Papers by Yuan He

The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service (2020.lrec-1)

Challenge:	Existing approaches to mitigating vision-knowledge conflict in Large Language Models (MLLMs) are not effective and can be further scaled.
Approach:	They propose a framework to generate inputs to simulate and evaluate vision-knowledge conflict in Multimodal Large Language Models (MLLMs) using original images and 1,122 high-quality question-answer pairs, they propose 'a diagnostic benchmark'
Outcome:	The proposed framework, benchmark, and analysis contribute to the understanding and mitigation of vision-knowledge conflicts in Multimodal Large Language Models (MLLMs).

Copied to clipboard

Meng Chen, Ruixue Liu, Lei Shen, Shaozu Yuan, Jingyan Zhou, Youzheng Wu, Xiaodong He, Bowen Zhou

Natural Language Interfaces

Challenge:	Existing datasets for human-like dialogue tasks are deficient due to the complexity of human conversations.
Approach:	They construct a large-scale Chinese E-commerce conversation corpus with 1 million dialogues, 20 million utterances, and 150 million words.
Outcome:	The proposed dataset includes 1 million multi-turn dialogues, 20 million utterances, and 150 million words.

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

Copied to clipboard

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

Green & Sustainable NLP

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

Data Selection Curriculum for Abstractive Text Summarization (2023.findings-emnlp)

Copied to clipboard

Shichao Sun, Ruifeng Yuan, Jianfei He, Ziqiang Cao, Wenjie Li, Xiaohua Jia

Summarization

Challenge:	Abstractive Text Summarization (ATS) models are commonly trained using large-scale data that is randomly shuffled.
Approach:	They propose a data selection curriculum scoring system that measures the learning difficulty of an ATS model and expected performance on an instance.
Outcome:	The proposed system surpasses baselines on CNN/DailyMail dataset, utilizing 20% of available instances.

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

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

Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models (2025.findings-emnlp)

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

Haonan He, Yuchen Ren, Yining Tang, Ziyang Xu, Junxian Li, Minghao Yang, Di Zhang, Yuan Dong, Tao Chen, Shufei Zhang, Yuqiang Li, Nanqing Dong, Wanli Ouyang, Dongzhan Zhou, Peng Ye

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

Challenge:	Biology-Instructions is the first large-scale instruction-tuning dataset for multi-omics biological sequences.
Approach:	They propose a large-scale instruction-tuning dataset for multi-omics biological sequences . they propose 'chatMultiOmics' to overcome limitations of current LLMs on multi-ome tasks .
Outcome:	The proposed dataset bridges LLMs and complex biological sequence-related tasks while maintaining conversational fluency.

Copied to clipboard

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

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

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

ZSEE: A Dataset based on Zeolite Synthesis Event Extraction for Automated Synthesis Platform (2024.findings-naacl)

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

Song He, Xin Peng, Yihan Cai, Xin Li, Zhiqing Yuan, WenLi Du, Weimin Yang

Information Extraction & Text Mining

Challenge:	Automated synthesis of zeolite holds great significance for attaining economic and environmental benefits.
Approach:	They propose an event extraction task to mine structural synthesis actions from experimental narratives for modular automated synthesis.
Outcome:	The proposed method can significantly expedite automated synthesis of zeolites owing to its machine readability.

TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games (2025.emnlp-main)

Copied to clipboard

Yuan Yuan, Muyu He, Muhammad Adil Shahid, Ziyang Li, Jiani Huang, Li Zhang

Reasoning

Challenge:	evaluating large language models' reasoning abilities via detective stories is often infeasible due to the large answer space and diverse reasoning types presented by its questions.
Approach:	They propose a framework and dataset for evaluating the deductive reasoning abilities of Large Language Models (LLMs) by leveraging the interactive gameplay of detective games Ace Attorney and Danganronpa.
Outcome:	The proposed framework and dataset are based on the detective games Ace Attorney and Danganronpa and show that they are more efficient than current strategies for enhancing deductive reasoning.

DRAMA: Dynamic Multi-Granularity Graph Estimate Retrieval over Tabular and Textual Question Answering (2024.lrec-main)

Copied to clipboard

Ruize Yuan, Xiang Ao, Li Zeng, Qing He

Structured Data in NLP

Challenge:	TableTextQA tasks require tabular and textual data, gaining increasing attention . however, row-based approaches suffer from limitations such as lack of interaction between rows .
Approach:	They propose a method that incorporates an interaction mechanism among multiple rows . Empirical results demonstrate that the proposed method is effective .
Outcome:	Empirical results show that the proposed model is effective on tabFact and HybridQA datasets.

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

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

Green & Sustainable NLP

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.

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction (2026.findings-acl)

Copied to clipboard

Yulin Chen, Haoran Li, Yuan Sui, Yue Liu, Yufei He, Xiaoling Bai, Chi Fei, Li Yabo, Haozhe Ma, Yangqiu Song, Bryan Hooi

SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs (2026.acl-long)

Challenge:	Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions.
Approach:	They propose a prompt injection defense method that suppresses the model's instruction-following tendencies rather than suppressing them.
Outcome:	The proposed method outperforms prompt-engineering-based approaches and fine-tuning methods and reduces the ASR to nearly 0% in some scenarios.

Copied to clipboard

Sihang Zhao, Kangrui Yu, Youliang Yuan, Pinjia He, Hongyi Wen

Structured Data in NLP

Challenge:	Existing educational LLMs are vulnerable to pedagogical jailbreaks where students use answer-inducing prompts to elicit solutions rather than scaffolded instructions.
Approach:	They propose a graph-augmented tutoring pipeline that infers prerequisite concepts from queries and identifies mastery gaps.
Outcome:	The proposed method improves safety under two pedagogical jailbreak scenarios while maintaining near-ceiling helpfulness under the same evaluation protocol.

HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification (2024.naacl-long)

Copied to clipboard

He Zhu, Junran Wu, Ruomei Liu, Yue Hou, Ze Yuan, Shangzhe Li, Yicheng Pan, Ke Xu

Neural Attention-Aware Hierarchical Topic Model (2021.emnlp-main)

Challenge:	Existing self-supervised methods in natural language processing rely on augmentation rules to generate contrastive samples.
Approach:	They propose a hierarchy-aware information lossless contrastive learning scheme that uses syntactic information reserved in the input sample and fused during the learning process.
Outcome:	The proposed learning scheme is superior to existing methods in hierarchical text classification . the proposed learning system is based on a structure encoder and a text encoder .

Copied to clipboard

Yuan Jin, He Zhao, Ming Liu, Lan Du, Wray Buntine

Schema Generation for Large Knowledge Graphs Using Large Language Models (2025.findings-emnlp)

Challenge:	Neural topic models (NTMs) use deep neural networks to learn topic information.
Approach:	They propose a variational autoencoder model that reconstructs sentence and document word counts using bag-of-words embeddings and pre-trained semantic embedders.
Outcome:	The proposed model lowers reconstruction errors at sentence and document levels and finds more coherent topics from real-world datasets.

Copied to clipboard

Bohui Zhang, Yuan He, Lydia Pintscher, Albert Meroño-Peñuela, Elena Simperl

Principles from Clinical Research for NLP Model Generalization (2024.naacl-long)

Challenge:	Schemas are a vital part of ontology engineering and require substantial knowledge engineers and domain experts to create them.
Approach:	They propose to use large language models to generate schemas in Shape Expressions (ShEx) to bridge the resource gap between knowledge engineers and domain experts.
Outcome:	The proposed pipelines use local and global information from knowledge graphs (KGs) to generate high-quality schemas in Shape Expressions (ShEx).

Copied to clipboard

Aparna Elangovan, Jiayuan He, Yuan Li, Karin Verspoor

Challenge:	In clinical research, generalizability depends on (a) internal validity of experiments and (b) external validity or transportability of the results to the wider population.
Approach:	They propose to ensure internal validity when building machine learning models in NLP by incorporating learning spurious correlations into their models.
Outcome:	The proposed model can perform well on data unseen during training, but drawn from the same distribution or population.

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

Copied to clipboard

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

Can Indirect Prompt Injection Attacks Be Detected and Removed? (2025.acl-long)

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

Yulin Chen, Haoran Li, Yuan Sui, Yufei He, Yue Liu, Yangqiu Song, Bryan Hooi

ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch (2025.emnlp-main)

Challenge:	Recent studies have developed various detection mechanisms to protect against prompt injection attacks.
Approach:	They investigate the feasibility of detecting and removing indirect prompt injection attacks . they use two methods to evaluate their performance and train detection models .
Outcome:	The proposed method is based on a benchmark dataset and is available on github . it evaluates the performance of existing models and open-source detection models .

Copied to clipboard

Jiawei Chen, Xinyan Guan, Qianhao Yuan, Mo Guozhao, Weixiang Zhou, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Xianpei Han

Dialogue Systems & Conversational Agents

Challenge:	Existing instruction data synthesis methods focus on single-turn instructions and neglect cross-turn coherence, resulting in context drift and reduced task completion rates.
Approach:	They propose a framework that constrains multi-turn instruction synthesis by explicitly modeling human conversational intent.
Outcome:	The proposed framework outperforms existing models trained on single-turn and multi-turn instruction datasets.

Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration (2025.acl-long)

Copied to clipboard

Tianyi Bai, Ling Yang, Zhen Hao Wong, Fupeng Sun, Xinlin Zhuang, Jiahui Peng, Chi Zhang, Lijun Wu, Qiu Jiantao, Wentao Zhang, Binhang Yuan, Conghui He

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

Challenge:	Efficient data selection is crucial to accelerate the pretraining of language models . limited research has addressed the inherent conflicts between data selection methods .
Approach:	They propose a multi-actor collaborative data selection mechanism that prioritizes data based on its specific criterion and updates prioritization rules using the current state of the model.
Outcome:	The proposed model accelerates convergence in LM pretraining and achieves an average relative performance gain of 10.5% across multiple language model benchmarks.

Copied to clipboard

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

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

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

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

BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models (2020.findings-emnlp)

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

Bin He, Di Zhou, Jinghui Xiao, Xin Jiang, Qun Liu, Nicholas Jing Yuan, Tong Xu

Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO (2026.acl-long)

Challenge:	Existing knowledge representation learning methods do not use graph contextualized knowledge.
Approach:	They propose to model subgraphs in a medical KG and integrate it with a pre-trained language model to do knowledge generalization.
Outcome:	The proposed model achieves state-of-the-art on several medical NLP tasks . it improves on MedERNIE, and the proposed model is effective .

Copied to clipboard

Jinquan Zheng, Jia Yuan, Jiacheng Yao, Chenyang Gu, Pujun Zheng, Guoxiu He

Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation (2025.findings-emnlp)

Challenge:	Existing inference-time debiasing ignores that the same question should yield consistent answers across permutations.
Approach:	They propose a permutation-aware group-relative policy optimization which enforces permutations-consistent semantic reasoning.
Outcome:	The proposed model outperforms strong baselines across seven benchmarks while maintaining high overall performance.

Copied to clipboard

Jiahao Cheng, Tiancheng Su, Jia Yuan, Guoxiu He, Jiawei Liu, Xinqi Tao, Jingwen Xie, Huaxia Li

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

Challenge:	Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging step-by-step reasoning, but its impact on halluciation detection remains underexplored.
Approach:	They conduct an empirical evaluation of CoT prompting in Large Language Models (LLMs) to examine their impact on hallucination detection methods.
Outcome:	The proposed method significantly affects the internal states and token probability distributions of the LLM.

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

MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models (2026.acl-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

Jie Cao, Tianwei Lin, Bo Yuan, Rolan Yan, Hongyang He, Wenqiao Zhang, Juncheng Li, Dongping Zhang, Siliang Tang, Yueting Zhuang

AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks (2023.findings-acl)

Challenge:	Existing methods for parameter-efficient fine-tuning (PEFT) are limited by computational costs and performance degradation.
Approach:	They propose a method that integrates Low-Rank Adaptation and Mixture-of-Experts (MoE) they propose combining expert load imbalance and representation collapse to improve LLM performance .
Outcome:	The proposed method outperforms homogeneous MoE-LoRA architectures in performance and parameter efficiency.

Copied to clipboard

Xinyi He, Mengyu Zhou, Mingjie Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian Yuan, Dongmei Zhang

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

Challenge:	Tabular data analysis is performed everyday across various domains.
Approach:	They propose to use a dataset of 467k tables with supervision labels for four types of field metadata.
Outcome:	The proposed framework improves the understanding capability of tabular models by incorporating distribution and knowledge information.

Copied to clipboard

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

Evaluating LLMs’ Assessment of Mixed-Context Hallucination Through the Lens of Summarization (2025.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

Siya Qi, Rui Cao, Yulan He, Zheng Yuan

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

Challenge:	Large language models generate coherent text and follow instructions across diverse tasks, but a critical challenge in scaling LLM applications is hallucination, where the generated content lacks factual grounding or deviates from the intended discourse context.
Approach:	They use summarization as a representative task to evaluate LLMs' capability in detecting mixed-context hallucinations, specifically distinguishing between factual and non-factual hallucinos.
Outcome:	The proposed model distinguishes between factual and non-factual hallucinations, and their performance bottlenecks.

Copied to clipboard

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

Information Retrieval

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

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

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

PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models (2023.findings-emnlp)

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

Xingwei He, A-Long Jin, Jun Ma, Yuan Yuan, Siu Yiu

Effects of Human Adversarial and Affable Samples on BERT Generalization (2023.findings-emnlp)

Challenge:	Existing methods for Factual Error Correction (FEC) use mask-then-correct paradigms . however, the lack of datasets containing false claims has impeded progress .
Approach:	They propose a method that enhances few-shot FEC with a pivot task approach using large language models.
Outcome:	The proposed method outperforms its few-shot counterpart by 7.9 points in SARI . it improves widely-adopted SARI metrics by 11.3 compared to the best-performing methods .

Copied to clipboard

Aparna Elangovan, Estrid He, Yuan Li, Karin Verspoor

Robustness in NLP

Challenge:	Limiting quantities of training data is considered a key impediment to achieving generalizability in machine learning.
Approach:	They examine the impact of training data quality, not quantity, on a model’s generalizability by comparing human-adversarial and human-affable training samples.
Outcome:	The proposed model performance improves with 10-30% h-adversarial instances in text classification and relation extraction tasks.

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Yuan Sui, Yufei He, Tri Cao, Sophia Simeng Han, Yulin Chen, Bryan Hooi

Self-Attention Guided Copy Mechanism for Abstractive Summarization (2020.acl-main)

Challenge:	Recent advances on prompting and post-training have enabled LLMs to perform step-wise reasoning tasks, but they tend to explore unproductive solution paths without effective backtracking or strategy adjustment.
Approach:	They propose a framework that empowers LLMs to “think about how to think” and dynamically adapts reasoning strategies in real-time.
Outcome:	The proposed framework outperforms previous SOTA methods by 9-12% in accuracy while reducing inference time by 28-35% under the same compute budget.

Copied to clipboard

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

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

Challenge:	Abstractive summarization models have been widely used to extract words from source into summary, but how to ensure that important words in source are copied remains a challenge.
Approach:	They propose a Transformer-based model to enhance copy mechanism by identifying the importance of each source word based on the degree centrality.
Outcome:	The proposed model outperforms baseline methods on CNN/Daily Mail and Gigaword datasets.

Copied to clipboard

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

Natural Language Interfaces

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.

PAWS: Paraphrase Adversaries from Word Scrambling (N19-1)

Copied to clipboard

Yuan Zhang, Jason Baldridge, Luheng He

A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation (2022.findings-acl)

Challenge:	Existing paraphrase identification datasets lack sentence pairs with high word overlap without being paraphrases.
Approach:	They propose a workflow for generating pairs of sentences with high word overlap . they use controlled word swapping and back translation followed by fluency and paraphrase judgments .
Outcome:	The proposed dataset has 108,463 well-formed paraphrase and non-paraphrase pairs with high lexical overlap.

Copied to clipboard

Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu

Challenge:	Existing methods to measure instance difficulty use generalization and threshold-tuning . a new approach to learn to exit is based on hash functions to assign tokens to a fixed exiting layer.
Approach:	They propose a Hash-based Early Exiting approach that replaces learn-to-exit modules with hash functions to assign each token to a fixed exiting layer.
Outcome:	The proposed approach improves on learning to exit and predicting instance difficulty.

Few-Shot Table Understanding: A Benchmark Dataset and Pre-Training Baseline (2022.coling-1)

Copied to clipboard

Ruixue Liu, Shaozu Yuan, Aijun Dai, Lei Shen, Tiangang Zhu, Meng Chen, Xiaodong He

PRINCE: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-Training (2022.emnlp-main)

Challenge:	Pre-trained language models have demonstrated their effectiveness for few-shot table understanding, but few-shoot table understanding is rarely explored due to the deficiency of public table pre-training corpus and well-defined downstream benchmark tasks.
Approach:	They establish a benchmark dataset and use it to explore few-shot table understanding in Chinese.
Outcome:	The proposed model improves the few-shot table understanding in Chinese.

Copied to clipboard

Song Xu, Haoran Li, Peng Yuan, Youzheng Wu, Xiaodong He

Beyond Self-Report: Bridging the Intention-Behavior Gap in Critical Thinking Assessment via Interpretable Multi-Agent System (2026.acl-long)

Challenge:	Existing studies focus on injecting noises into the input sequence, but feasibility of injecting them into the decoding sequence remains an open question.
Approach:	They propose a pre-training paradigm that integrates knowledge-enhanced decoding with noises in the prefix to strengthen the representation learning of entities that span over multiple input tokens.
Outcome:	The proposed model achieves state-of-the-art results on two knowledge-driven data-to-text generation tasks with up to 2% BLEU gains.

Copied to clipboard

Zekun Li, Jifan Yu, Haoxuan Li, Ye He, Daniel Zhang-Li, Shangqing Tu, Joy Jia Yin Lim, Yikun Jiang, Jiaxin Yuan, Yu Zhang

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

Challenge:	Accurate assessment of critical thinking is limited by the Intention Behavior Gap in psychology . evaluators that measure self-reported competence are limited by multiagent architectures .
Approach:	They propose a framework that operationalizes cognitive assessment into an interpretable multi-agent workflow with Assessment Chain-of-Thought.
Outcome:	The proposed framework aligns better with human expert ratings than gold-standard inventories on large-scale simulations and human participants.

Copied to clipboard

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

ChemAmp: Amplified Chemistry Tools via Composable Agents (2026.findings-acl)

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

Zhucong Li, Powei Chang, Jin Xiao, Zhijian Zhou, Qianyu He, Jiaqing Liang, Fenglei Cao, Xu Yinghui, Yuan Qi

Challenge:	LLM-based agents are powerful tools for automating complex scientific workflows, especially in chemistry, but their single-task performance is limited by tool constraints.
Approach:	They propose a framework that optimizes the collective capabilities of specialized tools by dynamic coordination within individual tasks.
Outcome:	The proposed framework outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration.

The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning (2025.findings-acl)

Copied to clipboard

Bingxiang He, Ning Ding, Cheng Qian, Jia Deng, Ganqu Cui, Lifan Yuan, Haiwen Hong, Huan-ang Gao, Longtao Huang, Hui Xue, Huimin Chen, Zhiyuan Liu, Maosong Sun

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

Challenge:	Existing work on instruction tuning has focused on task level, without considering that tasks are artificially defined and, to LLMs, merely consist of tokens and representations.
Approach:	They propose a training data arrangement framework that allows for continual learning and loss reduction.
Outcome:	The proposed framework promotes continual learning and loss reduction on unseen tasks.

Copied to clipboard

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

Reasoning

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%.

English-to-Chinese Transliteration with Phonetic Auxiliary Task (2020.aacl-main)

Copied to clipboard

Yuan He, Shay B. Cohen

Syntactic Text Processing

Challenge:	Several NMT techniques have been used to enhance machine transliteration models, but few focus on the linguistic features specific to the relevant languages.
Approach:	They propose a phonetic auxiliary task that integrates phonetic features into a model to improve generalization performance of the main transliteration task.
Outcome:	The proposed model achieves similar performance to the current state of the art with a much smaller size.

MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension (2024.findings-emnlp)

Copied to clipboard

Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, Yu Li

Question Answering

Challenge:	Existing models generate erroneous information and evaluations fail to assess factual correctness of models.
Approach:	They propose to use MoleculeQA to evaluate molecular factual correctness in large language models by organizing molecules into a taxonomy and building QA pairs through human and LLM efforts.
Outcome:	The proposed model improves the factual correctness of generated information and enables the development of new models.

Metaphor Reasoning is Meta-reasoning (2026.acl-long)

Copied to clipboard

Qianyu He, Junting Lu, Yikai Zhang, Siyu Yuan, Xiaojun Meng, Jiansheng Wei, Jiaqing Liang, Yanghua Xiao

Reasoning

Challenge:	Existing work on metaphor reasoning's impact on reasoning abilities is limited.
Approach:	They propose a system for synthesizing metaphorical riddles that satisfy five quality dimensions: diverse, balanced, reasoning-oriented, challenging, and verifiable.
Outcome:	The proposed system improves reasoning abilities across six domains using only thousands of metaphorical riddles.

Batch IS NOT Heavy: Learning Word Representations From All Samples (P18-1)

Copied to clipboard

Xin Xin, Fajie Yuan, Xiangnan He, Joemon M. Jose

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing (2024.emnlp-main)

Challenge:	Stochastic Gradient Descent with negative sampling is the most prevalent approach to learn word representations.
Approach:	They propose a method that uses batch gradient learning to generate word representations from all training samples.
Outcome:	The proposed method outperforms sampling-based methods on several benchmark tasks.

Copied to clipboard

Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, Dongmei Zhang

Programming Languages in NLP

Challenge:	Existing methods to improve code generation from natural language descriptions are difficult due to complex structure, subtle bugs, and lack of supplementary contents.
Approach:	They propose a framework that enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement.
Outcome:	The proposed framework improves the quality of complex code generation on the DS-1000 and ClassEval datasets.

TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models (2025.acl-long)

Copied to clipboard

Xinyi He, Yihao Liu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, Zejian Yuan, Dongmei Zhang

On the Faithfulness for E-commerce Product Summarization (2020.coling-main)

Challenge:	Tabular data are crucial in many fields and their understanding by large language models (LLMs) under high parameter efficiency paradigm is important.
Approach:	They propose a module that uses 2D LoRA to encode low-rank information on cell positions to improve table serialization and representation of two-dimensional structured information within a one-dimensional sequence.
Outcome:	Experiments on four tabular-related datasets show that TableLoRA outperforms vanilla LoRA and surpasses table encoding methods tested in control.

Copied to clipboard

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

KMatrix-2: A Comprehensive Heterogeneous Knowledge Collaborative Enhancement Toolkit for Large Language Model (2025.emnlp-demos)

Challenge:	e-commerce product summarization requires consistency between product attributes and summary . inconsistent product summaries can mislead users and decrease public credibility .
Approach:	They propose a model to generate e-commerce product summaries with product attributes . they encode product attribute table and constrain attribute words to be presented only through copying .
Outcome:	The proposed model significantly improves the faithfulness of e-commerce product summarization tasks.

Copied to clipboard

Shun Wu, Di Wu, Wangtao Sun, Ziyang Huang, Xiaowei Yuan, Kun Luo, XueYou Zhang, Shizhu He, Jun Zhao, Kang Liu

Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering (2025.acl-long)

Challenge:	Existing studies on K-LLMs systems focus on declarative knowledge and procedural knowledge (rules) .
Approach:	They propose to build a toolkit that supports comprehensive heterogeneous knowledge collaborative enhancement for Large Language Models (LLMs).
Outcome:	The proposed toolkit provides unified knowledge integration and joint knowledge retrieval methods to achieve more comprehensive heterogeneous knowledge collaborative enhancement.

Copied to clipboard

Yuan Sui, Yufei He, Zifeng Ding, Bryan Hooi

Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT (2023.emnlp-main)

Challenge:	Existing benchmarks for integrating Knowledge Graphs with Large Language Models focus on closed-ended tasks, leaving a gap in evaluating performance on more complex, real-world scenarios.
Approach:	They propose a benchmark to evaluate LLMs augmented with KGs in open-ended, real-world question answering settings.
Outcome:	The proposed benchmark reflects practical complexities through diverse question types and incorporates metrics to quantify both hallucination rates and reasoning improvements in LLM+KG models.

Copied to clipboard

Biru Zhu, Lifan Yuan, Ganqu Cui, Yangyi Chen, Chong Fu, Bingxiang He, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu

Language Model Analysis for Ontology Subsumption Inference (2023.findings-acl)

Challenge:	Large language models (LLMs) are capable of performing tasks but are likely to be misused.
Approach:	They propose a zero-shot black-box method to detect LLM-generated texts . they revise the text to be detected using the ChatGPT model .
Outcome:	The proposed method can detect LLM-generated texts with a zero-shot black-box model . it is based on intuition that the model will make fewer revisions to LLMs than to human-written texts .

Copied to clipboard

Yuan He, Jiaoyan Chen, Ernesto Jimenez-Ruiz, Hang Dong, Ian Horrocks

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

Challenge:	Existing studies focus on simple, triple-based, relational KBs but omit more sophisticated, logic-based conceptualised KB.
Approach:	They propose to use ontology subsumption axioms to probe LMs' knowledge of ontologies by probing datasets from atomic and complex concepts.
Outcome:	The proposed methods encode less background knowledge of Subsumption Inference (SI) than traditional Natural Language Inference but can improve on SI significantly when a small number of samples are given.

Copied to clipboard

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

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

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

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.

Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs (2024.findings-emnlp)

Copied to clipboard

Sihang Zhao, Youliang Yuan, Xiaoying Tang, Pinjia He

pFedRAG: A Personalized Federated Retrieval-Augmented Generation System with Depth-Adaptive Tiered Embedding Tuning (2025.findings-emnlp)

Challenge:	Existing research indicates that even state-of-the-art MLLMs still suffer from some straightforward visual question-answering (VQA) problems.
Approach:	They propose to use a model-based benchmark to investigate model laziness to identify models that err when answering simple visual questions about an image.
Outcome:	The proposed model laziness is found to be widespread in current MLLMs, including GPT-4o, Gemini-1.5-pro, Claude 3, LLaVA-1.5, LLva-1.6, and QWen-VL.

Copied to clipboard

Hangyu He, Xin Yuan, Kai Wu, Ren Ping Liu, Wei Ni

TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning (2024.findings-emnlp)

Challenge:	Personalized Federated RAG framework enables efficient collaborative fine-tuning of embedding models . depth-adaptive tieered Embedding (DATE) architecture is tailored for local data and training results of each client.
Approach:	a new Personalized Federated RAG framework is proposed for large language models . the framework enables efficient collaborative fine-tuning of embedding models based on common knowledge .
Outcome:	a novel Personalized Federated RAG framework is proposed for large language models . the framework enables efficient collaborative fine-tuning of embedding models based on common knowledge .

Copied to clipboard

Yuan Sui, Jiaru Zou, Mengyu Zhou, Xinyi He, Lun Du, Shi Han, Dongmei Zhang

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

Challenge:	Existing solutions for table reasoning tasks are mainly tested on small tables and face scalability issues and struggle with complex queries due to incomplete or dispersed data across different table sections.
Approach:	They propose a table reasoning pre-processor suite that can be used to leverage large language models (LLMs) in table-based tasks.
Outcome:	The proposed method improves LLMs’ reasoning capabilities in various tabular tasks and enhances interaction between LLM and tabular data by employing effective pre-processing.

Copied to clipboard

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

PaSa: An LLM Agent for Comprehensive Academic Paper Search (2025.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

Yichen He, Guanhua Huang, Peiyuan Feng, Yuan Lin, Yuchen Zhang, Hang Li, Weinan E

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

Challenge:	We introduce PaSa, an advanced Paper Search agent powered by large language models . despite being trained on synthetic data, PaSA outperforms existing baselines on RealScholarQuery .
Approach:	They introduce PaSa, an advanced Paper Search agent powered by large language models . they optimize PaSA using a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained queries .
Outcome:	The paper analyzes the performance of a paper search agent using a synthetic dataset . it significantly outperforms existing benchmarks on RealScholarQuery .

Copied to clipboard

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

Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models (2025.findings-acl)

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

Shuqi Liu, Han Wu, Bowei He, Xiongwei Han, Mingxuan Yuan, Linqi Song

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

Challenge:	Existing task vector-based model merging methods apply uniform coefficients across all parameters, overlooking varying parameter importance both within and across tasks.
Approach:	They propose a sensitivity-guided coefficient adjustment method that optimizes existing model merging techniques by operating at both task-specific and cross-task levels.
Outcome:	The proposed method outperforms existing model merging techniques on mistral 7B and LLaMA2 7B/13B models and enables them to outperformed specialized models.

Copied to clipboard

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

Mapping Natural Language Instructions to Mobile UI Action Sequences (2020.acl-main)

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

Yang Li, Jiacong He, Xin Zhou, Yuan Zhang, Jason Baldridge

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

Challenge:	a new problem of grounding natural language instructions to mobile UI actions is emerging . we use a Transformer to extract action phrase tuples from long-range natural language instruction .
Approach:	They propose a dataset that pairs English instructions with actions performed by people on a mobile UI emulator.
Outcome:	The proposed model achieves 70.59% accuracy on predicting complete ground-truth action sequences in PixelHelp.

Copied to clipboard

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

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

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

PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes (2024.findings-emnlp)

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

He Cao, Yanjun Shao, Zhiyuan Liu, Zijing Liu, Xiangru Tang, Yuan Yao, Yu Li

Efficient Test-Time Scaling via Temporal Reasoning Aggregation (2026.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific domains.
Approach:	They propose a framework that bridges the molecule-text modality gap by integrating a comprehensive benchmark of pretraining strategies and dataset configurations.
Outcome:	The proposed framework improves multimodal LLMs through cross-modal alignment and multi-graph understanding.

Copied to clipboard

Jiakun Li, Xingwei He, Kefan Li, Hongzheng Chai, Hongyue Yu, Yuan Yuan

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

Challenge:	Existing dynamic early-exit methods rely on single-step confidence signals . existing approaches are unreliable for detecting reasoning convergence in multi-step settings .
Approach:	They propose a training-free framework for efficient test-time scaling that determines when to terminate reasoning based on temporal aggregation of multi-step evidence rather than instantaneous signals.
Outcome:	Experiments show that TRACE reduces reasoning token usage by 25% on average while maintaining accuracy within 1–2% of full-length reasoning.

Copied to clipboard

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

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)

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

Xu Huang, Wenhao Zhu, Hanxu Hu, Conghui He, Lei Li, Shujian Huang, Fei Yuan

Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings (2025.findings-acl)

Challenge:	Existing multilingual benchmarks focus primarily on language understanding tasks.
Approach:	They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages.
Outcome:	Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve.

Copied to clipboard

Yuqicheng Zhu, Daniel Hernández, Yuan He, Zifeng Ding, Bo Xiong, Evgeny Kharlamov, Steffen Staab

Few-shot Intent Classification and Slot Filling with Retrieved Examples (2021.naacl-main)

Challenge:	Existing methods provide probabilistic guarantees over a reference set of queries and answers, but they fail to identify when the answers to a query are uncertain.
Approach:	They propose a method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets.
Outcome:	The proposed method provides predicate-conditional coverage guarantees while maintaining compact prediction sets.

Copied to clipboard

Dian Yu, Luheng He, Yuan Zhang, Xinya Du, Panupong Pasupat, Qi Li

Information Retrieval

Challenge:	Existing methods for few-shot learning are based on labeled examples, but they are non-trivial . few-sshot learning is challenging due to the imbalance in the amount of data between the source and target domains.
Approach:	They propose retrieval-based methods for intent classification and slot filling tasks . they use a batch-softmax objective to learn similar contextualized representations for spans .
Outcome:	The proposed method outperforms previous systems on the CLINC and SNIPS benchmarks.

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

Copied to clipboard

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

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

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

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

Structured Data in NLP

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.

QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining (2021.acl-short)

Copied to clipboard

Xinya Du, Luheng He, Qi Li, Dian Yu, Panupong Pasupat, Yuan Zhang

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

Challenge:	Existing methods to predict slots and their values do not encode enough semantic information, limiting the models’ zero-shot capability.
Approach:	They propose a QA-driven slot filling model which extracts slot-filler spans from utterances with a span-based QA model.
Outcome:	The proposed model outperforms baselines by over 5% on the SNIPS benchmark.

Copied to clipboard

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

LogToP: Logic Tree-of-Program with Table Instruction-tuned LLMs for Controlled Logical Table-to-Text Generation (2026.findings-eacl)

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

Yupian Lin, Guangya Yu, Cheng Yuan, Huan Du, Hui Luo, Yuang Bian, Jingping Liu, Zhidong He, Wen Du, Tong Ruan

General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation (2023.findings-acl)

Challenge:	Existing LLMs are difficult to achieve satisfactory results in table-related tasks.
Approach:	They propose to develop a specialized logical table-to-text generation model that can be used for table-related tasks.
Outcome:	The proposed model achieves state-of-the-art on a Logic2Text dataset.

Copied to clipboard

Rui Meng, Tong Wang, Xingdi Yuan, Yingbo Zhou, Daqing He

InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery (2025.coling-main)

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

He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, Yu Li