Papers by Jun He

MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming (2025.acl-long)

Challenge:	Existing methods for numerical reasoning are not flexible enough to handle diverse expressions.
Approach:	They propose a Relational Graph enhanced Hybrid table-text Numerical reasoning model with Tree decoder which captures relationship between numerical value, table schema, and text information on the encoder side.
Outcome:	The proposed model outperforms the baseline model and achieves state-of-the-art results on the publicly available tabletext hybrid QA benchmark.

Copied to clipboard

Weiyang Guo, Jing Li, Wenya Wang, Yu Li, Daojing He, Jun Yu, Min Zhang

Robustness in NLP

Challenge:	Existing jailbreak techniques rely on single-round interactions, pro-Corresponding author.
Approach:	They propose a multi-turn safety alignment framework to address the challenge of securing large language models in multi-round interactions.
Outcome:	The proposed framework exhibits state-of-the-art attack capabilities while improving safety performance on safety benchmarks.

Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism (P18-1)

Copied to clipboard

Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, Jun Zhao

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

Challenge:	Existing methods focus on normal class and fail to extract relational triplets precisely.
Approach:	They propose an end-to-end model which can jointly extract relational triplets from sentences . they employ two different strategies in decoding process: employing only one united decoder or applying multiple separated decodeurs.
Outcome:	The proposed model outperforms the baseline method significantly in two datasets.

Copied to clipboard

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

DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models (2024.findings-acl)

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

Copied to clipboard

Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang

LEGO: A Multi-agent Collaborative Framework with Role-playing and Iterative Feedback for Causality Explanation Generation (2023.findings-emnlp)

Challenge:	Large language models (LLMs) have shown impressive results, but still suffer from hallucination, i.e., the generation of false information.
Approach:	They propose a task of sequential model editing that aims to rectify mistakes continuously.
Outcome:	The proposed method significantly outperforms baselines in single-turn and sequential editing.

Copied to clipboard

Zhitao He, Pengfei Cao, Yubo Chen, Kang Liu, Ruopeng Li, Mengshu Sun, Jun Zhao

Explainability & Interpretability in NLP

Challenge:	Causality explanation generation is a generative task that aims to explain why a given cause-effect pair is true using natural language.
Approach:	They propose a multi-agent framework with role-playing and iterative feedback for causality explanation generation.
Outcome:	The proposed framework is superior to existing frameworks on WIKIWHY and e-CARE datasets.

Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering (2024.emnlp-main)

Copied to clipboard

Yao Xu, Shizhu He, Jiabei Chen, Zihao Wang, Yangqiu Song, Hanghang Tong, Guang Liu, Jun Zhao, Kang Liu

Structured Data in NLP

Challenge:	Existing methods to integrate LLMs with Knowledge Graphs (KGs) however, these methods are often incomplete to cover all the knowledge required to answer questions.
Approach:	They propose to integrate LLMs with Knowledge Graphs (KGs) to address insufficient knowledge and hallucination issues in Large Language Models.
Outcome:	The proposed method outperforms existing methods on two datasets.

Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning (2026.eacl-long)

Copied to clipboard

Qifan Yu, Zhenyu He, Sijie Li, Zhou Xun, Jun Zhang, Jingjing Xu, Di He

LlmLink: Dual LLMs for Dynamic Entity Linking on Long Narratives with Collaborative Memorisation and Prompt Optimisation (2025.coling-main)

Challenge:	Chain-of-Thought prompting is a powerful technique for enhancing language model’s reasoning capabilities, but generating long and correct CoT trajectories is challenging.
Approach:	They propose to align the steps of Chain-of-Thought reasoning with loop iterations and apply intermediate supervision during the training of Looped Transformers.
Outcome:	The proposed method generates accurate reasoning chains for complex problems exceeding training length, and improves performance of the auto-regressive model.

Copied to clipboard

Lixing Zhu, Jun Wang, Yulan He

Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphs (2023.findings-emnlp)

Challenge:	Existing methods focus on supervised fine-tuning or limited to one-off prediction, which poses a challenge where the context is long.
Approach:	They propose a dynamic approach to CoREFerence resolution in chunked long narratives by deploying dual Large Language Models.
Outcome:	The proposed model achieves performance gains over existing models and fine-tuning approaches on long narrative datasets, significantly reducing the resources required for inference and training.

Copied to clipboard

Yao Xu, Shizhu He, Cunguang Wang, Li Cai, Kang Liu, Jun Zhao

Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training (2022.emnlp-industry)

Challenge:	Complex Query Answering (CQA) is a challenge task of Knowledge Graphs due to incompleteness of KGs.
Approach:	They propose a query embedding approach that decouples the training for simple and complex queries.
Outcome:	The proposed approach decouples training for simple and complex queries and achieves state-of-the-art performance over three public benchmarks.

Copied to clipboard

Taolin Zhang, Junwei Dong, Jianing Wang, Chengyu Wang, Ang Wang, Yinghui Liu, Jun Huang, Yong Li, Xiaofeng He

Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources (2021.findings-acl)

Challenge:	Existing knowledge-enhanced pre-trained language models (KEPLMs) can capture internal knowledge, but can't understand external background knowledge.
Approach:	They propose to use Chinese knowledge-enhanced pre-trained language models to improve context-aware representations via learning from structured relations in knowledge bases.
Outcome:	Experiments show that Chinese knowledge-enhanced pre-trained language models outperform strong baselines over various benchmark NLP tasks and in different model sizes.

Copied to clipboard

Taolin Zhang, Chengyu Wang, Minghui Qiu, Bite Yang, Zerui Cai, Xiaofeng He, Jun Huang

MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment (2025.acl-long)

Challenge:	MRC is a popular task in NLP, aiming to understand a passage and answer the relevant questions.
Approach:	They propose a multi-target machine learning task for the medical domain that predicts answers to medical questions and corresponding support sentences from medical information sources simultaneously.
Outcome:	The proposed model outperforms baselines by fusing context-aware and knowledge-awful token representations.

Copied to clipboard

Weicong Qin, Yi Xu, Weijie Yu, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu

Information Retrieval

Challenge:	Existing personalized product search methods assume that users’ query fully captures their real motivation, but in practice, user's queries do not always articulate the requirements.
Approach:	They propose a Motivation-Aware Personalized Search method that embeds queries and consultations into a unified semantic space via LLMs and utilizes a Mixture of Attention Experts (MoAE) to prioritize critical semantics.
Outcome:	Extensive experiments on real and synthetic data show that the proposed method outperforms existing methods in retrieval and ranking tasks.

Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation (2023.emnlp-main)

Copied to clipboard

Xuanli He, Qiongkai Xu, Jun Wang, Benjamin Rubinstein, Trevor Cohn

Robustness in NLP

Challenge:	Modern NLP models are often trained over large untrustworthy datasets, raising the potential for a malicious adversary to compromise model behaviour.
Approach:	They propose to mitigate spurious correlations between textual triggers and classification labels by combining them with insertion-based attacks.
Outcome:	The proposed defence significantly reduces attack success rates across backdoor attacks and provides a near-perfect defence against insertion-based attacks.

ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis (2025.findings-naacl)

Copied to clipboard

Zeao Tu, Xiangdi Meng, Yu He, Zihan Yao, Tianyu Qi, Jun Liu, Ming Li

Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs (2026.acl-long)

Challenge:	Existing methods for enhancing large language models lack clear metrics for evaluating data characteristics.
Approach:	They propose a method that integrates models, data, and tasks to refine datasets.
Outcome:	The proposed method achieves comparable results to full-scale fine-tuning using only half the data in mathematical tasks and exhibits strong generalization across different models and domains.

Copied to clipboard

Jinhui Chen, Shizhu He, Xingchang Yang, Huanxuan Liao, Yequan Wang, Xiangwen Liao, Wenhao Teng, Kang Liu, Jun Zhao

ExpNote: Black-box Large Language Models are better Task Solvers with Experience Notebook (2023.findings-emnlp)

Challenge:	Existing continual learning paradigms prioritize instant performance through dense updates, leading to catastrophic forgetting and rapid exhaustion of model capacity.
Approach:	They propose a method that preserves previously acquired knowledge and acquires new task-specific skills while preserving sufficient parameter capacity for subsequent adaptation.
Outcome:	The proposed method is based on the brain's functional partitioning and can be used to map tasks between specialized and generalist neurons.

Copied to clipboard

Wangtao Sun, Xuanqing Yu, Shizhu He, Jun Zhao, Kang Liu

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have shown great power in solving various tasks but fail in many specific tasks.
Approach:	They propose a framework to help black-box LLMs better adapt to unfamiliar tasks by reflecting and noting experiences from training data and retrieving them from external memory during testing.
Outcome:	The proposed framework improves the performance of black-box Large Language Models on multiple tasks and demonstrates that it is a good choice for the future.

Copied to clipboard

Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan

Challenge:	Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction.
Approach:	They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process.
Outcome:	The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process .

Let’s Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models (2024.lrec-main)

Copied to clipboard

Shunyu Liu, Jie Zhou, Qunxi Zhu, Qin Chen, Qingchun Bai, Jun Xiao, Liang He

Sentiment Analysis

Challenge:	Empirical evaluations conducted on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.
Approach:	They propose a diffusion model which extracts aspects step by step and learns a denoising process that progressively restores them in a reverse manner.
Outcome:	Empirical evaluations on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.

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

TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models (2024.lrec-main)

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

Junbing Yan, Chengyu Wang, Taolin Zhang, Xiaofeng He, Jun Huang, Wei Zhang, Longtao Huang, Hui Xue

Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation (2025.findings-emnlp)

Challenge:	Existing methods for incorporating external knowledge into language models do not prioritize learning embeddings for entity-related tokens.
Approach:	They propose a framework for incorporating external knowledge into pre-training models that utilize entity-related tokens.
Outcome:	The proposed framework reduces pre-training time by 50% and outperforms other KEPLMs in knowledge probing tasks and multiple knowledge-aware language understanding tasks.

Copied to clipboard

Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu, Jun Song, Bo Zheng, Yancheng He, Shilong Li

End-to-End Conversational Search for Online Shopping with Utterance Transfer (2021.emnlp-main)

Challenge:	Existing methods for predicting hallucinations suffer from two drawbacks: Lack of scalable token-level rewards and Neglect of visual-anchored tokens.
Approach:	They propose a Token Preference Optimization model with self-calibrated rewards . they propose based on visual-anchored tokens and visual-aware training objective .
Outcome:	The proposed model improves hallucination performance by focusing on visual-anchored tokens without fine-grained annotations.

Copied to clipboard

Liqiang Xiao, Jun Ma, Xin Luna Dong, Pascual Martínez-Gómez, Nasser Zalmout, Chenwei Zhang, Tong Zhao, Hao He, Yaohui Jin

Natural Language Interfaces

Challenge:	a new study proposes a conversational search system that integrates product attributes and dialog with search . but it faces two real world challenges: imperfect product schema/knowledge and lack of training dialog data .
Approach:	They propose an end-to-end conversational search system that integrates search with text . they propose an utterance transfer approach that generates dialogue utterations from other domains .
Outcome:	The proposed system outperforms the best tested baseline in a conversational search dataset for online shopping.

S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Model (2024.naacl-long)

Copied to clipboard

Fangyu Lei, Qian Liu, Yiming Huang, Shizhu He, Jun Zhao, Kang Liu

Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining (2020.emnlp-main)

Challenge:	Existing benchmarks fail to evaluate extremely long-context LLMs or analyze their limitations.
Approach:	They propose a Synthetic, Scalable, Systematic evaluation suite for LLMs using SQL execution.
Outcome:	The proposed evaluation suite is able to scale text length and difficulty across scenarios and provides strong correlations with real-world benchmarks.

Copied to clipboard

Chengyu Wang, Minghui Qiu, Jun Huang, Xiaofeng He

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

Challenge:	Pre-trained neural language models improve learning for various NLP tasks by fine-tuning them on task-specific training sets.
Approach:	They propose a meta-learning procedure to fine-tune neural language models on task-specific training sets.
Outcome:	The proposed procedure solves a group of similar NLP tasks on a text mining dataset.

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

Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model (2023.eacl-main)

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

Fei Xia, Yixuan Weng, Shizhu He, Kang Liu, Jun Zhao

LLaSA: Large Language and Structured Data Assistant (2025.naacl-long)

Challenge:	Existing taxonomies focus on adding concepts to the leaf nodes of the existing tree, which does not fully utilize the taxonomy’s knowledge and is unable to update the original taxomy structure.
Approach:	They propose a two-stage method called ATTEMPT for taxonomy completion that inserts new concepts into the correct position by finding a parent node and labeling child nodes.
Outcome:	The proposed method performs best on taxonomy completion and extension tasks, surpassing existing methods.

Copied to clipboard

Yao Xu, Shizhu He, Jiabei Chen, ZengXiangrong ZengXiangrong, Bingning Wang, Guang Liu, Jun Zhao, Kang Liu

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Structured knowledge grounding (SKG) tasks are a key part of many NLP applications.
Approach:	They propose a framework for enhancing LLMs' ability to handle structured data . they represent various types of structured data in a unified hypergraph format .
Outcome:	The proposed framework outperforms existing methods on SKG tasks using LoRA finetuning.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models (2025.acl-long)

Copied to clipboard

Yuqiao Tan, Shizhu He, Kang Liu, Jun Zhao

LongHeads: Multi-Head Attention is Secretly a Long Context Processor (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) have a transparent brain with accessible parameters that encode extensive knowledge, which can be analyzed, located and transferred.
Approach:	They propose a new paradigm that aligns parametric spaces of LLMs using several training steps without following training.
Outcome:	The proposed model aligns parametric spaces across scales using only training steps without following training.

Copied to clipboard

Yi Lu, Xin Zhou, Wei He, Jun Zhao, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Green & Sustainable NLP

Challenge:	Large language models struggle to process lengthy inputs due to limited length generalization and attention’s quadratic computational demands.
Approach:	They propose a training-free framework that allows each head to attend to important context chunks instead of allowing each head a full sentence .
Outcome:	The proposed framework unlocks multi-head attention's untapped potential by allowing each head to attend to important context chunks instead of the full sentence.

POP: Prefill-Only Pruning for Efficient Large Model Inference (2026.findings-acl)

Copied to clipboard

Junhui He, Zhihui Fu, Jun Wang, Qingan Li

Green & Sustainable NLP

Challenge:	Existing structured pruning methods suffer from significant accuracy degradation . Existing pruning methods are expensive and require specialized hardware and kernels to perform .
Approach:	They propose a stage-agnostic pruning approach that overlooks asymmetric roles between prefill and decode stages.
Outcome:	The proposed pruning approach achieves 1.37 speedup in prefill latency with minimal performance loss.

Pattern-revising Enhanced Simple Question Answering over Knowledge Bases (C18-1)

Copied to clipboard

Yanchao Hao, Hao Liu, Shizhu He, Kang Liu, Jun Zhao

Knowledge Representation

Challenge:	Simple question answering over knowledge bases is one of the most important natural language processing tasks.
Approach:	They propose to conduct pattern extraction and entity linking first and put forward pattern revising procedure to mitigate the error propagation problem.
Outcome:	The proposed method outperforms the current state-of-the-art in this task by an absolute large margin.

LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration (2024.emnlp-main)

Copied to clipboard

Jun Zhao, Can Zu, Xu Hao, Yi Lu, Wei He, Yiwen Ding, Tao Gui, Qi Zhang, Xuanjing Huang

Question Answering

Challenge:	Large language models (LLMs) have been successful in understanding language and processing text, but their cost prohibits their practical applications.
Approach:	They propose a multi-agent collaboration method that breaks down lengthy documents into smaller, more manageable chunks and organizes the member agents to read their assigned chunks.
Outcome:	The proposed method achieves 16.42% and 1.63% accuracy gains over existing models on single-hop and multi-hop QA settings.

Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering (2025.coling-main)

Copied to clipboard

Huanxuan Liao, Shizhu He, Yao Xu, Yuanzhe Zhang, Shengping Liu, Kang Liu, Jun Zhao

An MRC Framework for Semantic Role Labeling (2022.coling-1)

Challenge:	Recent studies indicate that Large Language Models model rich knowledge, but it is often not activated and awakened.
Approach:	They propose a framework that leverages richer context to enhance question answering . Explicit awakening fine-tunes a context generator to create a synthetic, compressed document that functions as symbolic context.
Outcome:	The proposed framework mimics the human ability to answer questions using only thinking and recalling to compensate for knowledge gaps.

Copied to clipboard

Nan Wang, Jiwei Li, Yuxian Meng, Xiaofei Sun, Han Qiu, Ziyao Wang, Guoyin Wang, Jun He

Semantic Parsing

Challenge:	Existing work on semantic role labels ignores the semantic connection between the two tasks . et al. (2010) defined two types of semantic roles: core roles and non-core roles.
Approach:	They propose to use machine reading comprehension to bridge the gap between these two tasks . they formalize predicate disambiguation as multiple-choice machine reading understanding .
Outcome:	The proposed framework achieves state-of-the-art or comparable results to previous work . it uses the descriptions of candidate senses of a given predicate as options to select the correct sense .

Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing (2022.acl-short)

Copied to clipboard

Runxin Sun, Shizhu He, Chong Zhu, Yaohan He, Jinlong Li, Jun Zhao, Kang Liu

Programming Languages in NLP

Challenge:	Text-to-SQL parsing aims to parse natural language questions into SQL queries . current attention-based approaches can only model alignments at the token level .
Approach:	They propose a method to leverage explicit lexico-logical alignments by identifying possible phrase-level alignments and injecting them as additional contexts into the parsing procedure.
Outcome:	The proposed approach improves performance by 3.4% on Squall.

Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning (2025.acl-long)

Copied to clipboard

Fangzhi Xu, Hang Yan, Chang Ma, Haiteng Zhao, Qiushi Sun, Kanzhi Cheng, Junxian He, Jun Liu, Zhiyong Wu

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

Challenge:	Existing methods for enhancing LLM reasoning rely on supervisory signals . current methods rely heavily on outcome supervision and auxiliary reward models .
Approach:	They propose a gen-eralizable and purely unsupervised self-training framework to enhance LLM reasoning without supervision.
Outcome:	The proposed framework improves LLM reasoning without supervision without external supervision.

Copied to clipboard

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

Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models (2025.findings-acl)

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

Liyang He, Chenglong Liu, Rui Li, Zhenya Huang, Shulan Ruan, Jun Zhou, Enhong Chen

How Susceptible are Large Language Models to Ideological Manipulation? (2024.emnlp-main)

Challenge:	Sentence embedding is essential for many NLP tasks, but reliance on manual labels limits scalability.
Approach:	They propose a method for controlling the generation direction of large language models in the latent space by integrating ranking information and semantic information.
Outcome:	The proposed method achieves new SOTA performance with a modest cost in ranking sentence synthesis.

Copied to clipboard

Kai Chen, Zihao He, Jun Yan, Taiwei Shi, Kristina Lerman

An Adaptive Prompt Generation Framework for Task-oriented Dialogue System (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) have the potential to exert substantial influence on public perceptions and interactions with information.
Approach:	They examine how LLMs can learn and generalize ideological biases from their instruction-tuning data.
Outcome:	The LLMs show a startling ability to absorb ideology from one topic and generalize it to even unrelated ones.

Copied to clipboard

Jun Gao, Liuyu Xiang, Huijia Wu, Han Zhao, Yiqi Tong, Zhaofeng He

BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation (2024.lrec-main)

Challenge:	Existing black-box large language models (LLMs) have excellent performance in task-oriented dialogue (TOD) tasks, but obtaining suitable prompts for specific tasks is challenging.
Approach:	They propose a black-box large language model that generates domain and slot information in the belief state, which serves as prior knowledge for subsequent prompt generation.
Outcome:	The proposed framework outperforms existing prompting methods on the MultiWOZ 2.0 dataset.

Copied to clipboard

Yuhong He, Yongqi Zhang, Shizhu He, Jun Wan

Low-Resource NLP

Challenge:	Medical dialogue generation (MDG) has gained increasing attention due to its substantial practical value.
Approach:	They propose a method which explicitly models MDG’s multi-step reasoning process and iteratively enhances this reasoning process.
Outcome:	The proposed method outperforms state-of-the-art methods across objective and subjective evaluations on two publicly available datasets.

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels (2025.findings-acl)

Copied to clipboard

Lingxiao Wei, He Yan, Lu Xiangju, Junmin Zhu, Jun Wang, Wei Zhang

Information Extraction & Text Mining

Challenge:	Currently, long-context summarization mainly relies on memory ability.
Approach:	They propose a multi-scale long-context summarization benchmark based on Chinese novels . they use human-driven annotations to analyze long-constituency models .
Outcome:	The proposed benchmark features human-driven annotations across four subsets with lengths ranging from 16k to 128k.

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR (2026.acl-long)

Copied to clipboard

Jiaying Zhang, Lei Shi, Jiguo Li, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He

MedConQA: Medical Conversational Question Answering System based on Knowledge Graphs (2022.emnlp-demos)

Challenge:	Existing parameter-efficient methods for RLVR face limitations . low-rank adaptation methods do not account for the distinct optimization dynamics .
Approach:	They propose a low-rank adaptation method tailored for RLVR that exploits the anisotropic structure of RL update subspace and extracts its principal directions via Singular Value Decomposition (SVD).
Outcome:	Experiments on large reasoning models show that GeoRA outperforms strong low-rank baselines across RLVR settings while showing stronger generalization and less forgetting on out-of-domain tasks.

Copied to clipboard

Fei Xia, Bin Li, Yixuan Weng, Shizhu He, Kang Liu, Bin Sun, Shutao Li, Jun Zhao

Natural Language Interfaces

Challenge:	Existing medical dialogue systems have the problems of weak scalability, insufficient knowledge, and poor controllability.
Approach:	They propose a medical conversational question-answering system based on the knowledge graph to improve scalability and controllability.
Outcome:	The proposed system can conduct knowledge-grounded dialogues with users, using a Chinese medical knowledge graph and a large-scale dataset.

Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management (2026.acl-long)

Copied to clipboard

Weitao Ma, Xiaocheng Feng, Lei Huang, Xiachong Feng, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Bing Qin

From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models (2023.findings-emnlp)

Challenge:	Existing approaches to memory management rely on final task performance as the primary reward, resulting in severe reward sparsity and ineffective credit assignment.
Approach:	They propose a framework for fine-grained feedback alignment using a Chunk-level step reward and Evidence-Anchored Reward Attribution to redistribute global rewards based on memory items utilized as evidence in reasoning.
Outcome:	The proposed framework outperforms baselines and supports generalization across different model configurations and backbones.

Copied to clipboard

Yan Junbing, Chengyu Wang, Taolin Zhang, Xiaofeng He, Jun Huang, Wei Zhang

On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models (2024.acl-short)

Challenge:	Existing methods to solve complex logical reasoning problems are cumbersome for language models.
Approach:	They propose to use iterative methodology to construct a cognitive tree using language models . they propose to generate multiple responses by utilizing in-context examples .
Outcome:	The proposed model achieves a performance level comparable to that of GPT-3.5 . the proposed model contains fewer parameters than 5% of the model with 175B parameters .

Copied to clipboard

Dongyang Li, Junbing Yan, Taolin Zhang, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang

Decoupling Mixture-of-Graphs: Unseen Relational Learning for Knowledge Graph Completion by Fusing Ontology and Textual Experts (2022.coling-1)

Challenge:	Existing RAG methods focus on improving the task performance, without fine-grained process of knowledge.
Approach:	They propose a method that detects long-tail knowledge in large language models by analyzing retrieved documents and enhancing queries indiscriminately with retrieved information.
Outcome:	The proposed method achieves over 4x speedup in average inference time and consistent performance improvement in downstream tasks compared to existing pipelines.

Copied to clipboard

Ran Song, Shizhu He, Suncong Zheng, Shengxiang Gao, Kang Liu, Zhengtao Yu, Jun Zhao

Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation (P19-1)

Challenge:	Existing methods for knowledge Graph Completion (KGC) fail in unseen relation representations.
Approach:	They propose to use three kinds of graphs to obtain unseen relation representations . they propose to decouple mixture-of-graph experts (DMoG) for unseened relations learning .
Outcome:	The proposed method outperforms the state-of-the-art methods on unseen relation representations.

Copied to clipboard

Cao Liu, Shizhu He, Kang Liu, Jun Zhao

Text Generation

Challenge:	Conventional methods employ a fixed vocabulary and one-pass decoding, which make them prone to safe and general responses and lack further refinement to the first generated raw sequence.
Approach:	They propose a Vocabulary Pyramid Network which integrates multi-pass encoding and decoding with multi-level vocabularies into response generation.
Outcome:	The proposed system outperforms strong baselines on English Twitter and Chinese Weibo datasets.

KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals (2021.findings-emnlp)

Copied to clipboard

Jun Zhang, Yan Yang, Chencai Chen, Liang He, Zhou Yu

Natural Language Interfaces

Challenge:	Existing frameworks for multi-subgoal dialogs require a system to build a social bond with users to gain trust and develop affinity.
Approach:	They propose a framework for common knowledge-based multi-subgoal dialogs that divides up conversations with multiple subgoals and propose mechanisms to filter noisy knowledge and to include cleaned knowledge in the dialog response generation process.
Outcome:	The proposed framework obtains state-of-the-art results on a DuRecDial dataset in both automatic and human evaluation.

Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks (2021.emnlp-main)

Copied to clipboard

Qingbin Liu, Pengfei Cao, Cao Liu, Jiansong Chen, Xunliang Cai, Fan Yang, Shizhu He, Kang Liu, Jun Zhao

Dialogue Systems & Conversational Agents

Challenge:	Existing offline DST models require a fixed dataset to train . Existing domain-lifelong learning methods are impractical in real-world applications .
Approach:	They propose a domain-lifelong learning method to continuously train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains.
Outcome:	The proposed method outperforms state-of-the-art lifelong learning methods by 4.25% and 8.27% on the MultiWOZ and the SGD benchmarks.

Teaching Small Language Models to Reason for Knowledge-Intensive Multi-Hop Question Answering (2024.findings-acl)

Copied to clipboard

Xiang Li, Shizhu He, Fangyu Lei, JunYang JunYang, Tianhuang Su, Kang Liu, Jun Zhao

Shuttle Between Symbolic Instructions and Neural Parameters of Large Language Models (2026.acl-long)

Challenge:	Large language models can teach small language models to solve complex reasoning tasks by Chain-of-thought Distillation (CoTD) e.g., mathematical question answering.
Approach:	They propose a method that distills two student models to solve a multi-hop question . they use chain-of-thought distillation to generate step-by-step reasoning paths .
Outcome:	The proposed method surpasses existing methods on knowledge-intensive multi-hop questions.

Copied to clipboard

Wangtao Sun, Haotian Xu, Huanxuan Liao, Xuanqing Yu, Zhongtao Jiang, Shizhu He, Jun Zhao, Kang Liu

Why and How LLMs Benefit from Knowledge Introspection in Commonsense Reasoning (2025.emnlp-main)

Challenge:	Despite their distinct external representations, a deeper analysis reveals their intrinsic nature: instructions serve as a natural language compression devised by humans for data governing specific mapping patterns, whereas parameters act as 'neuro compression' of the same task data.
Approach:	They propose a neural network framework to model and learn the bi-directional mappings between instructions and parameters of large language models by evaluating it on the tasks of instruction deduction and induction.
Outcome:	The proposed framework can map one of the instructions/parameters to the other by evaluating it on the tasks of instruction deduction and induction.

Copied to clipboard

Chengfeng Zhao, Shizhu He, Shanshan Jiang, Bin Dong, Jun Zhao, Kang Liu

Class Lifelong Learning for Intent Detection via Structure Consolidation Networks (2023.findings-acl)

Challenge:	Large Language Models (LLMs) can improve commonsense reasoning by generating intermediate knowledge, but the effectiveness of this knowledge introspection is not always guaranteed.
Approach:	They propose a training-free strategy that optimizes introspection via two stages: Knowledge Detection and Knowledge Regeneration.
Outcome:	The proposed approach mitigates the limitations of standard introspection and has consistent performance gains across all settings.

Copied to clipboard

Qingbin Liu, Yanchao Hao, Xiaolong Liu, Bo Li, Dianbo Sui, Shizhu He, Kang Liu, Jun Zhao, Xi Chen, Ningyu Zhang, Jiaoyan Chen

Sentiment Analysis

Challenge:	Existing intent detection models can only handle predefined intent classes in the offline environment.
Approach:	They propose a method that continually learns new intent classes from new data . structure-based retrospection and contrastive knowledge distillation are used to solve these problems .
Outcome:	The proposed method outperforms existing models on three benchmarks.

Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Database (2024.lrec-main)

Copied to clipboard

Minjun Zhu, Yixuan Weng, Shizhu He, Kang Liu, Haifeng Liu, Yang jun Jun, Jun Zhao

Pre-trained Language Model Based Active Learning for Sentence Matching (2020.coling-main)

Challenge:	Existing benchmarks for textual question answering only focus on single-chain or single-hop retrieval . Existing approaches to answer complex questions have limitations .
Approach:	They propose to conduct Graph-Hop, a novel multi-chains and multi-hops retrieval paradigm in complex question answering.
Outcome:	The proposed model provides explicit and fine-grained evidence graphs for complex question to support comprehensive and detailed reasoning.

Copied to clipboard

Guirong Bai, Shizhu He, Kang Liu, Jun Zhao, Zaiqing Nie

Incremental Intent Detection for Medical Domain with Contrast Replay Networks (2022.findings-acl)

Challenge:	Existing active learning approaches for natural language processing ignore the characteristics of natural language.
Approach:	They propose a pre-trained language model based active learning approach for sentence matching that provides linguistic criteria to measure instances and help select more effective instances for annotation.
Outcome:	The proposed approach can achieve greater accuracy with fewer labeled training instances.

Copied to clipboard

Guirong Bai, Shizhu He, Kang Liu, Jun Zhao

Sentiment Analysis

Challenge:	Existing methods to detect medical intents require fixed pre-defined intent categories . however, novel medical intent categories incessantly emerge with new data and intents in the real world .
Approach:	They propose to incrementally learn emerged medical intents from continually arriving data of new intents while avoiding catastrophically forgetting old ones.
Outcome:	The proposed method outperforms the state-of-the-art model on two benchmarks by 5.7% and 9.1% accuracy.

Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models (2021.eacl-main)

Copied to clipboard

Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott, Bing Liu, James Glass, Fuchun Peng

Dialogue Systems & Conversational Agents

Challenge:	a large-scale unsupervised pretraining has been shown to greatly boost the performance of natural language processing models.
Approach:	They propose an intuitive finetuning strategy to regularize the finetune process . they propose a mix-review strategy to alleviate the forgetting problem .
Outcome:	The proposed strategy regularizes the finetuning process, and the forgetting problem is alleviated . the proposed strategy also improves the performance of the resulting model .

ItD: Large Language Models Can Teach Themselves Induction through Deduction (2024.acl-long)

Copied to clipboard

Wangtao Sun, Haotian Xu, Xuanqing Yu, Pei Chen, Shizhu He, Jun Zhao, Kang Liu

Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning (D19-1)

Challenge:	Recent studies have shown that Large Language Models (LLMs) have limited ability to conduct induction.
Approach:	They propose a framework to enable LLMs to teach themselves induction through deduction.
Outcome:	The proposed framework improves performance on two induction benchmarks and shows that it can be used to teach induction through deduction.

Copied to clipboard

Xiangrong Zeng, Shizhu He, Daojian Zeng, Kang Liu, Shengping Liu, Jun Zhao

Information Extraction & Text Mining

Challenge:	Existing works didn’t consider the extraction order of relational facts in a sentence.
Approach:	They propose to take the extraction order into consideration by applying reinforcement learning into a sequence-to-sequence model.
Outcome:	The proposed model could generate relational facts freely.

STaR-SQL: Self-Taught Reasoner for Text-to-SQL (2025.acl-long)

Copied to clipboard

Mingqian He, Yongliang Shen, Wenqi Zhang, Qiuying Peng, Jun Wang, Weiming Lu

Programming Languages in NLP

Challenge:	Existing methods for generating step-by-step “chain-of-thought” rationales are limited to text-to-SQL.
Approach:	They propose a method that prompts SQL query generation to produce reasoning steps for SQL queries and fine-tunes it on rationales that lead to correct outcomes.
Outcome:	The proposed method outperforms agent-like prompting methods on the Spider benchmark.

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

Copied to clipboard

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

GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks (2026.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

Jianwen Luo, Yiming Huang, Jinxiang Meng, Fangyu Lei, Shizhu He, Xiao Liu, Shanshan Jiang, Bin Dong, Jun Zhao, Kang Liu

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

Challenge:	Existing toolsets that use large language models are limited to single-task settings.
Approach:	They propose a framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios.
Outcome:	The proposed framework achieves up to 4.3 faster milestone completion in Minecraft compared to the previous state-of-the-art method and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks.

Copied to clipboard

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

Automatic Song Translation for Tonal Languages (2022.findings-acl)

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

Copied to clipboard

Fenfei Guo, Chen Zhang, Zhirui Zhang, Qixin He, Kejun Zhang, Jun Xie, Jordan Boyd-Graber

Machine Translation

Challenge:	Existing automatic song translation systems for tonal languages do not match the number of notes and beat the original rhythm of the song.
Approach:	They propose three criteria for effective AST: preserving meaning, singability and intelligibility.
Outcome:	The proposed system balances semantics and singability with human evaluations.

MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts (2024.lrec-main)

Copied to clipboard

Xiang Li, Shizhu He, Jiayu Wu, Zhao Yang, Yao Xu, Yang jun Jun, Haifeng Liu, Kang Liu, Jun Zhao

Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning (2024.lrec-main)

Challenge:	Current Chain-of-thought Distillation methods hinder CoT reasoning performance . student models are separately distilled from specific reasoning tasks . parameter update of student models severely harms CoT ability on unseen reasoning tasks.
Approach:	They propose a method which distills Chain-of-thought reasoning ability of large language models to much smaller student models.
Outcome:	The proposed method improves the reasoning ability of large language models on 14 datasets.

Copied to clipboard

Zhitao He, Pengfei Cao, Zhuoran Jin, Yubo Chen, Kang Liu, Zhiqiang Zhang, Mengshu Sun, Jun Zhao

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Challenge:	Existing studies focus on sentence-level ECI with high-resource languages, leaving document-level DECI with low-resourced languages under-explored.
Approach:	They propose a Heterogeneous Graph Interaction Model with Multi-granularity Contrastive Transfer Learning for zero-shot cross-lingual ECI.
Outcome:	The proposed model outperforms the state-of-the-art model on monolingual and multilingual scenarios by 9.4% and 8.2% of average F1 score.

Copied to clipboard

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo

S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering (2023.acl-short)

Challenge:	Existing research on reinforcement learning for LLMs under data scarcity has not been unified.
Approach:	They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric.
Outcome:	The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area.

Copied to clipboard

Fangyu Lei, Xiang Li, Yifan Wei, Shizhu He, Yiming Huang, Jun Zhao, Kang Liu

Foiling Training-Time Attacks on Neural Machine Translation Systems (2022.findings-emnlp)

Challenge:	Existing question answering systems use a retriever-reader framework to answer multi-hop questions . existing models lack retrieval, selector, and reasoner capabilities .
Approach:	They propose a three-stage text tableQA framework which comprises of retriever, selector, and reasoner.
Outcome:	The proposed framework outperforms baseline methods in the few-shot setting and ranks first on the HybridQA leaderboard.

Copied to clipboard

Jun Wang, Xuanli He, Benjamin Rubinstein, Trevor Cohn

Robustness in NLP

Challenge:	Neural machine translation systems are vulnerable to backdoor attacks . successful backdoors can cause slander, hate speech, phishing, etc. attacks can target very short trigger phrases, which can be challenging to detect even when included verbatim in poisoned instances.
Approach:	They propose a method that exploits asymmetry between source and target sentences to detect outlier tokens.
Outcome:	The proposed method reduces the success of attacks by up to 89.0% while not affecting predictive accuracy.

Backdoor Attacks on Multilingual Machine Translation (2024.naacl-long)

Copied to clipboard

Jun Wang, Qiongkai Xu, Xuanli He, Benjamin Rubinstein, Trevor Cohn

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors (2026.acl-long)

Challenge:	Recent studies have shown that multilingual machine translation systems are vulnerable to backdoor attacks through data poisoning.
Approach:	They propose to investigate the security of multilingual machine translation systems by exposing poisoned data into low-resource languages to cause malicious translations.
Outcome:	The proposed method achieves an average of 20% success rate in attacking high-resource languages.

Copied to clipboard

Rui Yin, Tianxu Han, Naen Xu, Changjiang Li, Ping He, Chunyi Zhou, Jun Wang, Zhihui Fu, Tianyu Du, Jinbao Li, Shouling Ji

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (2024.findings-naacl)

Challenge:	Existing methods to inject safety-aligned large language models rely on token-level mappings, which do not guarantee sustained harmful output.
Approach:	They propose a method that directly modifies model weights to map a trigger to an attacker-specified response.
Outcome:	The proposed method achieves high triggered attack success while maintaining non-triggered safety and general utility.

Copied to clipboard

Wei He, Shichun Liu, Jun Zhao, Yiwen Ding, Yi Lu, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models (2025.coling-main)

Challenge:	Existing methods that rely on limited demos and out-of-demonstration (OOD) queries fail when faced with out- of-demotion queries.
Approach:	They propose a query-aware prompting method that elicits the inherent generalizability of large language models by query-based demo generation.
Outcome:	The proposed method outperforms state-of-the-art methods in the OOD setting and two public math benchmarks.

Copied to clipboard

Huanxuan Liao, Shizhu He, Yupu Hao, Xiang Li, Yuanzhe Zhang, Jun Zhao, Kang Liu

Prediction and Calibration: Complex Reasoning over Knowledge Graph with Bi-directional Directed Acyclic Graph Neural Network (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have high computational costs and privacy concerns due to their high computational expenses and data privacy.
Approach:	They propose a method that empowers SLMs to internalize symbolic knowledge and few-shot examples gradually through a progressive fine-tuning process.
Outcome:	The proposed approach outperforms state-of-the-art baselines by over 5% while reducing inference costs by up to 4 across a wide range of SLMs in both in-domain (ID) and out-of domain (OOD) tasks.

Copied to clipboard

Yao Xu, Shizhu He, Li Cai, Kang Liu, Jun Zhao

Structured Data in NLP

Challenge:	Knowledge graphs (KGs) organize world knowledge as interlinked triples which describe entities and their relationships.
Approach:	They propose a bi-directional Directed Acyclic Graph neural network that splits the reasoning process into prediction and calibration.
Outcome:	The proposed model outperforms previous QE models on FB15k, FB16k-237, and NELL995 on prediction and calibration.

Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching (2023.findings-emnlp)

Copied to clipboard

Zhuoran Jin, Pengfei Cao, Zhitao He, Yubo Chen, Kang Liu, Jun Zhao

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models (2024.emnlp-main)

Challenge:	Continual learning and zero-shot learning approaches have not been adopted to scale to novel-emerging types.
Approach:	They propose a method to recognize entities in novel types by their textual names or descriptions.
Outcome:	The proposed method outperforms the state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types.

Copied to clipboard

Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu

Programming Languages in NLP

Challenge:	DA-Code is a code generation benchmark designed to assess LLMs on agent-based data science tasks.
Approach:	They propose a code generation benchmark specifically designed for LLMs on agent-based data science tasks.
Outcome:	The benchmark performs better than existing frameworks, but lacks accuracy . it is based on real-world data, and includes examples that cover a wide range of tasks .

OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)

Copied to clipboard

He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou

AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing (P19-1)

Challenge:	a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say .
Approach:	They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible .
Outcome:	The proposed framework achieves state-of-the-art performance among open-source projects.

Copied to clipboard

Xiang Zhang, Shizhu He, Kang Liu, Jun Zhao

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

Challenge:	Semantic parsing (SP) maps a natural language utterance into a formal language . standard Seq2Seq models ignore underlying grammars and may give ill-formed results.
Approach:	They propose an end-to-end model for semantic parsing that transduces a natural language sentence to the formal semantic representation.
Outcome:	The proposed model outperforms the state-of-the-art models and does not need expertise like predefined grammar or sketches in the meantime.

Copied to clipboard

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

Multilingual Knowledge Graph Completion from Pretrained Language Models with Knowledge Constraints (2023.findings-acl)

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

Ran Song, Shizhu He, Shengxiang Gao, Li Cai, Kang Liu, Zhengtao Yu, Jun Zhao

Instance-Level Dynamic LoRAs Composition for Cross-Task Generalization (2024.findings-emnlp)

Challenge:	Existing methods for multilingual knowledge graph completion do not align with mKGC tasks because of their English-centric bias.
Approach:	They propose to use multilingual pretrained language models to solve queries in different languages by reasoning a tail entity.
Outcome:	The proposed method outperforms the previous SOTA on Hits@1 and Hits @10 by 12.32% and 16.03% on public datasets.

Copied to clipboard

Zhiqi Wang, Shizhu He, Kang Liu, Jun Zhao

Challenge:	Large language models perform well on tasks that have undergone fine-tuning of instructions, but performance on completely unseen tasks is often less than ideal.
Approach:	They propose a task-level LoRAs combination which learns the LoRA modules combination weights based on a small number of samples to form the task model.
Outcome:	The proposed method outperforms the typical method, LoraHub, on 16 out of 27 tasks.

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs (2026.findings-acl)

Copied to clipboard

Zhongxiang Sun, Yi Zhan, Chenglei Shen, Weijie Yu, Xiao Zhang, Ming He, Jun Xu

Weicong Qin, Yi Xu, Weijie Yu, Teng Shi, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu

Challenge:	Personalization can inadvertently distort factual reasoning when faced with factual queries.
Approach:	They propose a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior.
Outcome:	Experiments across multiple LLM backbones and personalization methods show that FPPS significantly improves factual accuracy while maintaining personalized performance.

Copied to clipboard

Information Retrieval

Challenge:	Existing methods rely on semantic similarity to align historical consultations with current queries due to the absence of ‘value’ labels, but this lacks exploration of needs in user consultations.
Approach:	They propose a consultation value assessment framework that evaluates historical consultations from three novel perspectives: (1) Scenario Scope Value, (2) Posterior Action Value, and (3) Time Decay Value.
Outcome:	The proposed model outperforms baselines on public and commercial datasets on both retrieval and ranking tasks.

AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation (2024.findings-emnlp)

Copied to clipboard

Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Kang Liu, Jun Zhao

TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning (2025.findings-acl)

Challenge:	Recent advances in deep learning have significantly impacted the legal domain.
Approach:	They propose a multi-agent framework for judicial decision-making that simulates the court trial process . they propose 420 Chinese judgment documents to support their framework and build a large-scale legal knowledge base .
Outcome:	The proposed framework outperforms existing methods in various aspects, especially in generating legal articles.

Copied to clipboard

Xuanli He, Jun Wang, Qiongkai Xu, Pasquale Minervini, Pontus Stenetorp, Benjamin I. P. Rubinstein, Trevor Cohn

Improving Entity Linking through Semantic Reinforced Entity Embeddings (2020.acl-main)

Challenge:	Despite the increasing support for multilingual capabilities, the impact of backdoor attacks on LLMs remains under-explored.
Approach:	They propose to use poisoned instructiontuning data to attack multilingual LLMs . their results show that more powerful models show increased susceptibility to transferable cross-lingual backdoor attacks .
Outcome:	The proposed attack is effective in models like BLOOM and GPT-4o with high success rates in more than 7 out of 12 languages.

Copied to clipboard

Feng Hou, Ruili Wang, Jun He, Yi Zhou

Generating Questions for Knowledge Bases via Incorporating Diversified Contexts and Answer-Aware Loss (D19-1)

Challenge:	Existing entity embeddings are effective, but too distinctive for linking models to learn contextual commonality.
Approach:	They propose a method to inject fine-grained semantic information into entity embeddings . they use word embedds of type words to generate semantic embeddngs based on existing embeddables a sample of semantic information is injected into the embedded entities .
Outcome:	The proposed method reduces the distinctiveness of existing embeddings and improves performance.

Copied to clipboard

Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, Jun Zhao

Knowledge Representation

Challenge:	Conventional methods for question generation neglect two crucial research issues: 1) the given predicate needs to be expressed; 2) the answer to the generated question needs to have a definitive answer.
Approach:	They propose a neural encoder-decoder model with multi-level copy mechanisms to generate questions . they also introduce answer-aware loss to make generated questions correspond to more definitive answers.
Outcome:	The proposed model achieves state-of-the-art performance while corresponding to more definitive answers.

Large Language Models are Better Reasoners with Self-Verification (2023.findings-emnlp)

Copied to clipboard

Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, Jun Zhao

Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs (2026.acl-long)

Challenge:	Existing methods to solve complex natural language processing tasks require multiple steps to verify the answers.
Approach:	They propose to use chain of thought prompting to solve reasoning tasks with large language models.
Outcome:	The proposed method can improve reasoning performance on arithmetic, commonsense, and logical reasoning datasets.

Copied to clipboard

Huanxuan Liao, Shizhu He, Yupu Hao, Yequan Wang, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

Green & Sustainable NLP

Challenge:	Continual Learning (CL) for Large Language Models faces a fundamental Stability-Plasticity Dilemma . Rank-Blindness enforces a single rank constraint across diverse tasks, leading to catastrophic forgetting of earlier tasks and underfitting on complex new ones.
Approach:	They propose a rank-spectrum-based rehearsal-free framework that explicitly disentangles knowledge into two orthogonal subspaces.
Outcome:	The proposed framework achieves a superior stability-plasticity balance compared to single-rank baselines.

Safety Alignment via Constrained Knowledge Unlearning (2025.acl-long)

Copied to clipboard

Zesheng Shi, Yucheng Zhou, Jing Li, Yuxin Jin, Yu Li, Daojing He, Fangming Liu, Saleh Alharbi, Jun Yu, Min Zhang

Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval (2025.findings-acl)

Challenge:	Existing defense mechanisms have not fully deleted harmful knowledge in large language models (LLMs) Existing methods to address safety alignment have not completely deleted harmful information in LLMs.
Approach:	They propose a safety alignment strategy that uses scoring neurons to identify useful knowledge in LLMs and pruning the gradients of neurons in U to preserve beneficial information.
Outcome:	The proposed method significantly improves model safety while maintaining utility compared to existing methods.

Copied to clipboard

Jiabei Chen, Guang Liu, Shizhu He, Kun Luo, Yao Xu, Jun Zhao, Kang Liu

CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models (2025.findings-emnlp)

Challenge:	Existing approaches to multihop question answering (MHQA) over long contexts are often neglecting explicit reasoning or incurring expensive computational costs due to full-attention mechanisms over long contextuals.
Approach:	They propose a framework that integrates Monte Carlo Tree Search (MCTS) with dynamic key-value retrieval to enable iterative, context-aware reasoning.
Outcome:	The proposed framework integrates Monte Carlo Tree Search (MCTS) with dynamic key-value (KV) retrieval to enable iterative, context-aware reasoning.

Copied to clipboard

Zhuofan Chen, Jiyuan He, Yichi Zhang, Xing Hu, Haoxing Wen, Jun Bai, Wenge Rong