Papers by Yang Tan

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? (2025.acl-long)

Challenge:	Existing work on robustness in text or code tasks has focused on classification, while robustness for code generation tasks is an uncharted area.
Approach:	They propose a robustness evaluation benchmark for code generation models that customizes over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format.
Outcome:	The proposed model performs better on human annotators and on SOTA models with human annnotators.

Copied to clipboard

Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Chong Sun, Xiaoshuai Song, Jiapeng Wang, Zhuoma GongQue, Shanglin Lei, YiFan Zhang, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Xiao Zong, Yida Xu, Peiqing Yang, Zhimin Bao, Muxi Diao, Chen Li, Honggang Zhang

Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to LLM-Centered Topic Analysis (2026.findings-acl)

Challenge:	Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach:	They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome:	The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.

Copied to clipboard

Xuan Xu, Zhongliang Yang, Haolun Li, Rui Tian, Beilin Chu, J Song, Yu Li, Shaolin Tan, Linna Zhou

Information Extraction & Text Mining

Challenge:	Topic modeling (TM) is a classic unsupervised learning task in the field of natural language processing.
Approach:	They propose a new taxonomy that emphasizes the role of LLMs and the design of end-to-end workflows.
Outcome:	The proposed taxonomy emphasizes the role of LLMs and the design of end-to-end workflows.

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Copied to clipboard

Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

From Charts to Code: A Hierarchical Benchmark for Multimodal Models (2026.acl-long)

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

Copied to clipboard

Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang

Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification (2025.emnlp-main)

Challenge:	Chart2Code is a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Approach:	They introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models.
Outcome:	The proposed benchmark is the first to scale task complexity while capturing diverse scenarios.

Copied to clipboard

Boyang Zhang, Yicong Tan, Yun Shen, Ahmed Salem, Michael Backes, Savvas Zannettou, Yang Zhang

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

Challenge:	Recent advances in large language models (LLMs) have increased the vulnerability of LLMs, but they can cause more severe damage than standalone systems if compromised.
Approach:	They propose a new type of attack that induces malfunctions by misleading the agent into executing repetitive or irrelevant actions.
Outcome:	The proposed attacks induce failure rates exceeding 80% in multiple scenarios, highlighting the substantial risks associated with this vulnerability.

Copied to clipboard

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

Structured Data in NLP

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

MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators (2022.acl-long)

Copied to clipboard

Zhixing Tan, Xiangwen Zhang, Shuo Wang, Yang Liu

CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models (2024.emnlp-main)

Challenge:	Prompting has been shown to be a promising approach for applying pre-trained language models to perform downstream tasks.
Approach:	They propose a method that divides the translation process into three stages using pre-trained language models.
Outcome:	The proposed method significantly improves translation performance of pre-trained language models on three translation tasks.

Copied to clipboard

Jiawei Gu, Zacc Yang, Chuanghao Ding, Rui Zhao, Fei Tan

Towards Fine-grained Text Sentiment Transfer (P19-1)

Challenge:	Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus.
Approach:	They propose a power-law relationship between loss, mixture ratio, and training tokens scale and formalize the trade-off between general and domain-specific capabilities.
Outcome:	The proposed model achieves the desired domain transfer while maintaining general ability and highest utilization of available resources.

Copied to clipboard

Fuli Luo, Peng Li, Pengcheng Yang, Jie Zhou, Yutong Tan, Baobao Chang, Zhifang Sui, Xu Sun

Sentiment Analysis

Challenge:	Existing methods for fine-grained text sentiment transfer only reverse the sentiment polarity of text, but they lack a robust and parallel learning algorithm.
Approach:	They propose a novel fine-grained text sentiment transfer task that revises a sequence to satisfy a given sentiment intensity while preserving the original semantic content.
Outcome:	The proposed model outperforms existing methods by a large margin in automatic evaluation and human evaluation.

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data (2025.findings-acl)

Copied to clipboard

Juntao Tan, Liangwei Yang, Zuxin Liu, Zhiwei Liu, Rithesh R N, Tulika Manoj Awalgaonkar, Jianguo Zhang, Weiran Yao, Ming Zhu, Shirley Kokane, Silvio Savarese, Huan Wang, Caiming Xiong, Shelby Heinecke

Out-of-Domain Detection for Low-Resource Text Classification Tasks (D19-1)

Challenge:	Existing research lacks direct access to such data, making benchmarking difficult due to privacy concerns.
Approach:	They propose a synthetic data pipeline that generates realistic user profiles and private documents and a benchmark to evaluate models' ability to understand personal information.
Outcome:	The proposed pipeline generates realistic user profiles and private documents, enabling PersonaBench, a benchmark for evaluating models’ ability to understand personal information.

Copied to clipboard

Ming Tan, Yang Yu, Haoyu Wang, Dakuo Wang, Saloni Potdar, Shiyu Chang, Mo Yu

Low-Resource NLP

Challenge:	Existing methods for OOD detection and ID classification tasks require massive amounts of ID labeled data and no OOD labeles.
Approach:	They propose to use OOD-resistant Prototypical Network to detect OOD cases with limited in-domain (ID) training data to solve this task.
Outcome:	The proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task while maintaining a competitive performance on ID classification task.

Towards Unified Prompt Tuning for Few-shot Text Classification (2022.findings-emnlp)

Copied to clipboard

Jianing Wang, Chengyu Wang, Fuli Luo, Chuanqi Tan, Minghui Qiu, Fei Yang, Qiuhui Shi, Songfang Huang, Ming Gao

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Challenge:	Prompt-based fine-tuning has boosted performance of Pre-trained Language Models (PLMs) on few-shot text classification, but PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few- shot learning performance on downstream tasks.
Approach:	They propose a framework for prompt-based fine-tuning that captures prompting semantics from non-target NLP datasets and propose 'Prompt-Options-Verbalizer' for joint prompt learning across different NLP tasks.
Outcome:	Experiments show that the proposed framework outperforms state-of-the-art prompt-based fine-tuning frameworks on few-shot text classification tasks.

Copied to clipboard

Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing

The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025.acl-long)

Challenge:	Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach:	They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome:	Texar supports machine translation, summarization, dialog, content manipulation, and more.

Copied to clipboard

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Qi Cao, Dawei Yin, Huawei Shen, Xueqi Cheng

Question Answering

Challenge:	despite near-perfect results, effectiveness of model editing in real-world applications remains unclear.
Approach:	They propose QAEdit and WILD to better reflect real-world use of model editing . they propose a benchmark aligned with widely used question answering datasets and a task-agnostic evaluation framework .
Outcome:	The proposed QAEdit benchmark and WILD evaluation framework show that current models perform worse than previously reported.

DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature (2024.findings-emnlp)

Copied to clipboard

Dawei Li, Shu Yang, Zhen Tan, Jae Baik, Sukwon Yun, Joseph Lee, Aaron Chacko, Bojian Hou, Duy Duong-Tran, Ying Ding, Huan Liu, Li Shen, Tianlong Chen

Structured Data in NLP

Challenge:	Recent advances in large language models have achieved promising performances across various applications, but the challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains.
Approach:	They propose a dynamic co-augmentation framework for the refinement of large language models and knowledge graphs in the context of Alzheimer's Disease.
Outcome:	The proposed framework can be used to study Alzheimer's Disease (AD) using LLMs and KGs.

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

Copied to clipboard

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

Rethinking Depression Prediction from a Fine-Grained Subscore Modeling Perspective via Multi-Task Learning (2026.acl-long)

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

Copied to clipboard

Zhenguang Wang, Bo Li, Wenhui Tan, Peng Cao, Yang Wang, Jia Duan, Fei Wang, Osmar Zaiane

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

Challenge:	Existing methods for depression assessment rely on standardized ratings, but they are time-consuming and subject to inter-rater variability.
Approach:	They propose a fine-grained model for subscore prediction via multi-task learning that can be used to predict depression severity using multiple tasks.
Outcome:	The proposed model outperforms baselines and Qwen3-14B direct scoring on the public E-DAIC dataset and to a large-scale private clinical dataset.

Copied to clipboard

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

AgentAsk: Multi-Agent Systems Need to Ask (2026.acl-long)

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

Copied to clipboard

Bohan Lin, Kuo Yang, Zelin Tan, Yingchuan Lai, Chen Zhang, Guibin Zhang, Xinlei Yu, Miao Yu, Xu Wang, Yudong Zhang, Yang Wang

Green & Sustainable NLP

Challenge:	Multi-agent systems fail to consistently outperform strong single-a agent baselines due to error propagation at inter-aggent message handoffs.
Approach:	They propose an edge-level error taxonomy that identifies four main errors in multi-agent interactions as data gaps, signal corruption, referential drift and capacity gaps as primary sources of failure.
Outcome:	The proposed module outperforms existing systems on five benchmarks and is architecture-agnostic.

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

Copied to clipboard

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

EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms (2025.naacl-long)

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

Copied to clipboard

Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, Deqing Yang

CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations (2025.coling-main)

Challenge:	Existing work on extending specialized agents to multi-agent systems is dependent on human-designed frameworks, limiting the functional scope and scalability of agent systems.
Approach:	They propose a generic method to automatically extend specialized agents to multi-agent systems via evolutionary algorithm . they consider existing agent frameworks as the initial individual and apply evolutionary operators to generate multiple agents with diverse settings.
Outcome:	The proposed method can extend specialized agents to multi-agent systems . it can generate multiple agents with diverse settings, and improves performance across tasks .

Copied to clipboard

Jiahao Zhao, Jingwei Zhu, Minghuan Tan, Min Yang, Renhao Li, Yang Di, Chenhao Zhang, Guancheng Ye, Chengming Li, Xiping Hu, Derek F. Wong

Challenge:	CPsyExam prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.
Approach:	They propose a psychological benchmark, CPsyExam, constructed from questions from Chinese examination systems.
Outcome:	The proposed benchmark prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.

TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph (2022.coling-1)

Copied to clipboard

Zhitong Yang, Bo Wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou

Dialogue Systems & Conversational Agents

Challenge:	Existing target-oriented dialogs take a local and greedy strategy for response generation, where global planning is absent.
Approach:	They propose a global planning method for target-oriented dialog on a commonsense knowledge graph to adjust local response generation towards the global target.
Outcome:	The proposed method can reach the target with a higher success rate, fewer turns, and more coherent responses.

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)

Copied to clipboard

Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun

Consultant Decoding: Yet Another Synergistic Mechanism (2025.findings-acl)

Challenge:	Scientific data visualization is an essential process in research, but its use of large language models remains unexplored.
Approach:	They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks.
Outcome:	The proposed framework improves performance of commercial and open-source models.

Copied to clipboard

Chuanghao Ding, Jiaping Wang, Ziqing Yang, Xiaoliang Wang, Dahua Lin, Nguyen Cam-Tu, Fei Tan

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2026.findings-acl)

Challenge:	Large language models (LLMs) have attracted widespread attention and adoption across diverse domains due to their exceptional performance and robust generalization abilities.
Approach:	They propose a synergetic mechanism for Consultant Decoding (CD) that achieves a 2.5-fold increase in inference speed compared to the target model while maintaining comparable generation quality.
Outcome:	The proposed mechanism achieves 2.5-fold increase in inference speed while maintaining comparable generation quality (100% of the target model’s performance).

Copied to clipboard

Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu

Focal Training and Tagger Decouple for Grammatical Error Correction (2023.findings-acl)

Challenge:	Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning from large language models (LLMs).
Approach:	They propose a data distribution lens to understand when and why CoT reasoning fails . they propose 'data-based' training that trains LLMs from scratch .
Outcome:	The proposed model enables models to generate reasoning trajectories that approximate those observed during training.

Copied to clipboard

Minghuan Tan, Min Yang, Ruifeng Xu

Syntactic Text Processing

Challenge:	Existing methods for Grammatical Error Correction (GEC) are categorized into sequence-to-sequence approaches, tagging-based approaches, and hybrid approaches.
Approach:	They propose to decouple error detection layer from label tagging layer and to down-weight label imbalance and tabbing entanglement loss using Focal Loss.
Outcome:	The proposed methods are effective over three latest Chinese Grammatical Error Correction datasets.

SegDRE: A Salient Entity Guided Approach to Document-Level Relation Extraction (2026.findings-acl)

Copied to clipboard

Xing Yang, Chengxiang Tan

Information Extraction & Text Mining

Challenge:	Existing models struggle to address two major bottlenecks in Document-level Relation Extraction: extreme class imbalance and complexity of multi-hop reasoning.
Approach:	They propose a method that decouples the extraction space into dense and sparse scenarios.
Outcome:	The proposed approach yields consistent improvements over various backbone models and achieves advanced performance compared to existing enhancement methods.

Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning (2024.findings-acl)

Copied to clipboard

Qiming Bao, Alex Peng, Zhenyun Deng, Wanjun Zhong, Gael Gendron, Timothy Pistotti, Neset Tan, Nathan Young, Yang Chen, Yonghua Zhu, Paul Denny, Michael Witbrock, Jiamou Liu

CoEvol: Constructing Better Responses for Instruction Finetuning through Multi-Agent Cooperation (2024.emnlp-main)

Challenge:	Empirical evidence shows that our proposed method improves performance across seven downstream tasks.
Approach:	They propose a logic-driven data augmentation approach that converts text into AMR graphs and converts them back into text to create augmented data.
Outcome:	The proposed method leads on the ReClor leaderboard and improves on seven downstream tasks.

Copied to clipboard

Renhao Li, Minghuan Tan, Derek Wong, Min Yang

CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling (2024.findings-acl)

Challenge:	Recent studies have focused on constructing substantial quantities of IFT data with minimal human effort.
Approach:	They propose a multi-agent cooperation framework for the improvement of IFT responses for large language models using a debate-advise-edit-judge paradigm.
Outcome:	The proposed framework outperforms baseline models on unseen tasks and shows that it can improve instruction-following capabilities on large language models.

Copied to clipboard

Chenhao Zhang, Renhao Li, Minghuan Tan, Min Yang, Jingwei Zhu, Di Yang, Jiahao Zhao, Guancheng Ye, Chengming Li, Xiping Hu

Dialogue Systems & Conversational Agents

Challenge:	Existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence.
Approach:	They propose a report-based multi-turn dialogue reconstruction framework for Chinese psychological counseling that uses large language models to assist counseling.
Outcome:	The proposed framework is open-source and can be used in future research.

Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model (2024.findings-acl)

Copied to clipboard

Hengyuan Zhang, Yanru Wu, Dawei Li, Sak Yang, Rui Zhao, Yong Jiang, Fei Tan

Dynamic Transformers Provide a False Sense of Efficiency (2023.acl-long)

Challenge:	Aligned Large Language Models exhibit remarkable versatility, capable of handling diverse real-world tasks.
Approach:	They propose a coarse to fine framework to fine-tune aligned Large Language Models to achieve a balance between speciality and versatility.
Outcome:	The proposed framework outperforms baseline methods across diverse tasks and model scales.

Copied to clipboard

Yiming Chen, Simin Chen, Zexin Li, Wei Yang, Cong Liu, Robby Tan, Haizhou Li

Integrating Vectorized Lexical Constraints for Neural Machine Translation (2022.acl-long)

Challenge:	Pre-trained language models typically lead to high computational cost during inference.
Approach:	They propose a slowdown attack framework that can reduce inference efficiency by 80% by leveraging existing adversarial attacks targeting model accuracy.
Outcome:	The proposed framework can reduce the efficiency of multi-exit models by 80% on average, validating its effectiveness and generalization ability.

Copied to clipboard

Shuo Wang, Zhixing Tan, Yang Liu

Multilinguality

Challenge:	Existing studies focus on integrating discrete lexical constraints into neural machine translation models.
Approach:	They propose to integrate constraints into NMT models by integrating them into keys and values . they show that their method outperforms representative baselines on four language pairs .
Outcome:	The proposed method outperforms baselines on four language pairs, showing superiority .

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.acl-long)

Copied to clipboard

Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun

Robustness in NLP

Challenge:	Existing approaches to safety alignment of large language models rely on costly manual annotations or human review.
Approach:	They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation.
Outcome:	The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability.

A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings (2022.findings-acl)

Copied to clipboard

Haochen Tan, Wei Shao, Han Wu, Ke Yang, Linqi Song

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? (2024.acl-long)

Challenge:	Existing approaches to contrastive learning are heavily affected by superficial features like sentence length and syntax.
Approach:	They propose a semantic-aware contrastive learning framework for sentence embeddings that explores the pseudo-token space representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax.
Outcome:	The proposed framework outperforms the state-of-the-art on six standard semantic textual similarity tasks while maintaining an additional queue to store the representation of sentence embeddings.

Copied to clipboard

Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, Xueqi Cheng

QAEval: Mixture of Evaluators for Question-Answering Task Evaluation (2025.acl-long)

Challenge:	Recent advances in augmenting Large Language Models (LLMs) with auxiliary information have significantly revolutionized their efficacy in knowledge-intensive tasks.
Approach:	They propose a systematic framework to identify whether LLMs’ responses are attributed to either generated or retrieved contexts.
Outcome:	The proposed framework identifies whether LLMs’ responses are attributed to either generated or retrieved contexts.

Copied to clipboard

Tan Yue, Rui Mao, Xuzhao Shi, Shuo Zhan, Zuhao Yang, Dongyan Zhao

Natural Language Interfaces

Challenge:	Existing QA evaluation methods struggle with open-ended and unstructured responses.
Approach:	They propose a hybrid framework that combines rule-based reliability with LLM-based adaptability to overcome these challenges.
Outcome:	The proposed framework outperforms existing models like GPT-4o and Claude-3 in accuracy and cost.

ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents (2026.findings-acl)

Copied to clipboard

Yilun Yao, Shan Huang, Elsie Dai, Zhewen Tan, Zhenyu Duan, Shousheng Jia, Yanbing Jiang, Tong Yang

DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment (2024.findings-emnlp)

Challenge:	Existing approaches to managing context are based on raw accumulation or passive summarization, treating it as static artifact and allowing early errors or misplaced emphasis to persist.
Approach:	They propose a framework that treats context as a dynamic internal reasoning state during execution.
Outcome:	Experiments on long-horizon information-seeking benchmarks show that ARC outperforms passive context compression methods.

Copied to clipboard

Liang Zhu, Feiteng Fang, Yuelin Bai, Longze Chen, Zhexiang Zhang, Minghuan Tan, Min Yang

Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation (2023.acl-long)

Challenge:	Experimental results show that the methods enhanced by DEFT outperform the original methods in both alignment capability and generalization ability, with significantly reduced training time.
Approach:	They propose a distribution-based alignment framework that integrates data filtering and distributional guidance to improve alignment efficiency and generalization ability.
Outcome:	The proposed framework outperforms existing methods in alignment capability and generalization ability with significantly reduced training time.

Copied to clipboard

Robert Giaquinto, Dejiao Zhang, Benjamin Kleiner, Yang Li, Ming Tan, Parminder Bhatia, Ramesh Nallapati, Xiaofei Ma

NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models (2024.findings-acl)

Challenge:	Existing methods for learning representations of structured knowledge are limited to the minority of people with technical skills.
Approach:	They propose a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem.
Outcome:	The proposed model improves on two SQL tasks and shows a 1.7 and 2.2 percentage point improvement over existing methods.

Copied to clipboard

Ancheng Xu, Minghuan Tan, Lei Wang, Min Yang, Ruifeng Xu

Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training (2024.findings-acl)

Challenge:	Existing LLMs are not able to handle numerals and units of measurement, but they can be improved by introducing perturbations.
Approach:	They propose to analyze existing LLMs on processing numerals and units of measurement by perturbing their datasets.
Outcome:	The proposed model improves on ancient Chinese arithmetic problems and can handle numeral and measurement conversions.

Copied to clipboard

Qingyan Guo, Rui Wang, Junliang Guo, Xu Tan, Jiang Bian, Yujiu Yang

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

Challenge:	Large language models (LLMs) have achieved impressive performance across diverse tasks, but suffer from the "reversal curse" this limitation poses a challenge to the advancement of artificial general intelligence (AGI)
Approach:	They propose to use training data to permute training sentences into entities and feed them into the model.
Outcome:	The proposed method improves the performance of large language models (LLMs) on reversed questions and improves existing models.

Copied to clipboard

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

V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me (2025.acl-long)

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

Copied to clipboard

Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Jiapeng Wang, YiFan Zhang, Zhuoma GongQue, Chong Sun, Yida Xu, Yadong Xue, Ye Tian, Zhimin Bao, Lan Yang, Chen Li, Honggang Zhang

Self-Supervised Quality Estimation for Machine Translation (2021.emnlp-main)

Challenge:	Deciphering oracle bone scripts using AI technology is not an overnight task due to the evolution of written language over millennia.
Approach:	They propose a framework that utilizes Large Multi-modal Models (LMMs) for interpreting Oracle Bone Script (OBS).
Outcome:	The proposed framework provides quantitative analyses and superior deciphering capability.

Copied to clipboard

Yuanhang Zheng, Zhixing Tan, Meng Zhang, Mieradilijiang Maimaiti, Huanbo Luan, Maosong Sun, Qun Liu, Yang Liu

Rejection-to-Acceptance Transition: Model Editing-Based Jailbreak Backdoor Injection Not Limited to Few Output Tokens (2026.findings-acl)

Challenge:	Training QE models require massive parallel data with hand-crafted quality annotations, which are time-consuming and labor-intensive to obtain.
Approach:	They propose a self-supervised method to evaluate machine-translated sentences without references by recovering masked target words.
Outcome:	The proposed method outperforms previous unsupervised methods on several QE tasks in different language pairs and domains.

Copied to clipboard

Shiji Yang, Min Cai, Hao Xiong, Congyao Mei, Haodong Zou, Shicheng Tan, Jie Chen, Fulan Qian, Shu Zhao

Robustness in NLP

Challenge:	Existing methods for jailbreaking LLMs are implemented by binding backdoors to predefined phrases as first few output tokens, inducing the LLM’s next-token prediction to produce continuous responses.
Approach:	They propose a model editing-based jailbreak backdoor attack that hijacks LLM representations into a acceptance domain rather than binding to a few output tokens.
Outcome:	The proposed model editing method outperforms existing methods, showing stronger jailbreak capabilities across LLMs and datasets.

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring (2026.acl-long)

Copied to clipboard

Dongxu Zhang, Yiding Sun, Cheng Tan, Wenbiao Yan, Ning Yang, Jihua Zhu, Haijun Zhang

Knowledge Representation Learning with Contrastive Completion Coding (2021.findings-emnlp)

Challenge:	Existing efforts to mitigate this via token compression fail due to its autoregressive nature . linguistically redundant tokens are erroneously pruned, leading to hallucinations .
Approach:	They propose a method that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem.
Outcome:	Experiments on Qwen2-VL and Llama-3.2 families show that the proposed model achieves a speedup with negligible accuracy loss.

Copied to clipboard

Bo Ouyang, Wenbing Huang, Runfa Chen, Zhixing Tan, Yang Liu, Maosong Sun, Jihong Zhu

Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)

Challenge:	Existing knowledge representation learning methods suffer from immaturity on tackling potentially-imperfect knowledge graphs and highly-imbalanced positive-negative instances during training.
Approach:	They propose a framework for knowledge representation learning that incorporates two functional components to achieve robust embedding for each entity/relation.
Outcome:	The proposed framework achieves better convergence against state-of-the-art methods on several benchmarks.

Copied to clipboard

Ruochong Xiong, Qien Li, Wangwang Lian, Yulong Wan, Hanlin Xue, Zhouxing Tan, Han Yang, Fengyu Lu, Junfei Liu

STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation (2025.findings-acl)

Challenge:	Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability.
Approach:	They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures.
Outcome:	The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios.

Copied to clipboard

Jiaming Li, Yukun Chen, Ziqiang Liu, Minghuan Tan, Lei Zhang, Yunshui Li, Run Luo, Longze Chen, Jing Luo, Ahmadreza Argha, Hamid Alinejad-Rokny, Wei Zhou, Min Yang

On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)

Challenge:	Existing methods for storytelling lack coherence and consistency, compromising the overall storytelling experience.
Approach:	They propose a novel approach that improves the coherence and consistency of automatically generated stories by managing plot nodes and enabling dynamic interactions between different parts of the story.
Outcome:	The proposed approach outperforms existing methods in 84.33% of the trials.

Copied to clipboard

Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie

Dialogue Systems & Conversational Agents

Challenge:	under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors.
Approach:	They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients .
Outcome:	The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets.

MalayMMLU: A Multitask Benchmark for the Low-Resource Malay Language (2024.findings-emnlp)

Copied to clipboard

Soon Poh, Sze Jue Yang, Jeraelyn Tan, Lawrence Chieng, Jia Tan, Zhenyu Yu, Foong Mun, Chee Seng Chan

SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Challenge:	Large Language Models (LLMs) and Large Vision Language Model (LVLMs) exhibit advanced proficiency in language reasoning and comprehension across a wide array of languages.
Approach:	They propose to use a multitask language understanding benchmark specifically designed for the Malay language to assess their proficiency.
Outcome:	The proposed model performs well in well-resourced languages, but in low-resource languages such as Bahasa Melayu, they are less studied due to a lack of studies and benchmarks.

Copied to clipboard

Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing

WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling (2026.findings-acl)

Challenge:	Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach:	They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome:	SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .

Copied to clipboard

Jiacheng Li, Jianchao Tan, Zhidong Yang, Pingwei Sun, Feiye Huo, Jiayu Qin, Xiangyu Zhang, Maoxin He, Guangming Tan, Weile Jia, Xunliang Cai, Tong Zhao

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

Challenge:	Recent advances in training optimization for Transformer-based large language models lack systematic optimization of weight patterns during training.
Approach:	They propose a Weight Scaling method that rescales weights while preserving model outputs to improve model training efficiency and model quality.
Outcome:	The proposed method significantly improves convergence quality and loss reduction in LLMs with Grouped Query Attention architectures and LoRA fine-tuning tasks.

Copied to clipboard

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

EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction (2025.naacl-long)

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

Copied to clipboard

Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Kan Ren, Dongsheng Li, Deqing Yang

End-to-End Open-Domain Question Answering with BERTserini (N19-4)

Challenge:	EASYTOOL combines tools from diverse tool documentation into a single tool instruction.
Approach:	They propose a framework that transforms tool documentation into a unified tool instruction.
Outcome:	EASYTOOL combines extensive tool documentation into a concise tool instruction . it reduces token consumption and improves performance of LLM-based agents .

Copied to clipboard

Wei Yang, Yuqing Xie, Aileen Lin, Xingyu Li, Luchen Tan, Kun Xiong, Ming Li, Jimmy Lin

Question Answering

Challenge:	a new open-domain question answering system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles.
Approach:	They propose an end-to-end question answering system that integrates BERT with an IR reader.
Outcome:	The proposed system improves on a standard benchmark test collection.

On the Language Coverage Bias for Neural Machine Translation (2021.findings-acl)

Copied to clipboard

Shuo Wang, Zhaopeng Tu, Zhixing Tan, Shuming Shi, Maosong Sun, Yang Liu

Multilinguality

Challenge:	Language coverage bias is important for neural machine translation because of the target-original training data.
Approach:	They propose two approaches to alleviate the language coverage bias problem by explicitly distinguishing between the source-and target-original training data.
Outcome:	The proposed methods improve translation tasks on both back-and forward-translation and their tagged variants.

Multi2Claim: Generating Scientific Claims from Multi-Choice Questions for Scientific Fact-Checking (2023.eacl-main)

Copied to clipboard

Neset Tan, Trung Nguyen, Josh Bensemann, Alex Peng, Qiming Bao, Yang Chen, Mark Gahegan, Michael Witbrock

Banking Done Right: Redefining Retail Banking with Language-Centric AI (2025.emnlp-industry)

Challenge:	Existing scientific fact-checking datasets are limited due to expertise bottleneck . multi2Claim pipeline is a tool to convert multiple-choice questions into fact- checking data .
Approach:	They propose a pipeline for automatically converting multiple-choice questions into fact-checking data . they generate two large-scale datasets for scientific-fact-checker tasks . success at this task can help the reader understand scientific topics and promote science .
Outcome:	The proposed pipeline improves performance on two large-scale scientific fact-checking datasets.

Copied to clipboard

Xin Jie Chua, Jeraelyn Ming Li Tan, Jia Xuan Tan, Soon Chang Poh, Yi Xian Goh, Debbie Hui Tian Choong, Foong Chee Mun, Sze Jue Yang, Chee Seng Chan

Natural Language Interfaces

Challenge:	This is the first global regulator-approved deployment where conversational AI functions as the primary banking interface.
Approach:	They propose a framework that powers a conversational AI framework that is powered by a closed-source LLM developed internally and replaces rigid multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents.
Outcome:	The proposed framework replaces multi-screen workflows with a single dialogue orchestrated by four LLM-powered agents (Guardrails, Intent, Payment, and FAQ).

Progressive Generation of Long Text with Pretrained Language Models (2021.naacl-main)

Copied to clipboard

Bowen Tan, Zichao Yang, Maruan Al-Shedivat, Eric Xing, Zhiting Hu

Taming the Real-world Complexities in CPT E/M Coding with Large Language Models (2025.emnlp-industry)

Challenge:	Existing methods for "long" text generation are limited to outputs of 50-200 tokens . however, our proposed ProGen generates coherent long passages of text in a progressive manner .
Approach:	They propose a method for generating coherent long passages of text in a progressive manner . they first produce domain-specific content keywords and then refine them into complete passages . human evaluation validates that their proposed generation is more coherent .
Outcome:	The proposed method produces domain-specific content keywords and refines them into complete passages in multiple stages.

Copied to clipboard

Islam Nassar, Yang Lin, Yuan Jin, Rongxin Zhu, Chang Wei Tan, Zenan Zhai, Nitika Mathur, Thanh Tien Vu, Xu Zhong, Long Duong, Yuan-Fang Li

MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property (2024.lrec-main)

Challenge:	Evaluation and Management (E/M) coding is performed by physicians and trained human coders who review clinical encounter notes and electronic health record data to assign appropriate codes.
Approach:	They propose a framework that automates evaluation and management coding tasks using the Current Procedural Terminology (CPT) taxonomy.
Outcome:	The proposed framework achieves an increase in coding accuracy of more than 36% over a commercial CPT E/M coding system and almost 5% over our strongest single-prompt baseline.

Copied to clipboard

Shiwen Ni, Minghuan Tan, Yuelin Bai, Fuqiang Niu, Min Yang, Bowen Zhang, Ruifeng Xu, Xiaojun Chen, Chengming Li, Xiping Hu

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks.
Approach:	They propose a benchmark for the evaluation of large language models in the IP domain . they also propose supervised multilingual large language model called MoZi .
Outcome:	The proposed model outperforms four well-known LLMs on the MoZIP benchmark . the most powerful ChatGPT does not reach the passing level .

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Copied to clipboard

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao

Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)

Challenge:	Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach:	They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome:	The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.

Copied to clipboard

Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin

Challenge:	e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features.
Approach:	They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent.
Outcome:	The proposed model outperforms baseline models and provides better recall and triage for specialized agents.

M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

Copied to clipboard

Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Programming Languages in NLP

Challenge:	Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach:	They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome:	The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)

Copied to clipboard

Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Neural-DINF: A Neural Network based Framework for Measuring Document Influence (2020.acl-main)

Challenge:	Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations.
Approach:	They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference.
Outcome:	The proposed method significantly mitigates object hallucinations across various model architectures.

Copied to clipboard

Jie Tan, Changlin Yang, Ying Li, Siliang Tang, Chen Huang, Yueting Zhuang

Challenge:	Existing methods to measure scholarly impact of documents without citations only consider word frequency change.
Approach:	They propose a neural network framework that measures document influence without citations by using word frequency changes and word semantic shifts.
Outcome:	The proposed model outperforms existing models on document influence evaluation without citations.

A Template-based Method for Constrained Neural Machine Translation (2022.emnlp-main)

Copied to clipboard

Shuo Wang, Peng Li, Zhixing Tan, Zhaopeng Tu, Maosong Sun, Yang Liu

Multilinguality

Challenge:	Existing methods to solve this problem can not satisfy the following three desiderata: (1) high translation quality, (2) high match accuracy, and (3) low latency.
Approach:	They propose a template-based method that can provide high translation quality and match accuracy and a low latency inference.
Outcome:	The proposed method outperforms baselines in lexically and structurally constrained translation tasks and can be used in a variety of applications.

AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)

Copied to clipboard

Kaibo Huang, Jin Tan, Yukun Wei, Wanling Li, Zipei Zhang, Hui Tian, Zhongliang Yang, Linna Zhou

Challenge:	Recent advances in large language models (LLMs) have improved text generation and reasoning.
Approach:	They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility.
Outcome:	The proposed framework embeds multi-bit provenance into planning decisions while preserving utility.

The Fall of ROME: Understanding the Collapse of LLMs in Model Editing (2024.findings-emnlp)

Copied to clipboard

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Du Su, Dawei Yin, Huawei Shen

BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026.acl-long)

Challenge:	Recent studies have found that model editing methods can cause large language models to collapse with just a single edit.
Approach:	They propose a method that uses prefixed keys and adds prefixes during testing to prevent model collapse.
Outcome:	The proposed method prevents model collapse while maintaining effectiveness, the authors show . Rank-One Model Editing (ROME) has been found to cause model collapse with just a single edit .

Copied to clipboard

Hexiang Tan, Wanli Yang, Junwei Zhang, Xin Chen, Rui Tang, Du Su, Jingang Wang, Yuanzhuo Wang, Fei Sun, Xueqi Cheng

Unsupervised Speech-text word-level alignment with Dynamic Programming (2025.findings-naacl)

Challenge:	Post-trained LLMs typically compromise reliability with severe overconfidence, resulting in inaccurate responses.
Approach:	They propose a solution that feeds PoLLMs into the base LLM to get confidence.
Outcome:	The proposed solution reduces expected calibration error (ECE) by 42.90% compared to the best unsupervised baselines.

Copied to clipboard

Tianshu Yu, Zihan Gong, Minghuan Tan, Guhong Chen, Min Yang

More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning (2025.emnlp-industry)

Challenge:	Word-level alignment in speech-text pretraining models is limited by word-level annotated data . authors propose an iterative training method for USDP that reduces the dependency on scarce annotation resources.
Approach:	They propose an Unsupervised Speech-text word-level alignment with Dynamic Programming (USDP) this method uses Dynamic programming principles to iteratively refine temporal alignment predictions .
Outcome:	The proposed method significantly improves on speech-text pretraining tasks compared to existing methods.

Copied to clipboard

Yike Zhao, Simin Guo, Ziqing Yang, Shifan Han, Dahua Lin, Fei Tan

VenusFactory: An Integrated System for Protein Engineering with Data Retrieval and Language Model Fine-Tuning (2025.acl-demo)

Challenge:	Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored.
Approach:	They conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning under a unified pipeline designed to mirror training and deployment scenarios.
Outcome:	The proposed pipelines mirror training and deployment scenarios and are suitable for industrial applications.

Copied to clipboard

Yang Tan, Chen Liu, Jingyuan Gao, Wu Banghao, Mingchen Li, Ruilin Wang, Lingrong Zhang, Huiqun Yu, Guisheng Fan, Liang Hong, Bingxin Zhou