feijun Jiang, Wai Lam

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs (2026.findings-acl)

Challenge:	Recent advances in conversational IR systems have seen a resurgent interest in conversation . generative query rewrite generates reconstructed query based on the conversation history .
Approach:	They propose to use unlabeled data to make further improvements using contrastive co-training paradigm.
Outcome:	The proposed model is robust to noise and language style shift under few-shot and zero-shot scenarios.

Copied to clipboard

Hongyuan Yuan, Xinran He, Run Shao, Bolei He, Xianwei Xue, Mengke Chen, Qiutong Pan, Haiwei Wang, Haifeng Li

GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning (2025.findings-acl)

Challenge:	Extending CoT through RL can induce undesirable thinking patterns such as overthinking . prior work has focused on inefficient reflection, which manifests in two problematic patterns: Indiscriminate Reflection and Repetitive Reflectione .
Approach:	They propose a graph-based approach to optimize CoT by pruning each linear CoT into a directed acyclic graph with explicit dependency edges.
Outcome:	The proposed approach reduces the average reasoning tokens by 42% while maintaining or improving accuracy.

Copied to clipboard

Sifan Zhou, Shuo Wang, Zhihang Yuan, Mingjia Shi, Yuzhang Shang, Dawei Yang

SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) fine-tuning techniques require large Floating Point(FP) computation and are impractical for resource-constrained edge devices.
Approach:	They propose a framework for on-device LLM fine-tuning that eliminates the need for floating-point operations in both inference and training.
Outcome:	The proposed framework reduces memory and compute costs while reducing memory usage.

Copied to clipboard

Hairu Wang, Yuan Feng, Yukun Cao, Xike Xie, S Kevin Zhou

TeCES: Collaborative Geometric Knowledge Representation Framework under Evolving Fact Snapshots (2026.acl-long)

Challenge:	Large language models incur high inference costs during deployment, causing hallucination . no dedicated routing methods exist for RAG, and existing training-based routers face challenges scaling to this domain .
Approach:	They propose a plug-and-play routing framework that optimizes performance and cost . the framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x .
Outcome:	The proposed framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x compared to existing methods.

Copied to clipboard

Jiujiang Guo, Zhengliang Guo, Kai Wang, Meiyang Wang, Dehua Peng, Shaozu Yuan, Chengyin Hu, Shuan Ai, Yiwei Wei

Generative Dense Retrieval: Memory Can Be a Burden (2024.eacl-long)

Challenge:	Existing knowledge graphs represent static facts but lack collaborative modeling of both . e.g., existing knowledge graph models lack a framework for integrating snapshots into knowledge graph.
Approach:	They propose a framework for high-fidelity modeling of evolving snapshots using concept of snapshots.
Outcome:	The proposed framework outperforms existing models on six benchmarks.

Copied to clipboard

Peiwen Yuan, Xinglin Wang, Shaoxiong Feng, Boyuan Pan, Yiwei Li, Heda Wang, Xupeng Miao, Kan Li

Text Clustering

Challenge:	Empirical results show that Generative Dense Retrieval (GDR) achieves an average of 3.0 R@100 improvement on NQ dataset under multiple settings and has better scalability.
Approach:	They propose a Generative Dense Retrieval paradigm that auto-decodes document identifiers given a query and uses memory to avoid memory confusion.
Outcome:	Empirical results show that the proposed paradigm improves on the small-scale corpora and improves scalability.

Hierarchical Pretraining on Multimodal Electronic Health Records (2023.emnlp-main)

Copied to clipboard

Xiaochen Wang, Junyu Luo, Jiaqi Wang, Ziyi Yin, Suhan Cui, Yuan Zhong, Yaqing Wang, Fenglong Ma

Measuring Social Norms of Large Language Models (2024.findings-naacl)

Challenge:	Existing pretraining models on EHR data are too specific, limiting their transferability.
Approach:	They propose a general, unified pretraining framework for hierarchically multimodal EHR data that can be used to train models on a large dataset before fine-tuning it on 'upstream' tasks.
Outcome:	The proposed model performs on eight downstream tasks spanning three levels and compares with baselines on 18 different tasks.

Copied to clipboard

Ye Yuan, Kexin Tang, Jianhao Shen, Ming Zhang, Chenguang Wang

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

Challenge:	Existing datasets that evaluate a general understanding of social science are inadequate to understand social norms.
Approach:	They propose a multi-agent framework to improve large language models’ ability to understand social norms by comparing them to elementary students.
Outcome:	The proposed framework improves large language models to be on par with humans.

Copied to clipboard

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

All Languages Matter: On the Multilingual Safety of LLMs (2024.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

Wenxuan Wang, Zhaopeng Tu, Chang Chen, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, Michael Lyu

EquiBench: Benchmarking Large Language Models’ Reasoning about Program Semantics via Equivalence Checking (2025.emnlp-main)

Challenge:	Existing safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English.
Approach:	They propose a prompting method to improve multilingual safety of ChatGPT by enhancing cross-lingual generalization of safety alignment.
Outcome:	The proposed method can significantly reduce the ratio of unsafe responses by 42% for non-English queries.

Copied to clipboard

Anjiang Wei, Jiannan Cao, Ran Li, Hongyu Chen, Yuhui Zhang, Ziheng Wang, Yuan Liu, Thiago S. F. X. Teixeira, Diyi Yang, Ke Wang, Alex Aiken

Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark (2023.findings-acl)

Challenge:	EquiBench is a new benchmark to evaluate large language models' ability to reason about program semantics . Unlike natural language, code is executable.
Approach:	They propose a benchmark to evaluate large language models through equivalence checking . EquiBench consists of 2400 program pairs across four languages and six categories .
Outcome:	The proposed benchmark consists of 2400 program pairs across four languages and six categories.

Copied to clipboard

Yuxing Long, Binyuan Hui, Caixia Yuan, Fei Huang, Yongbin Li, Xiaojie Wang

A Span-based Multimodal Variational Autoencoder for Semi-supervised Multimodal Named Entity Recognition (2022.emnlp-main)

Challenge:	Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario.
Approach:	They propose a multimodal task-oriented dialog dataset with subjective preferences and recommendation acts that is well-annotated with sales experts.
Outcome:	The proposed model is powered by a state-of-the-art multimodal model for these tasks.

Copied to clipboard

Baohang Zhou, Ying Zhang, Kehui Song, Wenya Guo, Guoqing Zhao, Hongbin Wang, Xiaojie Yuan

EvoMemKG: An Evolvable Memory Agent for Multi-hop Knowledge Graph Reasoning (2026.findings-acl)

Challenge:	Existing methods for named entity recognition on social media are not efficient for semi-supervised MNER because of the mismatch between the posted text and image.
Approach:	They propose a novel method to fuse the text and image features for multimodal named entity recognition under semi-supervised setting by exploiting modal-specific VAEs.
Outcome:	The proposed method outperforms baselines under supervised setting and improves performance with less labeled data than existing semi-supervised methods.

Copied to clipboard

Shiyu Tian, Shuyue Xing, Zhuoxin Han, Caixia Yuan, Xiaojie Wang

Knowledge Representation

Challenge:	Existing methods for integrating knowledge graphs with large language models lack continuous learning capabilities.
Approach:	They propose an agent framework with a dynamic, evolvable memory mechanism specifically designed for KG reasoning.
Outcome:	EvoMemKG achieves state-of-the-art performance without training or tools . it achieves improvements of up to 20% over baseline on multi-hop queries .

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Task-Oriented Clustering for Dialogues (2021.findings-emnlp)

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Copied to clipboard

Chenxu Lv, Hengtong Lu, Shuyu Lei, Huixing Jiang, Wei Wu, Caixia Yuan, Xiaojie Wang

Poor-Supervised Evaluation for SuperLLM via Mutual Consistency (2024.findings-acl)

Challenge:	Existing methods for task-oriented dialogue clustering are difficult to apply directly due to inherent differences between them.
Approach:	They propose a Dialogue Task Clustering Network model for task-oriented clustering . they use context-aware utterance representations and cross-dialogue utterrance cluster representations .
Outcome:	The proposed model outperforms baselines on three public datasets on all metrics.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Automated Tone Transcription and Clustering with Tone2Vec (2024.findings-emnlp)

Challenge:	evaluating superLLMs is especially difficult because of their intelligence-intensive nature.
Approach:	They propose an evaluation benchmark with accurate labels for SuperLLMs whose capabilities surpass those of humans . they first prove that consistency between model under evaluation and reference model can equalize the true capabilities of the model to be evaluated .
Outcome:	The proposed evaluation benchmarks can assess the true capabilities of the model to be evaluated without accurate labels.

Copied to clipboard

Yi Yang, Yiming Wang, ZhiQiang Tang, Jiahong Yuan

Text Clustering

Challenge:	Lexical tones play a crucial role in Sino-Tibetan languages, but current phonetic fieldwork relies on manual effort.
Approach:	They propose a pitch-based similarity representations for tone transcription called Tone2Vec . they propose an open-source package that facilitates automated fieldwork and analysis .
Outcome:	Experiments on dialect clustering and variance show that Tone2Vec captures fine-grained tone variation.

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)

Copied to clipboard

Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong

RefGPT: Dialogue Generation of GPT, by GPT, and for GPT (2023.findings-emnlp)

Challenge:	Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency.
Approach:	They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs.
Outcome:	The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks.

Copied to clipboard

Dongjie Yang, Ruifeng Yuan, Yuantao Fan, Yifei Yang, Zili Wang, Shusen Wang, Hai Zhao

General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data.
Approach:	They propose a method to generate huge truthful and customized dialogues without worrying about factual errors caused by the model hallucination.
Outcome:	The proposed method solves the model hallucination in dialogue generation by restricting the LLMs to leverage the given reference instead of reciting their own knowledge to generate dialogues.

Copied to clipboard

Rui Meng, Tong Wang, Xingdi Yuan, Yingbo Zhou, Daqing He

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

Challenge:	Large distribution shifts among different domains hinder transferability of keyphrase generation models.
Approach:	They propose a pipeline which guides KPG models’ learning focus from general syntactical features to domain-related semantics in a data-efficient manner.
Outcome:	The proposed pipeline can produce good quality keyphrases in new domains and achieve consistent improvements after adaptation with limited in-domain annotated data.

Copied to clipboard

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

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

Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning (2022.aacl-main)

Copied to clipboard

Zhepei Wei, Yue Wang, Jinnan Li, Zhining Liu, Erxin Yu, Yuan Tian, Xin Wang, Yi Chang

Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization (2021.findings-emnlp)

Challenge:	Empirical study shows superiority of proposed method over time-tested knowledge-driven and data-driven methods.
Approach:	They propose a cognitive knowledge graph that unifies expert rules and relational facts as the substrate of machine learning and reasoning models.
Outcome:	Empirical results show the proposed method superior to time-tested methods . the proposed model can perform both learning and reasoning with labeled data .

Copied to clipboard

Junpeng Liu, Yanyan Zou, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Caixia Yuan, Xiaojie Wang

Explaining Length Bias in LLM-Based Preference Evaluations (2025.findings-emnlp)

Challenge:	Existing methods to abstractly summarize dialogues are limited to two or more interlocutors.
Approach:	They propose to use existing document summarization models to capture the various topic information of a conversation and outline salient facts for the captured topics.
Outcome:	The proposed method significantly outperforms baselines and achieves new state-of-the-art performance on benchmark datasets.

Copied to clipboard

Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong

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

Challenge:	a preference evaluation metric is often biased towards longer responses, revealing a reliability problem . a decomposition of the preference evaluation into two components is needed to understand this bias.
Approach:	They propose to decompose the preference evaluation metric into two key components . the first component is length-dependent and related to trustworthiness .
Outcome:	The proposed evaluation metric is based on two components: desirability and information mass.

Copied to clipboard

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

Transformer-based Speech Model Learns Well as Infants and Encodes Abstractions through Exemplars in the Poverty of the Stimulus Environment (2025.coling-main)

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

Copied to clipboard

Yi Yang, Yiming Wang, Jiahong Yuan

Character is Destiny: Can Persona-assigned Language Models Make Personal Choices? (2025.findings-emnlp)

Challenge:	Existing theories of language learning for infants are inadequate, according to Chomsky . infants learn language in impoverished environments, according a new study .
Approach:	They designed a series of tasks, scenarios, and metrics to simulate the POS . they found that the emerging speech model wav2vec2.0 can learn well in noisy Mandarin environments.
Outcome:	The proposed model can learn in noisy and sparse Mandarin environments.

Copied to clipboard

Rui Xu, Xintao Wang, Jiangjie Chen, Siyu Yuan, Xinfeng Yuan, Jiaqing Liang, Zulong Chen, null Xiaoqingdong, Yanghua Xiao

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human–Agent Interaction (2026.acl-long)

Challenge:	Recent research has demonstrated the potential of using LLMs to develop role-playing language agents (RPLAs) however, imitative decision-making necessitates a more nuanced understanding of personas.
Approach:	They propose a method that uses persona-based memory retrieval to improve RPLAs.
Outcome:	The proposed method significantly advances RPLAs on this task.

Copied to clipboard

Zisu Huang, Muzhao Tian, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng

Challenge:	Existing systems that use memory as an "all-or-nothing" approach to memory usage are often static and rely on experience-following tendencies.
Approach:	They propose a framework that allows users to dynamically regulate memory reliance by adding context into the model's prompt.
Outcome:	The proposed model outperforms prompting and memory masking strategies in multiple scenarios.

Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation (2023.findings-acl)

Copied to clipboard

Xingdi Yuan, Tong Wang, Yen-Hsiang Wang, Emery Fine, Rania Abdelghani, Hélène Sauzéon, Pierre-Yves Oudeyer