Papers by Liang Cheng
To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models (2024.findings-emnlp)
Copied to clipboard
Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng, Qingbin Liu, Mengru Wang, Dianbo Sui, Xi Chen, Huajun Chen, Ningyu Zhang
| Challenge: | Existing unlearning paradigms are mired in vague forgetting boundaries, erasing knowledge indiscriminately. |
| Approach: | They propose a benchmark to evaluate if unlearning erases essential knowledge . they propose 'knowUnDo' which uses copyrighted content and privacy domains . |
| Outcome: | The proposed method is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs. |
Transductive Learning for Unsupervised Text Style Transfer (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for style transfer are based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases. |
| Approach: | They propose a retrieval-based context-aware style representation that involves top-K relevant sentences in the target style in the transfer process. |
| Outcome: | The proposed method outperforms several strong baselines and is general and effective to the task of unsupervised style transfer. |
Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for dialogue summarization only apply to specific scenarios and domains. |
| Approach: | They propose a pre-trained model specifically designed for multi-scenario multi-domain dialogue summarization. |
| Outcome: | The proposed model significantly outperforms state-of-the-art models on three dialogue summarization datasets from different scenarios and domains. |
SDBench: A Survey-based Domain-specific LLM Benchmarking and Optimization Framework (2025.acl-long)
Copied to clipboard
| Challenge: | acquiring domain-specific knowledge often requires professional expert manpower. |
| Approach: | They propose a generic framework for generating evaluation datasets for domain-specific LLMs. |
| Outcome: | The proposed framework reduces the reliance on expert manpower while ensuring that the collected data is uniformly distributed. |
UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation (2024.acl-long)
Copied to clipboard
Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Cheng Peng, Zhonghao Wang, Haiying Deng
| Challenge: | Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts. |
| Approach: | They have developed an unconstrained hallucination generation evaluation benchmark that contains hallucines generated by large language models with minimal restrictions. |
| Outcome: | The proposed benchmarks are based on a Chinese-language dataset that is lacking in the field. |
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (2022.acl-long)
Copied to clipboard
Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang
| Challenge: | Named Entity Recognition models are feature-engineering and machine learning based. |
| Approach: | They propose a new NER learning framework that uses entity mentions to improve model performance. |
| Outcome: | The proposed model achieves better performance on OOV entities on various settings and datasets. |
Neutralizing Bias in LLM Reasoning using Entailment Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Natural Language Inference (NLI) is a foundational understanding task in language understanding. |
| Approach: | They propose a framework to construct counterfactual reasoning data and fine-tune LLMs to reduce attestation bias. |
| Outcome: | The proposed framework reduces hallucinations from attestation bias on original and bias-neutralized datasets while keeping hypotheses unchanged. |
HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)
Copied to clipboard
Qiao Cheng, Juntao Liu, Xiaoye Qu, Jin Zhao, Jiaqing Liang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Yanghua Xiao
| Challenge: | Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention. |
| Approach: | They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents. |
| Outcome: | The proposed model achieves a high 96% F1 score on data quality and is far lower than humans. |
SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness (2026.acl-long)
Copied to clipboard
Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang, Zhou Zhao
| Challenge: | SDiaReward is an end-to-end spoken dialogue system that integrates paralinguistic nuances and spontaneous nature of human conversation. |
| Approach: | They propose an end-to-end multi-turn reward model trained on SDiaReward-Dataset . it is a collection of episode-level preference pairs targeting modality and colloquiality gaps . |
| Outcome: | The proposed model outperforms general-purpose audio LLMs in episode-level evaluation. |
Sources of Hallucination by Large Language Models on Inference Tasks (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI) |
| Approach: | They propose to use LLMs to probe their behavior using controlled experiments. |
| Outcome: | The proposed models perform significantly worse on NLI test samples which do not conform to these biases than those which do. |
VisDiaHalBench: A Visual Dialogue Benchmark For Diagnosing Hallucination in Large Vision-Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Despite the significant success of large vision-language models, some studies have revealed that LVLMs suffer from the hallucination problem when given long-term misleading textual history. |
| Approach: | They propose a visual dialogue hallucination evaluation benchmark VisDiaHalBench to investigate the halluciation problem of large vision-language models when given long-term misleading textual history. |
| Outcome: | The proposed benchmark consists of samples with five-turn questions about an edited image and its original version. |
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)
Copied to clipboard
Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu
| Challenge: | Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature. |
| Approach: | They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management. |
| Outcome: | The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench. |
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results. |
| Approach: | They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment. |
| Outcome: | The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining. |
Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-modal entity alignment (MMEA) is a critical task that aims to identify equivalent entity pairs across multi-modal knowledge graphs (MMKGs). |
| Approach: | They propose a novel MMEA transformer that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance alignment task. |
| Outcome: | The proposed transformer hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task. |
UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions (2026.acl-long)
Copied to clipboard
Chunyu Qiang, Xiaopeng Wang, Kang Yin, Yuzhe Liang, Yuxin Guo, Teng Ma, Ziyu Zhang, Tianrui Wang, Cheng Gong, Yushen Chen, Ruibo Fu, Longbiao Wang, Jianwu Dang
| Challenge: | Generative audio modeling has been fragmented into specialized tasks such as text-to-speech (TTS), text- to-music (TTM), and text-ta (TTA) specialized models require reference audio for timbre cloning and strict phoneme alignment, whereas TTA models generate unstructured textures from open-ended captions. |
| Approach: | They propose a unified flow-matching framework capable of synthesizing speech, music, sound effects . they propose 'token injection mechanism' that projects unstructured environmental sounds into structured temporal latent space . |
| Outcome: | The proposed framework achieves state-of-the-art performance in instruction-based TTS and TTM while maintaining competitive fidelity in TTA. |
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)
Copied to clipboard
Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li
| Challenge: | In-context learning of large-language models has achieved remarkable success in the field of natural language processing . however, the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL. |
| Approach: | They propose a workflow paradigm method to enhance the attention and problem-solving scope of large-language models through decomposition. |
| Outcome: | The proposed method outperforms existing methods on three datasets and improves the upper limit of LLM-based approaches. |
MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on knowledge editing focus on monolingual scenarios, neglecting the complexities presented by multilingual contexts and multi-hop reasoning. |
| Approach: | They propose a benchmark to evaluate the adaptability of multilingual knowledge editing methods. |
| Outcome: | The proposed benchmark evaluates the adaptability of multilingual knowledge editing methods across five languages. |
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning (2022.acl-long)
Copied to clipboard
Qin Liu, Rui Zheng, Bao Rong, Jingyi Liu, ZhiHua Liu, Zhanzhan Cheng, Liang Qiao, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to generating adversarial perturbations scale up the cost of training computational complexity by the number of gradient steps it takes to obtain the adversarials. |
| Approach: | They propose a flood method which aims at better generalization and a criterion to bring hyper-parameter-dependent flooding into effect with a narrowed-down search space by measuring how the gradient steps taken within one epoch affect the loss of each batch. |
| Outcome: | The proposed method improves BERT’s resistance to textual adversarial attacks by a large margin and achieves state-of-the-art robust accuracy on various text classification and GLUE tasks. |
DialogGen: Multi-modal Interactive Dialogue System with Multi-turn Text-Image Generation (2025.findings-naacl)
Copied to clipboard
Minbin Huang, Yanxin Long, Xinchi Deng, Ruihang Chu, Jiangfeng Xiong, Xiaodan Liang, Hong Cheng, Qinglin Lu, Wei Liu
| Challenge: | Text-to-image (T2I) generation models have advanced in recent years, but effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation. |
| Approach: | They propose to use off-the-shelf MLLMs and T2I models to build a multi-modal interactive dialogue system (MIDS) that can generate correct output modalities and coherence of output images. |
| Outcome: | The proposed pipeline can generate correct output modalities and coherent multi-modal outputs compared with other state-of-the-art models. |
MCS: An In-battle Commentary System for MOBA Games (2022.coling-1)
Copied to clipboard
Xiaofeng Qi, Chao Li, Zhongping Liang, Jigang Liu, Cheng Zhang, Yuanxin Wei, Lin Yuan, Guang Yang, Lanxiao Huang, Min Li
| Challenge: | In-battle commentary is an important component of live streaming of e-sports competitions and is applicable to a wide range of scenarios like combat information analysis and live streaming. |
| Approach: | They propose a generative system for in-battle real-time commentary in mobile MOBA games and propose 'transform' method to convert match statistics and utterances into consistent encoding space. |
| Outcome: | The proposed system is based on real-time match statistics and events and can be used for live streaming, e-sports commentary and combat information analysis. |
Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue (2024.findings-naacl)
Copied to clipboard
| Challenge: | emergence of large language models (LLMs) improves capabilities of dialogue systems . but they lack communication skills, which make them more like information seeking tools . |
| Approach: | They propose to empower LLMs with communication skills through inner monologues . they use a benchmark to evaluate the dialogue generation ability of the model . |
| Outcome: | The proposed model outperforms the baselines in the evaluation of communication skills. |
Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM-based agents lack inherent spatial awareness, relying on web search or text matching while hallucinating spatial relationships. |
| Approach: | They propose a spatial-based agent that can perform real-world geospatial computations . they use natural-language questions to parse into executable workflows based on geoFlow Graphs - directed acyclic graphs with nodes corresponding to spatial concepts and edges representing transformations. |
| Outcome: | The proposed agent outperforms existing baselines on MapEval-API and MapQA benchmarks while producing interpretable and executable geospatial workflows. |
MaCSC: Towards Multimodal-augmented Pre-trained Language Models via Conceptual Prototypes and Self-balancing Calibration (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to training pre-trained language models (PLMs) focus on static image modality; inevitably encounter modality gaps and noise; and treat all modalities. |
| Approach: | They propose a multimodal-augmented framework that can infuse multimodal semantics into PLMs and facilitate a self-balancing calibration of information allocation. |
| Outcome: | The proposed framework outperforms baselines on multiple NLP tasks and outperformed existing frameworks. |
MedQPA-Gen: Medical Question Proposing and Answering for Report Generation (2026.findings-acl)
Copied to clipboard
Weijie Liang, Xiyue Zhu, Ruike Zhu, Chenhao Li, Cheng Tang, Zhiyu Liu, Zhihua Gong, Shirui Luo, Yudu Li, Volodymyr Kindratenko
| Challenge: | Existing training paradigms fail to explicitly target factual accuracy, resulting in inaccuracies and serious patient safety risks. |
| Approach: | They propose an automatic and generalizable report evaluation technique that uses question proposing and answering to enable controllable, structured reasoning grounded in medical domain knowledge and the factual correctness of the report. |
| Outcome: | The proposed method can improve human preference scores and perform better on downstream tasks. |
BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval (2023.acl-long)
Copied to clipboard
| Challenge: | Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets. |
| Approach: | They propose a method to capture matching signal to improve generalization of dense retrieval by capturing matching signal between two texts. |
| Outcome: | The proposed method can be combined with different training methods to improve generalization ability without additional inference overhead and target domain data. |
Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs. |
| Approach: | They propose a framework with three modules designed to assess diversity, redundancy, and difficulty. |
| Outcome: | The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs. |
Making Pre-trained Language Models Better Continual Few-Shot Relation Extractors (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to learn new relations with limited labeled data are prone to catastrophic forgetting and overfitting. |
| Approach: | They propose a framework that uses prompts to acquire more generalized knowledge . they propose CFRE to continuously learn new relations while retaining knowledge of old ones . |
| Outcome: | The proposed method outperforms state-of-the-art methods by a large margin and significantly mitigates catastrophic forgetting and overfitting in low-resource scenarios. |
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models (2025.acl-long)
Copied to clipboard
Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng
| Challenge: | Existing approaches to tool learning rely on hand-crafted prompts and natural language reasoning, making multi-step planning difficult and lacking precise error diagnosis and reflection mechanisms. |
| Approach: | They propose a framework that reformulates tool learning as a code generation task. |
| Outcome: | The proposed framework achieves superior performance in task completion accuracy and execution reliability compared to existing approaches. |
Logic-Thinker: Teaching Large Language Models to Think more Logically. (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent Large Reasoning Models (LRMs) have demonstrated the ability to generate long chains of thought (LongCoT) LongCoT still faces challenges such as redundancy and logical incoherence. |
| Approach: | They propose a neural-symbolic reasoning framework that generates chains of thought . they propose Logic-Thinker, which transforms symbolic solvers into chains of thoughts . |
| Outcome: | The proposed framework outperforms models fine-tuned with ThinkerCoT on logic reasoning tasks. |
Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that LLMs face challenges in effectively using retrieved information . authors propose a method that considers LLM as "Information Refiner" |
| Approach: | They propose a method that considers LLMs as "Information Refiners" they propose INFO-RAG, which is low-cost and general across various tasks . |
| Outcome: | The proposed method improves performance of LLaMA2 by 9.39% relative points . it is low-cost and general across various tasks, and is robust and in-context learning is possible . |
TamEdit: Trajectory-Aware Meta-Learning for Specificity-Preserving Continual Knowledge Editing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for continual knowledge editing focus on single edits or preventing knowledge forgetting. |
| Approach: | They propose a meta-learning method that preserves specificity for continual knowledge editing by capturing relationships between different single edits within the trajectory. |
| Outcome: | Experiments show that TamEdit outperforms baselines in continual editing while preserving general capabilities. |
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing research on building ES conversation systems only considered single-turn interactions with users, which is over-simplified and has limited support for multi-turn systems. |
| Approach: | They propose a multi-turn ES conversation system that uses lookahead heuristics to estimate future user feedback after using particular strategies. |
| Outcome: | The proposed system significantly outperforms baselines in both dialogue generation and strategy planning. |
Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task (2022.coling-1)
Copied to clipboard
Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin
| Challenge: | Existing answer selection approaches for community question answering lack additional answer summaries due to redundancy and lengthiness issues of crowdsourced answers. |
| Approach: | They constructed a dataset which contains a corresponding reference summary for each original lengthy answer. |
| Outcome: | The proposed model improves the performance of a question and candidate answer on a WikiHowQA dataset. |
Qsnail: A Questionnaire Dataset for Sequential Question Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Questionnaires are a professional research methodology used for qualitative and quantitative analysis of human opinions, preferences, and behaviors. |
| Approach: | They propose a questionnaire-based dataset that consists of 13,168 human-written questionnaires. |
| Outcome: | The proposed dataset contains 13,168 human-written questionnaires gathered from online platforms. |
ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation (P19-1)
Copied to clipboard
| Challenge: | Existing hierarchical recurrent encoder-decoder models treat all contexts indiscriminately, which may hurt the following response generation process. |
| Approach: | They propose a hierarchical recurrent encoder-decoder model that treats all contexts indiscriminately and uses a word level LSTM encoder to obtain the initial representation of each context. |
| Outcome: | The proposed model outperforms baseline models on Chinese customer services and English Ubuntu dialogue datasets in terms of both metric-based and human evaluations. |
M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)
Copied to clipboard
Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu
| Challenge: | Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains. |
| Approach: | They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs. |
| Outcome: | The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods. |
S2LPP: Small-to-Large Prompt Prediction across LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a small model can be used to select effective prompt templates for a larger model. |
| Approach: | They propose a method to use a smaller model to select effective prompt templates for a larger model. |
| Outcome: | The proposed method significantly reduces the cost of prompt engineering while matching performance with optimal prompts among candidates. |
Explicit Inductive Inference using Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) suffer a signifi- cant performance drop when entailment labels disagree with the attestation label of hypothesis H. |
| Approach: | They propose a pipeline that exploits an LLM's attestation bias to do explicit inductive inference . they transform a premise into attested alternatives and aggregate the results . |
| Outcome: | The proposed pipeline improves the performance of large language models on inference tasks and alleviates the attestation bias. |
Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to extract entities from visually-rich documents ignore the inherent multimodality of VRDs and thus the suboptimal results are achieved. |
| Approach: | They propose a multimodal semantic enhancement method that filters redundant information in the current document and a cross-document information awareness technique to enrich the entity-related context. |
| Outcome: | The proposed method outperforms existing methods on two documents understanding benchmarks covering eight languages. |
Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Gradient-based explanation methods are increasingly used to interpret neural models in natural language processing (NLP) however, in the context of Aspect-based Sentiment Analysis, only specific dimensions are pertinent. |
| Approach: | They propose a Gradient-based explanation framework that leverages an information bottleneck to refine word embeddings into a concise intrinsic dimension, maintaining essential features and omitting unrelated information. |
| Outcome: | The proposed framework improves both the models’ performance and explanations’ clarity by identifying sentiment-aware features. |
G-Cap: A Game Character Caption Generator (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on Large Vision-Language Models (LVLMs) primarily focus on real-world scenarios, leaving surreal, highly stylized, and semantically hybrid virtual-world situations significantly underexplored. |
| Approach: | They propose to use a manually annotated benchmark to evaluate LVLMs' ability to perceive and describe game character from the virtual-world. |
| Outcome: | The proposed task evaluates LVLMs’ ability to perceive and describe game character from the virtual-world. |
Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are difficult to interpret due to their black-box nature and randomness. |
| Approach: | They propose a new method which enhances influence functions by addressing fitting errors by eliminating knowledge bias present in the base model before fine-tuning. |
| Outcome: | The proposed method outperforms existing methods and achieves an average AUC of 91.64%. |
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to large vision-language models fail to capture interleaved nature of human visual-verbal reasoning processes. |
| Approach: | They propose a framework that integrates visuospatial and linguistic domains to facilitate multimodal slow thinking by enabling progressive visual-textual reasoning. |
| Outcome: | Experiments show that VisuoThink significantly improves reasoning capabilities even without fine-tuning. |
Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation (2025.coling-main)
Copied to clipboard
| Challenge: | LLMs are used to emulate sequential decision-making processes of humans . however, their ability to perform probabilistic sampling is limited . |
| Approach: | They propose to use large language models (LLMs) as agents to emulate the sequential decision-making processes of humans represented as Markov decision-makers (MDPs). |
| Outcome: | The proposed models can understand probabilities, but struggle with sampling precision . integrating coding tools can improve sampling precision, but this level of sampling precision still makes it difficult to simulate human behavior as agents. |
PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling (2024.acl-long)
Copied to clipboard
| Challenge: | Spoken language understanding (SLU) suffers from error propagation from automatic speech recognition (ASR) in actual scenarios. |
| Approach: | They propose a framework which calibrates bias and errors and achieves adaptive-balanced decoupling training by a prototype-based loss model. |
| Outcome: | The proposed framework outperforms existing approaches and achieves state-of-the-art performance on three datasets. |
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)
Copied to clipboard
Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu
| Challenge: | Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning. |
| Approach: | They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs. |
| Outcome: | The proposed benchmarks demonstrate the stability of the proposed system and its caching system. |
Open-ended Commonsense Reasoning with Unrestricted Answer Candidates (2023.findings-emnlp)
Copied to clipboard
Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Mika Oishi, Takao Osaki, Katsushi Matsuda, Haifeng Chen, Liang Zhao
| Challenge: | Current approaches to commonsense reasoning are limited due to limited answer scope. |
| Approach: | They propose to solve a commonsense question without a pre-defined answer scope . they leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base . |
| Outcome: | The proposed method achieves better performance on two commonsense benchmark datasets. |
LLMDet: A Third Party Large Language Models Generated Text Detection Tool (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing detection tools rely on access to LLMs and can only distinguish between machine-generated and human-authored text. |
| Approach: | They propose a model-specific, secure, efficient, and extendable detection tool that can source text from specific LLMs. |
| Outcome: | The proposed tool can source text from specific LLMs, such as GPT-2, OPT, LLaMA, and others. |
MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multi-aspect controllable text generation require expensive iteration / searching within the discrete text space during the decoding stage, resulting in a degradation of text quality due to the domain discrepancies between different aspects. |
| Approach: | They propose a framework that estimates compact latent space for multiple aspects and performs efficient Sampling with a fast sampler to eliminate domain discrepancies. |
| Outcome: | The proposed framework outperforms baselines on attribute relevance and textual quality while maintaining a high inference speed. |
SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing work on large-scale corpora-based language models is limited and hard to generalize to all types of pre-trained language models. |
| Approach: | They propose a two-stage SimOAP strategy that over-samples and post-evaluates large-scale responses from existing models and selects a good response based on multiple evaluation metrics. |
| Outcome: | The proposed strategy outperforms baseline and automatic evaluation strategies in both automatic and human evaluations. |
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification (2026.acl-long)
Copied to clipboard
Zenghao Duan, Zhiyi Yin, Zhichao Shi, Liang Pang, Shaoling Jing, Zihe Huang, Jiayi Wu, Yu Yan, Jingcheng Deng, Huawei Shen, Xueqi Cheng
| Challenge: | Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content. |
| Approach: | They propose a method that removes toxic subspaces from FFN parameters . they propose to use a lightweight method to eliminate toxic subespaces . |
| Outcome: | The proposed method achieves SOTA detoxification while preserving general capabilities without large-scale retraining. |
OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs (2024.findings-emnlp)
Copied to clipboard
Jintian Zhang, Cheng Peng, Mengshu Sun, Xiang Chen, Lei Liang, Zhiqiang Zhang, Jun Zhou, Huajun Chen, Ningyu Zhang
| Challenge: | Recent advances in Large Language Models (LLMs) have significantly enhanced the generative capabilities for various NLP tasks, but they still suffer from hallucinations due to their exclusive reliance on parametric knowledge. |
| Approach: | They propose a framework that integrates retrieval tokens generated autoregressively into a single LLM to handle both tasks simultaneously in a unified forward pass. |
| Outcome: | The proposed framework bridges the traditionally separate training approaches for generation and retrieval by incorporating retrieval tokens generated autoregressively. |
Beyond Language: Learning Commonsense from Images for Reasoning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing commonsense reasoning methods use raw texts to perform data representation and answer prediction tasks. |
| Approach: | They propose a novel approach to learn commonsense from images instead of limited raw texts or costly knowledge bases. |
| Outcome: | The proposed approach outperforms language-based methods on commonsense reasoning problems on two commonsence reasoning problems. |
CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers? (2025.findings-emnlp)
Copied to clipboard
Jiefu Ou, William Gantt Walden, Kate Sanders, Zhengping Jiang, Kaiser Sun, Jeffrey Cheng, William Jurayj, Miriam Wanner, Shaobo Liang, Candice Morgan, Seunghoon Han, Weiqi Wang, Chandler May, Hannah Recknor, Daniel Khashabi, Benjamin Van Durme
| Challenge: | CLAIMCHECK is an annotated dataset of NeurIPS 2023 and 2024 submissions and reviews from OpenReview. |
| Approach: | They annotate NeurIPS 2023 and 2024 submissions and reviews for weaknesses and dispute them for fine-grained labels of validity, objectivity, and type of the identified weaknesses. |
| Outcome: | The proposed dataset is richly annotated by ML experts for weaknesses statements in the reviews and the claims that they dispute, as well as fine-grained labels of validity, objectivity, and type of the identified weaknesses. |
Uncertainty Quantification for In-Context Learning of Large Language Models (2024.naacl-long)
Copied to clipboard
Chen Ling, Xujiang Zhao, Xuchao Zhang, Wei Cheng, Yanchi Liu, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Jie Ji, Guangji Bai, Liang Zhao, Haifeng Chen
| Challenge: | Existing studies on in-context learning have focused on quantifying the uncertainty associated with the model's response, but they neglect the complexity of the LLM and the uniqueness of in-constitut learning. |
| Approach: | They propose a method to quantify the uncertainty associated with in-context learning and propose corresponding estimation method to quantify both types of uncertainties. |
| Outcome: | The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion. |
On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning (2026.acl-long)
Copied to clipboard
Changyu Liu, Yiyang Liu, Taowen Wang, Qiao Zhuang, James Chenhao Liang, Wenhao Yang, Renjing Xu, Qifan Wang, Dongfang Liu, Cheng Han
| Challenge: | Existing vision-language-action models are unsuitable for simulated or physical-world deployments . current methods fail when confronted with inherent real-world dynamic variability. |
| Approach: | They propose a test-time reinforcement learning framework that enables on-the-fly policy adaptation during inference. |
| Outcome: | Empirical results show that the proposed framework improves adaptability, stability and task success in dynamic, previously unseen scenarios. |
A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning (2026.acl-long)
Copied to clipboard
Tianyu Yang, Sihong Wu, Yilun Zhao, Zhenwen Liang, Lisen Dai, Chen Zhao, Minhao Cheng, Arman Cohan, Xiangliang Zhang
| Challenge: | Multimodal mathematical Reasoning (MMR) has attracted increasing attention for its ability to solve mathematical problems involving both textual and visual modalities. |
| Approach: | They review the theoretical frameworks of multimodal reasoning and examine the challenges they face in visual math tasks. |
| Outcome: | The proposed models can solve problems involving both textual and visual modalities. |
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)
Copied to clipboard
Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng
| Challenge: | Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome . |
| Approach: | They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens. |
| Outcome: | The proposed method reduces token usage by up to 44% while preserving accuracy. |
Adaptive Information Seeking for Open-Domain Question Answering (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing iterative approaches to open-domain question answering use predefined strategies . e.g., BM25, DPR, and hyperlink are defined as actions . |
| Approach: | They propose a novel adaptive information-seeking strategy for open-domain question answering . they propose to use a partially observed Markov decision process to select a proper retrieval action . |
| Outcome: | Experiments on SQuAD Open and HotpotQA fullwiki show that AISO outperforms baseline methods with predefined strategies in retrieval and answer evaluations. |
MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)
Copied to clipboard
Siwei Wu, King Zhu, Yu Bai, Yiming Liang, Yizhi Li, Haoning Wu, Jiaheng Liu, Ruibo Liu, Xingwei Qu, Xuxin Cheng, Ge Zhang, Wenhao Huang, Chenghua Lin
| Challenge: | Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images. |
| Approach: | They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs. |
| Outcome: | The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks. |
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment (2025.emnlp-main)
Copied to clipboard
Jingcheng Deng, Zhongtao Jiang, Liang Pang, Zihao Wei, Liwei Chen, Kun Xu, Yang Song, Huawei Shen, Xueqi Cheng
| Challenge: | Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches when using the same amount of data. |
| Approach: | They propose a new contrastive learning method built on embedding conditional probability distributions that integrates two tasks: information compression and conditional distribution alignment. |
| Outcome: | The proposed method outperforms traditional contrastive learning approaches and achieves comparable performance to state-of-the-art models when using the same amount of data. |
Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System (P19-3)
Copied to clipboard
Guo Zhipeng, Xiaoyuan Yi, Maosong Sun, Wenhao Li, Cheng Yang, Jiannan Liang, Huimin Chen, Yuhui Zhang, Ruoyu Li
| Challenge: | Existing systems for automatic poetry generation are model-oriented, resulting in poor user participation. |
| Approach: | They propose a human-machine collaborative Chinese classical poetry generation system called Jiuge . Jiuge allows users to revise unsatisfied parts of a generated poem draft repeatedly . |
| Outcome: | The proposed system allows users to revise unsatisfied parts of a generated poem draft repeatedly. |
Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data (2025.naacl-long)
Copied to clipboard
Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, Kenji Kawaguchi
| Challenge: | Contrastive Language-Image Pre-training (CLIP) is a standard for cross-modal image-text representation learning. |
| Approach: | They propose a framework that enhances pre-trained CLIP models by exploiting challenging text-image pairs within existing datasets. |
| Outcome: | The proposed framework improves CLIP models by exploiting text-image pairs in training. |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)
Copied to clipboard
Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive. |
| Approach: | They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory . |
| Outcome: | The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient. |
Plot Retrieval as an Assessment of Abstract Semantic Association (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing information retrieval datasets cannot capture abstract semantic associations well. |
| Approach: | They propose a task that retrieves relevant plots from the book for a query using a labeled dataset. |
| Outcome: | The proposed task can be used to evaluate the performance of IR models on the novel task Plot Retrieval. |
Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers (2024.acl-long)
Copied to clipboard
| Challenge: | Existing transformer-based models struggle with long-sequence processing due to computational costs . a framework to enhance long-content processing of transformers is proposed . |
| Approach: | They propose a framework to enhance long-sequence processing of transformers by three steps . they demonstrate that the framework significantly outperforms prior long-quence processors . |
| Outcome: | The proposed framework outperforms baseline models on long-sequence summarization and reading comprehension tasks. |
Contrastive Demonstration Tuning for Pre-trained Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies focus on searching discrete or continuous prompts or optimized verbalizers, yet the demonstration examples are crucial for an excellent final performance of prompt-tuning. |
| Approach: | They propose a pluggable, extensible, and efficient approach to prompt tuning that is free of demonstration sampling. |
| Outcome: | The proposed approach can be pluggable, extensible, and efficient on 16 datasets. |
RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on retrieval-augmented language models has two main problems: determining what information to retrieve and effectively combining retrieved information during generation. |
| Approach: | They propose a retrieval-augmented language model that captures current and future information from source and target text into a latent space. |
| Outcome: | The proposed model is more efficient than explicit raw text, but limited by context length and noise. |