Papers by Li Kong

Event Transition Planning for Open-ended Text Generation (2022.findings-acl)

Challenge:	Recent advances in speech large language models have enabled end-to-end spoken interactions, but their robustness in real-world applications remains unclear.
Approach:	They propose a multi-turn, multi-domain speech–text TOD dataset for Chinese users . it contains 5.4k dialogues with annotations for dialogue states, disfluency types, speaker characteristics .
Outcome:	The proposed model can be used to evaluate speech large language models in real-world scenarios . the proposed model is based on 5.4k real human-to-human dialogues with annotations .

Copied to clipboard

Qintong Li, Piji Li, Wei Bi, Zhaochun Ren, Yuxuan Lai, Lingpeng Kong

Text Generation

Challenge:	Open-ended text generation tasks require models to generate coherent continuation given limited preceding context.
Approach:	They propose a novel two-stage method which explicitly arranges ensuing events in open-ended text generation tasks.
Outcome:	The proposed method improves coherence and diversity of open-ended text generation tasks.

Large Language Models are not Fair Evaluators (2024.acl-long)

Copied to clipboard

Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui

FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining (2026.acl-long)

Challenge:	Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent.
Approach:	They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt.
Outcome:	The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments.

Copied to clipboard

Xiquan Li, Xuenan Xu, Ziyang Ma, Wenxi Chen, Haolin He, Qiuqiang Kong, Xie Chen

Multi-Hop Question Generation via Dual-Perspective Keyword Guidance (2025.findings-acl)

Challenge:	Existing audio-language models excel at clip-level understanding but struggle with frame-level tasks.
Approach:	They propose a novel training paradigm that advances both clip- and frame-level alignment in CLAP with heterogeneous data.
Outcome:	The proposed training paradigm improves both clip- and frame-level alignment in CLAP with heterogeneous data.

Copied to clipboard

Maodong Li, Longyin Zhang, Fang Kong

How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models (2025.findings-naacl)

Challenge:	Existing work fails to fully utilize the guiding potential of keywords and neglect to differentiate the distinct roles of question-specific and document-specific keywords.
Approach:	They propose a dual-perspective keyword-guided framework that integrates question and document keywords into the multi-hop question generation process.
Outcome:	The proposed framework integrates question and document keywords into the multi-hop question generation process.

Copied to clipboard

Jiyue Jiang, Pengan Chen, Liheng Chen, Sheng Wang, Qinghang Bao, Lingpeng Kong, Yu Li, Chuan Wu

MalURLBench: A Benchmark Evaluating Agents’ Vulnerabilities When Processing Web URLs (2026.findings-acl)

Challenge:	Cantonese has scant representation in NLP research, especially compared to other languages from similarly developed regions.
Approach:	They propose to evaluate Cantonese LLM performance in factual generation, mathematical logic, complex reasoning, and general knowledge in Cantonesian.
Outcome:	The proposed models will evaluate Cantonese's performance in factual generation, mathematical logic, complex reasoning, and general knowledge in Cantone.

Copied to clipboard

Dezhang Kong, Zhuxi Wu, Shiqi Liu, ZhiCheng Tan, Kuichen Lu, Minghao Li, Qichen Liu, Shengyu Chu, Zhenhua Xu, Xuan Liu, Meng Han

Robustness in NLP

Challenge:	Existing models struggle to detect elaborately disguised malicious URLs, despite their ability to process malicious URL's.
Approach:	They propose a benchmark to evaluate LLMs’ vulnerabilities to malicious URLs and a lightweight defense module to mitigate the vulnerability.
Outcome:	The proposed framework analyzes 61,845 attack instances spanning 10 real-world scenarios and 7 categories of real malicious websites.

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

Copied to clipboard

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

A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure (2020.acl-main)

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

Copied to clipboard

Longyin Zhang, Yuqing Xing, Fang Kong, Peifeng Li, Guodong Zhou

Benchmarking LLM’s Capability in Reasoning over Conflicting Web References (2026.acl-long)

Challenge:	Text-level discourse parsing of discourse rhetorical structure (DRS) is a fundamental research topic in natural language processing.
Approach:	They propose a top-down neural architecture for text-level discourse parsing . they cast the parser as a recursive split point ranking task .
Outcome:	The proposed top-down approach is more suitable for text-level discourse parsing.

Copied to clipboard

Yizhen Yuan, Rui Kong, Dongze Li, Yuanchun Li, Yunxin Liu

Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading (2020.coling-main)

Challenge:	Large language models (LLMs) integrated with retrieval-augmented generation (RAG) are a dominant framework for building intelligent assistants.
Approach:	They propose a benchmark to evaluate LLMs' reasoning capability over real-world conflicting documents retrieved from the web.
Outcome:	The proposed benchmark evaluates LLMs' reasoning capability over real-world conflicting documents retrieved from the web.

Copied to clipboard

Feng Jiang, Xiaomin Chu, Peifeng Li, Fang Kong, Qiaoming Zhu

Syllogistic Reasoning for Legal Judgment Analysis (2023.emnlp-main)

Challenge:	Existing methods on discourse parsing in English suffer from long discourse units and fewer explicit connectives.
Approach:	They propose to use two reading modes to construct Chinese paragraph level discourse trees.
Outcome:	The proposed model outperforms baselines on Chinese discourse trees.

Copied to clipboard

Wentao Deng, Jiahuan Pei, Keyi Kong, Zhe Chen, Furu Wei, Yujun Li, Zhaochun Ren, Zhumin Chen, Pengjie Ren

SCVQ: Sparse-Compensated Vector Quantization for Large Language Models (2026.acl-long)

Challenge:	Legal judgment assistants are developing fast due to impressive progress of large language models.
Approach:	They construct and manually correct a syllogistic reasoning dataset for legal judgment analysis using large language models as benchmarks.
Outcome:	The proposed dataset contains 11,239 criminal cases covering 4 criminal elements, 80 charges and 124 articles.

Copied to clipboard

Zixuan Zhou, Yujun Diao, Zicheng Kong, Dehua Ma, Zhenbo Xu, Pei Pei Li, Zhaofeng He

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)

Challenge:	Existing vector quantization methods incur inference overhead due to massive codebook storage and intensive index lookups.
Approach:	They propose a framework for vector quantization that incorporates a salience-aware weighted K-means clustering scheme with symmetry constraints to reduce codebook size and indexing costs.
Outcome:	The proposed framework achieves a perplexity of 5.78 on WikiText-2 for LLaMA-2-7B at 2-bit quantization while delivering a 1.4 speedup over existing baselines.

Copied to clipboard

Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu

A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing (2022.coling-1)

Challenge:	Large vision-language models (LVLMs) are evolving rapidly and require data with human supervision to achieve better alignment.
Approach:	They introduce VLFeedback, the first large-scale vision-language feedback dataset . they train Silkie, an LVLM fine-tuned via direct preference optimization .
Outcome:	The proposed model outperforms its base model in helpfulness, visual faithfulness, and safety metrics and exhibits enhanced resilience against red-teaming attacks.

Copied to clipboard

Yaxin Fan, Peifeng Li, Fang Kong, Qiaoming Zhu

Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning (2020.findings-emnlp)

Challenge:	Existing studies have focused on graph-based and transition-based discourse parsing, but no study has investigated the advantages of both paradigms for conversational discourse paring.
Approach:	They propose a distance-aware multi-task framework that incorporates the strengths of transition-based paradigms to facilitate conversational discourse parsing.
Outcome:	The proposed framework improves the graph-based paradigm on long-distance dependency links.

Copied to clipboard

Bingbing Li, Zhenglun Kong, Tianyun Zhang, Ji Li, Zhengang Li, Hang Liu, Caiwen Ding

Joint Semantic and Strategy Matching for Persuasive Dialogue (2023.findings-emnlp)

Challenge:	Pretrained large-scale language models have been criticized for their limited weight storage and computational speed on hardware platforms.
Approach:	They propose an efficient transformer-based large-scale language representation using hardware-friendly block structure pruning.
Outcome:	The proposed model achieves 5.0x accuracy on GLUE benchmarks and 1.79x compression rate on DistilBERT.

Copied to clipboard

Chuhao Jin, Yutao Zhu, Lingzhen Kong, Shijie Li, Xiao Zhang, Ruihua Song, Xu Chen, Huan Chen, Yuchong Sun, Yu Chen, Jun Xu

Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models (2025.findings-emnlp)

Challenge:	Persuasive dialogue models rely on utterance semantic matching and a key aspect has been ignored . compared with utterrance semantics, conversation strategies are high-level concepts, which can be informative and provide complementary information to achieve effective persuation.
Approach:	They propose to model conversation semantics and strategies to match them using a BERT-like module and an auto-regressive predictor.
Outcome:	The proposed model improves state-of-the-art by 5% on a small and 37% on 'large' datasets.

Copied to clipboard

Jiyue Jiang, Alfred Kar Yin Truong, Yanyu Chen, Qinghang Bao, Sheng Wang, Pengan Chen, Jiuming Wang, Lingpeng Kong, Yu Li, Chuan Wu

TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Review (2025.emnlp-main)

Challenge:	Cantonese is considered a low-resource language due to the dominance of Mandarin . rich colloquial vocabulary of Cantone, English loanwords, and code-switching characteristics add to the complexity of corpus collection and processing.
Approach:	We collect Cantonese texts from open source corpora, Hong Kong-specific forums, Wikipedia . we refine the model through supervised fine-tuning on curated Cantonesian tasks .
Outcome:	The model achieves state-of-the-art (SOTA) performance on four Cantonese benchmarks.

Copied to clipboard

Yuan Chang, Ziyue Li, Hengyuan Zhang, Yuanbo Kong, Yanru Wu, Hayden Kwok-Hay So, Zhijiang Guo, Liya Zhu, Ngai Wong

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have shown significant potential in assisting peer review, but current methods struggle to generate thorough and insightful reviews while maintaining efficiency.
Approach:	They propose a framework that models paper review as a hierarchical and bidirectional question-answering process.
Outcome:	The proposed framework outperforms baselines on full review generation and actionable feedback comments generation tasks while reducing LLM token usage by up to 80% compared to computationally intensive approaches.

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

Copied to clipboard

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

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models (2024.findings-acl)

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

Copied to clipboard

Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong

A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment (2023.acl-long)

Challenge:	Multimodal reasoning is a key capability for large vision-language models . however, the vanilla Chain-of-Thought method fails to address critical steps in multi-step reasoning tasks.
Approach:	They propose a bi-modal Behavioral Alignment method to augment multimodal reasoning . they use domain-specific language to integrate multimodal information into a precise alternative form .
Outcome:	The proposed method significantly improves GPT-4V(ision) on geometry problem solving, chess positional advantage prediction and molecular property prediction.

Copied to clipboard

Jiyue Jiang, Sheng Wang, Qintong Li, Lingpeng Kong, Chuan Wu

Mitigating Contradictions in Dialogue Based on Contrastive Learning (2022.findings-acl)

Challenge:	Existing cognitive stimulation systems lack data on how to integrate emotional support and therapy principles into chit-chat dialogue systems.
Approach:	They propose a multi-source knowledge fusion method for CS dialogue to generate open-ended responses guided by the therapy principle and emotional support strategy.
Outcome:	The proposed method generates open-ended responses guided by the therapy principle and emotional support strategy of the target response.

Copied to clipboard

Weizhao Li, Junsheng Kong, Ben Liao, Yi Cai

MODDP: A Multi-modal Open-domain Chinese Dataset for Dialogue Discourse Parsing (2024.findings-acl)

Challenge:	Current chatbots generate fluent, informative responses but sometimes generate contradictory responses when interacting with human.
Approach:	They propose to use contrastive learning technique to mitigate contradiction issues in chatbots by minimizing the similarity between the target response and contradiction related negative example.
Outcome:	The proposed method outperforms existing methods on automatic and human evaluation while preserving response fluency.

Copied to clipboard

Chen Gong, DeXin Kong, Suxian Zhao, Xingyu Li, Guohong Fu

NarGINA: Towards Accurate and Interpretable Children’s Narrative Ability Assessment via Narrative Graphs (2025.findings-acl)

Challenge:	Existing benchmark datasets for discourse parsing are domain-specific and contain only textual modality . this makes it difficult to accurately understand the dialogue without multi-modal clues .
Approach:	They propose a multi-modal Chinese discourse parsing dataset based on open-domain dialogues . they propose to integrate multi-modality into the original textual unimodal DDP model .
Outcome:	The proposed dataset improves on the existing unimodal model by adding multimodalities to the model.

Copied to clipboard

Jun Zhong, Longwei Xu, Li Kong, Xianzhuo Li, Dandan Liang, Junsheng Zhou

Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks (2025.coling-main)

Challenge:	Existing methods for assessing children's narrative ability are limited to evaluating completeness of narrative content and the coherence of expression, as well as interpretability of assessment results.
Approach:	They propose a computational framework for assessing narrative ability using a narrative graph to provide a concise and structured summary representation of narrative text.
Outcome:	The proposed framework achieves significant performance improvement over baselines while possessing good interpretability.

Copied to clipboard

Qintong Li, Leyang Cui, Lingpeng Kong, Wei Bi

MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints (2026.findings-acl)

Challenge:	Existing work uses large language models (LLMs) to evaluate natural language process tasks, but there are shortcomings in current LLMs.
Approach:	They examine the alignment between LLM evaluators and human annotators by comparing conventional and alignment tasks with different evaluation criteria.
Outcome:	The proposed models excel in general criteria, such as fluency, but face challenges with complex criteria, including numerical reasoning.

Copied to clipboard

Kangyang Luo, Shuzheng Si, Yuzhuo Bai, Cheng Gao, Zhitong Wang, Cheng Huang, Yingli Shen, Yufeng Han, Wenhao Li, Cunliang Kong, Maosong Sun

Information Extraction & Text Mining

Challenge:	Existing supervised neural methods are underexplored for coreference resolution, especially in incremental clustering.
Approach:	They propose a dual-threshold incremental clustering approach based on a lightweight Transformer.
Outcome:	Experiments on common benchmarks show that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints.

Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation (2023.findings-acl)

Copied to clipboard

Fei Yuan, Yinquan Lu, Wenhao Zhu, Lingpeng Kong, Lei Li, Yu Qiao, Jingjing Xu

Multilinguality

Challenge:	Existing monolithic models for multilingual neural machine translation encounter parameter interference and inefficient inference for large models.
Approach:	They propose a detachable multi-way model that assigns each language to an individual branch . they use data from OPUS to build a translation benchmark covering 433 languages .
Outcome:	The proposed model outperforms existing models in OPUS and is faster than existing models.

Aspect-Category Enhanced Learning with a Neural Coherence Model for Implicit Sentiment Analysis (2023.findings-emnlp)

Copied to clipboard

Jin Cui, Fumiyo Fukumoto, Xinfeng Wang, Yoshimi Suzuki, Jiyi Li, Wanzeng Kong

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) is a major research topic in NLP since social networking services have increased . but the recognition of implicit sentiments that do not contain obvious opinion words remains unexplored . elcom captures document-level coherence by using contrastive learning and sentence-level by a hypergraph .
Approach:	They propose aspect-category enhanced learning with a neural coherence model . it captures document-level coherency by contrastive learning and sentence-level by a hypergraph .
Outcome:	The proposed model captures document-level coherence by using contrastive learning and sentence-level by a hypergraph to mine opinions from explicit sentences to aid implicit sentiment classification.

Modeling and Solving Stable Matching under Probabilistic Preferences with Large Language Models (2026.findings-acl)

Copied to clipboard

Yuqi Kong, Shiyu Liu, Jiaxu Li, Hongtao Liu, Qi Qi, Weiran Shen

GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers (2024.acl-long)

Challenge:	Large language models (LLMs) have shown strong capability in understanding and simulating humans’ decisions, suggesting a new way to use LLMs as tools to study social systems.
Approach:	They propose a Hybrid GS–LLM matching method that integrates Gale–Shapley with probabilistic acceptance decisions.
Outcome:	The proposed method outperforms classical baselines in terms of stability and improves robustness under uncertainty.

Copied to clipboard

Qintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong, Wei Bi

Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation (2026.acl-industry)

Challenge:	Large language models (LLMs) have demonstrated impressive performance across various mathematical reasoning benchmarks.
Approach:	They introduce an adversarial grade school math dataset and explore whether LLMs can be more robust when questions are slightly changed.
Outcome:	The proposed method generates and verifies each intermediate thought based on its reasoning goal and calculation result.

Copied to clipboard

Hongyang Su, Beibei Kong, Lei Cheng, Chengxiang Zhuo, Zang Li, Chenyun Yu

Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition (2025.emnlp-main)

Challenge:	a new approach to news recommendation grounds each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords.
Approach:	They propose an intent-driven Semantic ID generation paradigm to address these challenges . they map diverse intents to hierarchical SID prefixes and then fuzzy-match them to current news pool .
Outcome:	The proposed model achieves 0% hallucination and 12.4% L1 match on a mainstream Chinese news platform.

Copied to clipboard

Chenxin An, Zhihui Xie, Xiaonan Li, Ming Zhong, Shansan Gong, Lei Li, Jun Zhang, Jingjing Xu, Lingpeng Kong

SenseJudge: Human-Centric Preference-Driven Judgment Framework (2026.findings-acl)

Challenge:	Existing research on long-context scaling in language models has focused on managing lengthy input prompts instead of producing long outputs.
Approach:	They propose a sequence-level curriculum learning framework that shifts a model’s focus from interpreting long chain-of-thoughts to generating them.
Outcome:	Experiments on rigorous reasoning benchmarks, including AIME24 and GPQA Diamond, show that the proposed approach surpasses standard fine-tuning by over 10% while maintaining robust performance on understanding tasks.

Copied to clipboard

Rui Li, Junfeng Liu, Xiangwen Kong, Zhifang Sui

Challenge:	Existing judgment approaches rely on trained judgers using fixed preference data . existing judgment approaches neglect diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios.
Approach:	They propose a customizable judgment framework driven by human preferences and a diverse instruction following benchmark derived from real-world multi-turn interactions.
Outcome:	The proposed framework surpasses other judgment methods and models in two tasks, and achieves model ranking that aligns with real human sense.

Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph (2020.emnlp-main)

Copied to clipboard

Xin Lv, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Wei Zhang, Yichi Zhang, Hao Kong, Suhui Wu

Structured Data in NLP

Challenge:	Existing reasoning methods for sparse KGs are incomplete and lack of evidential paths to target entities makes multi-hop reasoning difficult.
Approach:	They propose a multi-hop reasoning model over sparse KGs to solve this problem . they use latent prediction of embedding-based models to make the model perform more potential path search over sparses .
Outcome:	The proposed method outperforms state-of-the-art models on five datasets from Freebase, NELL and Wikidata.

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

Copied to clipboard

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

ProcWorld: Benchmarking Large Model Planning in Reachability-Constrained Environments (2025.emnlp-main)

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

Copied to clipboard

Dong Wang, Xinghang Li, Zhengshen Zhang, Jirong Liu, Xiao Ma, Hanbo Zhang, Tao Kong, Huaping Liu

TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Industry Systems (2024.emnlp-industry)

Challenge:	Existing benchmarks for embodied spatial reasoning and long-term planning are non-trivial due to the combinatorial complexity of long-horizon abstract reasoning.
Approach:	They propose a large-scale benchmark for partially observable embodied spatial reasoning and long-term planning with large language models and vision language models.
Outcome:	The proposed model performs better in 16 task types, 5,000 rooms, and over 10 million evaluation trajectories with diverse data distribution.

Copied to clipboard

Yilun Kong, Jingqing Ruan, YiHong Chen, Bin Zhang, Tianpeng Bao, Shi Shiwei, Du Qing, Xiaoru Hu, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao, Xueqian Wang

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

Challenge:	Large language models have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools.
Approach:	They propose a framework to enhance the task planning and tool usage abilities of LLMs in industrial systems.
Outcome:	The proposed framework enhances the task planning and tool usage abilities of LLM-based agents in industrial systems.

Copied to clipboard

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

EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning (2025.acl-long)

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

Copied to clipboard

Xiaoqian Liu, Ke Wang, Yongbin Li, Yuchuan Wu, Wentao Ma, Aobo Kong, Fei Huang, Jianbin Jiao, Junge Zhang

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Existing methods for strategic reasoning face challenges in adaptability, scalability, and transferring strategies to new contexts.
Approach:	They propose an explicit policy optimization model that provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior.
Outcome:	The proposed model provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism (2026.acl-long)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Huan Li, Cong Wang

Information Retrieval

Challenge:	Parallel Speculative Decoding (PSD) has limitations due to speedup limits and high computational waste . a novel synchronous mechanism solves the Retrieval Precision-Efficiency Dilemma .
Approach:	They propose a framework that combines a draft-verification-based approach with a synchronous mechanism to solve the Retrieval Precision-Efficiency Dilemma.
Outcome:	The proposed framework breaks speedup limits for Speculative Decoding by overlapping draft generation with verification.

Automated Essay Scoring via Pairwise Contrastive Regression (2022.coling-1)

Copied to clipboard

Jiayi Xie, Kaiwei Cai, Li Kong, Junsheng Zhou, Weiguang Qu

Challenge:	Existing approaches to automate essay scoring use regression or ranking objectives . a novel neural pairwise ranking model is developed to optimize both objectives based on the same loss .
Approach:	They propose a novel Neural Pairwise Contrastive Regression model that optimizes both objectives simultaneously as a single loss.
Outcome:	The proposed model outperforms previous methods on the public Automated Student Assessment Prize dataset.

Leveraging AMR Graph Structure for Better Sequence-to-Sequence AMR Parsing (2024.lrec-main)

Copied to clipboard

Linyu Fan, Wu Wu Yiheng, Jun Xie, Junhui Li, Fang Kong, Guodong Zhou

Prompting Scientific Names for Zero-Shot Species Recognition (2023.emnlp-main)

Challenge:	Recent studies on AMR parsing often regard this task as a seq2seq translation problem.
Approach:	They propose to translate AMR graphs into AMR token sequences in pre-processing and recover AMR from sequences after decoding.
Outcome:	The proposed approach outperforms baseline and achieves 85.5 0.1 and 84.2 0.2 Smatch scores on AMR 2.0 and AMR 3.0.

Copied to clipboard

Shubham Parashar, Zhiqiu Lin, Yanan Li, Shu Kong

PromptRank: Unsupervised Keyphrase Extraction Using Prompt (2023.acl-long)

Challenge:	We use visionlanguage models (VLMs) to recognize images of common objects in a zero-shot fashion, but it is underexplored how to use CLIP for zero- shot species recognition of highly specialized concepts.
Approach:	They propose a method to translate scientific names to common English names and use them in prompts to improve their performance.
Outcome:	The proposed method performs poorly for species recognition with prompts that use scientific names, e.g., “a photo of Lepus Timidus” (which is a scientific name in Latin) and additionally use them in the prompts.

Copied to clipboard

Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xiaoyan Bai

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

Challenge:	Existing keyphrase extraction methods struggle with document and candidate length discrepancies or fail to fully utilize the pre-trained language model without further fine-tuning.
Approach:	They propose an unsupervised keyphrase extraction approach that uses a pre-trained language model to rank candidates based on document embeddings.
Outcome:	The proposed approach outperforms the existing keyphrase extraction approach on six benchmarks.

Copied to clipboard

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

ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement (2026.acl-long)

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

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao, Zhitong Wang, Yingli Shen, Wenhao Li, Zhu Liu, Yufeng Han, Jiayi Wu, Cunliang Kong, Maosong Sun

Information Extraction & Text Mining

Challenge:	Existing supervised neural methods for coreference resolution are underexplored . current methods rely on small language models, but their potential is underexploited .
Approach:	They propose a framework that integrates an enhanced supervised model with LLM-based reasoning.
Outcome:	The proposed method surpasses existing state-of-the-art methods in coreference resolution.

From Scaffolding to Assimilation: Progressive Structural Internalization for Format-Constrained Creative Text Generation (2026.findings-acl)

Copied to clipboard

Wenhao Li, Yuwei Yang, Xiaoqing Wu, Yufeng Han, Cunliang Kong, Yuzhuo Bai, Xin Cong, Maosong Sun

Text Generation

Challenge:	Existing paradigms rely on unreliable prompting or rigid constrained decoding strategies to achieve aesthetic unity.
Approach:	They propose a framework to embed external constraints into the model’s intrinsic intuition and use it to generate open-ended creative texts.
Outcome:	The proposed framework surpasses baselines in both strict constraint adherence and literary aesthetics.

SDPO: Segment-Level Direct Preference Optimization for Social Agents (2025.acl-long)

Copied to clipboard

Aobo Kong, Wentao Ma, Shiwan Zhao, Yongbin Li, Yuchuan Wu, Ke Wang, Xiaoqian Liu, Qicheng Li, Yong Qin, Fei Huang

Challenge:	Direct Preference Optimization (DPO) has proven effective in aligning LLM behavior with human preferences across various tasks, but is limited in multi-turn social interactions.
Approach:	They propose a method which dynamically selects key segments within interactions to optimize multi-turn agent behavior.
Outcome:	The proposed methods outperform existing methods and proprietary LLMs on the SOTOPIA benchmark and show that they can improve social intelligence.

CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network (2021.acl-long)

Copied to clipboard

Jiajia Tang, Kang Li, Xuanyu Jin, Andrzej Cichocki, Qibin Zhao, Wanzeng Kong

Text Generation

Challenge:	Existing methods for multimodal sentiment analysis require all modalities as input, thus are sensitive to missing modality at predicting time.
Approach:	They propose to model bi-direction interplay via couple learning and exploit multiple bi-directional translations to exploit multimodal fusion embeddings.
Outcome:	The proposed framework achieves state-of-the-art or often competitive performance on two multimodal benchmarks with extensive ablation studies.

Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese (P19-1)

Copied to clipboard

Sheng Xu, Peifeng Li, Fang Kong, Qiaoming Zhu, Guodong Zhou

Challenge:	Currently, most studies on implicit discourse relation recognition use sentence-level representations . Chinese is a paratactic language that tends to pro-drop clause connectives .
Approach:	They propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations.
Outcome:	The proposed model outperforms state-of-the-art models in micro and macro F1 scores on a Chinese discourse corpus.

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation (2021.acl-long)

Copied to clipboard

Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom (2025.emnlp-main)

Challenge:	Recent studies report improvements when equipping models with multimodal information, but it remains unclear whether such improvements actually come from the multimodal part.
Approach:	They propose to extend conventional text-only translation models with multimodal information by extending them with visual input.
Outcome:	The proposed models replicate similar gains as recently developed multimodal-integrated systems achieved, but learn to ignore multimodal information.

Copied to clipboard

Jingqi Zhou, Sheng Wang, Jingwei Dong, Kai Liu, Lei Li, Jiahui Gao, Jiyue Jiang, Lingpeng Kong, Chuan Wu

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)

Challenge:	Large vision-language models often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.
Approach:	They propose a visual reasoning framework that decouples vision-reasoning capabilities and multi-run proactive perception.
Outcome:	The proposed framework outperforms existing models on benchmarks for open-source and closed-source models with 13.2% performance gain.

Copied to clipboard

Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li

Multilinguality

Challenge:	Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored.
Approach:	They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation.
Outcome:	The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs.

E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models (2024.findings-acl)

Copied to clipboard

Jinchang Hou, Chang Ao, Haihong Wu, Xiangtao Kong, Zhigang Zheng, Daijia Tang, Chengming Li, Xiping Hu, Ruifeng Xu, Shiwen Ni, Min Yang

Explanation Regeneration via Information Bottleneck (2023.findings-acl)

Challenge:	despite the rapid development of Large Language Models, there is no dedicated benchmark for evaluating LLMs in Chinese K-12 education.
Approach:	They propose to develop a benchmark specifically tailored for Chinese K-12 education.
Outcome:	EVAL is the first evaluation benchmark specifically tailored for Chinese K-12 education.

Copied to clipboard

Qintong Li, Zhiyong Wu, Lingpeng Kong, Wei Bi

The Devil in Linear Transformer (2022.emnlp-main)

Challenge:	Recent work builds on prompt engineering to generate free-text explanations without specific training, but they lack sufficiency and conciseness due to the prompt complexity and hallucination issues.
Approach:	They propose to generate explanations via the information bottleneck theory by polishing the single-pass output of large pretrained language models but retaining the information that supports the contents being explained by balancing two information bottle neck objectives.
Outcome:	The proposed explanations are based on the information bottleneck theory . they are able to explain black-box predictions naturally and accurately .

Copied to clipboard

Zhen Qin, Xiaodong Han, Weixuan Sun, Dongxu Li, Lingpeng Kong, Nick Barnes, Yiran Zhong

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Challenge:	Existing linear transformers suffer from performance degradations on various tasks and corpus.
Approach:	They propose a new linear attention that replaces scaling with a normalization to stabilize gradients and confine attention to neighbouring tokens in early layers.
Outcome:	The proposed model outperforms vanilla transformers on the long-range arena benchmark while being significantly more space-time efficient.

Copied to clipboard

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Haiquan Zhao, Lingyu Li, Shisong Chen, Shuqi Kong, Jiaan Wang, Kexin Huang, Tianle Gu, Yixu Wang, Jian Wang, Liang Dandan, Zhixu Li, Yan Teng, Yanghua Xiao, Yingchun Wang

Adversarial Text Generation by Search and Learning (2023.findings-emnlp)

Challenge:	Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance.
Approach:	They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 .
Outcome:	The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs.

Copied to clipboard

Guoyi Li, Bingkang Shi, Zongzhen Liu, Dehan Kong, Yulei Wu, Xiaodan Zhang, Longtao Huang, Honglei Lyu

MIND: Towards Immersive Psychological Healing with Multi-Agent Inner Dialogue (2025.findings-emnlp)

Challenge:	Existing text generation methods only use heuristic replacement strategies or language models to generate replacement words at the word level.
Approach:	They propose a search and learning framework for Adversarial Text Generation by Search and Learning to evaluate the robustness of natural language processing models.
Outcome:	The proposed methods are significantly superior to the most advanced methods in terms of attack efficiency and adversarial text quality.

Copied to clipboard

Yujia Chen, Changsong Li, Yiming Wang, Tianjie Ju, Qingqing Xiao, Nan Zhang, Zifan Kong, Peng Wang, Binyu Yan

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)

Challenge:	Mental health issues are worsening in today’s competitive society, such as depression and anxiety.
Approach:	They propose a multi-agent inner dialogue paradigm that provides more immersive psychological healing environments.
Outcome:	The proposed paradigm provides more immersive psychological healing environments.

Copied to clipboard

Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong

Challenge:	Existing methods for detecting unsafe mobile GUI agents are underexplored.
Approach:	They propose a mobile agent safety detection framework that integrates a formal verifier and a VLM-based contextual judge to detect system-level violations.
Outcome:	The proposed framework achieves 10%–30% improvements over existing approaches across multiple metrics.

MECH: A Cost-Effective Multi-Task Cascade Framework for Classroom Opinion Evolution Recognition (2026.acl-long)

Copied to clipboard

Yancui Li, Xiaoyu Zhou, Guoyi Miao, Fang Kong

Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee Recognition (2023.emnlp-main)

Challenge:	Existing studies focus on dialogue act annotation, overlooking the deeper dimension of opinion evolution.
Approach:	They propose a framework for Classroom Opinion Evolution Recognition that translates "Action-Opinion" dualism into a risk-aware routing mechanism.
Outcome:	The proposed framework achieves state-of-the-art accuracy of 78.55% while reducing API costs by 44.4%.

Copied to clipboard

Yaxin Fan, Feng Jiang, Peifeng Li, Fang Kong, Qiaoming Zhu

ZeroGen: Efficient Zero-shot Learning via Dataset Generation (2022.emnlp-main)

Challenge:	Existing approaches to learn dialogue discourse parsing with related tasks require additional annotation, thus limiting their generality.
Approach:	They propose a multitasking framework that integrates dialogue discourse parsing with addressee recognition to reflect relation-based structure of dialogue.
Outcome:	The proposed framework outperforms baselines on the Molweni and STAC datasets.

Copied to clipboard

Jiacheng Ye, Jiahui Gao, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu, Lingpeng Kong

Better Zero-Shot Reasoning with Role-Play Prompting (2024.naacl-long)

Challenge:	Existing approaches to generate training data with pre-trained language models have been found effective in various scenarios.
Approach:	They propose an unsupervised zero-shot learning method that generates a dataset from scratch and trains a tiny task model under supervision of the synthesized dataset.
Outcome:	The proposed method is annotated-free and efficient, but can provide useful insights from the perspective of data-free model-agnostic knowledge distillation and unreferenced text generation evaluation.

Copied to clipboard

Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, Xiaohang Dong

Low-Resource NLP

Challenge:	Recent years have witnessed a paradigm shift in natural language processing, driven by large language models such as GPT-3, PaLM, and Llama.
Approach:	They propose a strategy for role-play prompting and assess its performance under the zero-shot setting.
Outcome:	The proposed method outperforms the standard zero-shot prompting approach across 12 reasoning benchmarks.

Generating Data for Symbolic Language with Large Language Models (2023.emnlp-main)

Copied to clipboard

Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu

Lexical Knowledge Internalization for Neural Dialog Generation (2022.acl-long)

Challenge:	Large language models (LLMs) bring performance and complexity, but they incur a large computational cost in practice.
Approach:	They propose a task-based model which uses large language models to generate symbolic language data by an informative prompt and agreement-based verifier.
Outcome:	The proposed model can generate symbolic language data with a few human demonstrations and saves a considerable amount of inference effort.

Copied to clipboard

Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)

Challenge:	Existing knowledge-grounded dialog models ignore the knowledge that resides in people's minds during a conversation.
Approach:	They propose to integrate lexical knowledge internally into the model's parameters instead of further conditioning them on external knowledge . they adopt contrastive learning approach and use a dictionary-based token-level lexicon retriever that requires only weak supervision.
Outcome:	The proposed model can relate J.K Rowling to Khalsa Aid with the knowledge retrieved from Wikipedia.

Copied to clipboard

Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu

Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning (2025.acl-long)

Challenge:	Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately .
Approach:	They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes .
Outcome:	The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show .

Copied to clipboard

Hui Liu, Wenya Wang, Hao Sun, Chris Xing Tian, Chenqi Kong, Xin Dong, Haoliang Li

Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play (2026.acl-long)

Challenge:	Recent learning-based demonstration selection methods have proven beneficial to in-context learning (ICL) by choosing more useful exemplars.
Approach:	They propose two methods to capture task-agnostic similarities between input and output of LLMs.
Outcome:	The proposed methods integrate task-agnostic similarities of different levels between input and output of exemplars and test cases to eliminate costly data collection.

Copied to clipboard

Xiachong Feng, Deyi Yin, Xiaocheng Feng, Yi Jiang, Libo Qin, Yangfan Ye, Lei Huang, Weitao Ma, Qiming Li, Yuxuan Gu, Bing Qin, Lingpeng Kong

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms (2026.findings-acl)

Challenge:	Existing self-play approaches to developing general reasoning in language models rely on terminal game outcomes.
Approach:	They propose a game-based reasoning transfer model that addresses two barriers to reasoning transfer.
Outcome:	The proposed model improves mathematical reasoning, general reasoning, and code generation benchmarks.

Copied to clipboard

Jinghao Luo, Yuchen Tian, Chuxue Cao, Ziyang Luo, Hongzhan Lin, Kaixin Li, Chuyi Kong, Ruichao Yang, Jing Ma

Challenge:	Large Language Models (LLMs)-based agents have fundamentally reshaped artificial intelligence . however, the inherent statelessness of LLMs hinders their ability to maintain logical consistency across complex, multi-step tasks .
Approach:	They propose a framework for LLM agent memory mechanisms that formalizes the development process into three stages: storage, reflection, and experience.
Outcome:	The proposed framework breaks the development process into three stages . it analyzes the need for long-range consistency, challenges in dynamic environments, and the ultimate goal of continual learning.

Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis (2024.lrec-main)

Copied to clipboard

Jin Cui, Fumiyo Fukumoto, Xinfeng Wang, Yoshimi Suzuki, Jiyi Li, Noriko Tomuro, Wanzeng Kong

Sentiment Analysis

Challenge:	Aspect-category-based sentiment analysis (ACSA) is a popular approach for identifying aspect categories and predicting their sentiments.
Approach:	They propose an enhanced coherence-aware network with hierarchical disentanglement (ECAN) to capture contexts across the whole review and to help the implicit aspect and sentiment identification.
Outcome:	The proposed network decouples multiple aspects and sentiment features and achieves state-of-the-art (SOTA) performance.

Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders (2021.eacl-main)

Copied to clipboard

Xiang Kong, Adithya Renduchintala, James Cross, Yuqing Tang, Jiatao Gu, Xian Li

Multilinguality

Challenge:	Recent work in multilingual translation has improved translation quality surpassing bilingual baselines using deep transformer models with increased capacity.
Approach:	They propose a deep encoder with multiple shallow decoders to reduce inference latency while maintaining translation quality.
Outcome:	The proposed model achieves 1.8x speedup on average compared to a standard transformer model with no drop in translation quality.

DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models (2023.findings-emnlp)

Copied to clipboard

Shansan Gong, Mukai Li, Jiangtao Feng, Zhiyong Wu, Lingpeng Kong

ImgTrojan: Jailbreaking Vision-Language Models with ONE Image (2025.naacl-long)

Challenge:	Existing approaches to text generation use discrete text within a continuous diffusion space, which incurs substantial computational overhead during training and results in slower sampling speeds.
Approach:	They propose a soft absorbing state that facilitates diffusion models in learning to reconstruct discrete mutations based on the underlying Gaussian space.
Outcome:	The proposed method accelerates training convergence by 4x and generates samples of similar quality 800x faster, rendering it closer to practical application.

Copied to clipboard

Xijia Tao, Shuai Zhong, Lei Li, Qi Liu, Lingpeng Kong

Bridging the Preference Gap between Retrievers and LLMs (2024.acl-long)

Challenge:	Existing studies on the safety of large language models (LLMs) with human values have focused on the integration of multi-modal user input into these models.
Approach:	They propose a method to bypass safety constraints of large language models by using poisoned images instead of original textual captions.
Outcome:	The proposed attack bypasses safety constraints of large language models (VLMs) by replacing the original textual captions with malicious jailbreak prompts.

Copied to clipboard

Zixuan Ke, Weize Kong, Cheng Li, Mingyang Zhang, Qiaozhu Mei, Michael Bendersky

Information Retrieval

Challenge:	Existing studies on retrievers and LLMs treat them as separate components . a novel bridge model is proposed to optimize the relationship between the retriever and the LLM .
Approach:	They propose a framework that chains together supervised and reinforcement learning to train a bridge model that optimizes the connection between the retriever and the LLM.
Outcome:	Empirical results show that the proposed model optimizes the connection between the retriever and the LLM.

Can Language Models Understand Physical Concepts? (2023.emnlp-main)

Copied to clipboard

Lei Li, Jingjing Xu, Qingxiu Dong, Ce Zheng, Xu Sun, Lingpeng Kong, Qi Liu