Papers by Hu Zhang
Towards Reward Fairness in RLHF: From a Resource Allocation Perspective (2025.acl-long)
Copied to clipboard
| Challenge: | if rewards are imperfect, they can adversely affect the alignment of large language models (LLMs). |
| Approach: | They propose a bias-agnostic method to address the issue of reward unfairness from a resource allocation perspective without specifically designing for each type of bias . they apply methods Fairness Regularization and Fairness Coefficient to achieve fairness in rewards. |
| Outcome: | The proposed method achieves fairness in rewards while minimizing biases . it can be applied to verification and reinforcement learning scenarios . |
MIBench: Evaluating Multimodal Large Language Models over Multiple Images (2024.emnlp-main)
Copied to clipboard
Haowei Liu, Xi Zhang, Haiyang Xu, Yaya Shi, Chaoya Jiang, Ming Yan, Ji Zhang, Fei Huang, Chunfeng Yuan, Bing Li, Weiming Hu
| Challenge: | Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored. |
| Approach: | They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios. |
| Outcome: | The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC. |
PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Speculative decoding is limited by sequential stage dependencies that prevent full hardware utilization. |
| Approach: | They propose a framework that generalizes speculative decoding to use multiple models arranged in a hierarchical pipeline and enables asynchronous execution with lightweight coordination for prediction verification and rollback. |
| Outcome: | The proposed framework achieves 2.25 tokens/unit through pipelined parallelism with multiple models arranged in a hierarchical pipeline. |
Towards Faithful Dialogues via Focus Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge-grounded models rely on elaborate data engineering or increasing the model’s parameters ignoring to track the tokens that significantly influence losses, which is decisive for the optimization direction of the model in each iteration. |
| Approach: | They propose a novel learning approach that adjusts the contribution of each token to the optimization direction by directly scaling the corresponding objective loss. |
| Outcome: | The proposed approach achieves the new state-of-the-art results and generates more reliable responses while maintaining training stability. |
Multiview Clickbait Detection via Jointly Modeling Subjective and Objective Preference (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing clickbait detection models rely on analyzing the objective semantics of posts or correlating posts with article content only, but fail to identify and exploit the manipulation intention of clickbaiting from a user’s subjective perspective. |
| Approach: | They propose a multiview clickbait detection model to model subjective and objective preferences simultaneously to capture clickbaiting from a user's subjective perspective. |
| Outcome: | The proposed model outperforms state-of-the-art models on two real-world datasets and shows that it integrates subjective and objective preferences simultaneously. |
SP3: Enhancing Structured Pruning via PCA Projection (2024.findings-acl)
Copied to clipboard
| Challenge: | Structured pruning is a widely used technique for reducing the size of pre-trained language models, but current methods overlook the potential of compressing the hidden dimension d in PLMs. |
| Approach: | They propose a structured pruning approach that projectes features into a space defined by principal components before masking the hidden dimension d in pre-trained language models. |
| Outcome: | Experiments on benchmarks show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy. |
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have shown that large language models implicitly embed reasoning trees, but their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. |
| Approach: | They propose to use circuit analysis and self-influence functions to map the reasoning process of large models. |
| Outcome: | The proposed model is able to map human-interpretable reasoning paths and a model's underlying circuits reveal human-mediated reasoning processes. |
R2A-TLS: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Integration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods struggle to capture coherent event narratives due to fragmented descriptions . Existing approaches accumulate noise through iterative retrieval strategies that lack relevance evaluation. |
| Approach: | They propose a reflective retrieval-augmented timeline summarization with Causal-Semantic Intergration approach for open-domain timeline summarizing . |
| Outcome: | The proposed approach outperforms the best prior published approaches. |
VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)
Copied to clipboard
Shuliang Liu, Zheng Qi, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu
| Challenge: | Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable. |
| Approach: | They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns . |
| Outcome: | The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC). |
From Selection to Refinement: Iterative Optimization for Instruction Data (2026.acl-long)
Copied to clipboard
Hang Hu, Ziyan Liu, Rujie Wen, Ruihui Hou, Xueyan Wu, Mu Zhang, Jianxing Yu, Tong Ruan, Jingping Liu
| Challenge: | Existing methods to optimize instruction tuning datasets face two main challenges: unreasonable pruning of potentially valuable low-quality data and the persistence of noise or semantic drift during revision. |
| Approach: | They propose an automated iterative framework for instruction data optimization that prunes low-quality data and refines low quality data using feedback-driven iteration. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on seven public benchmark datasets with high data efficiency. |
SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use heuristics or distant-supervised annotations, but distant supervised methods make strong assumptions on entity cooccurrence without sufficient contexts. |
| Approach: | They propose a framework that exploits weak, self-supervised signals by leveraging large pretrained language models for adaptive clustering on contextualized relational features. |
| Outcome: | The proposed framework exploits weak, self-supervised signals on open-domain Relation Extraction . it bootstraps the self-supervised signals by improving contextualized features in relation classification . |
Multiscale Collaborative Deep Models for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural machine translation models with deeper neural networks are difficult to train. |
| Approach: | They propose a MultiScale Collaborative framework to boost gradient back-propagation . they let each encoder block learn a fine-grained representation and enhance it . |
| Outcome: | The proposed framework outperforms baseline models on translation tasks with three translation directions and achieves a BLEU score of 30.56 on the English-to-German task. |
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)
Copied to clipboard
Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap . |
| Approach: | They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models. |
| Outcome: | The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting . |
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for embedding binary messages into LLM-generated text suffer from key limitations, such as a poor trade-off between text quality and decoding accuracy. |
| Approach: | They propose a method for embedding binary messages into Large Language Model (LLM)-generated text that uses a limited number of tokens to decode and recover the encoded message. |
| Outcome: | The proposed method significantly outperforms existing methods in multiple downstream tasks and will be made publicly available upon acceptance. |
PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions (2025.findings-emnlp)
Copied to clipboard
Song Dai, Yibo Yan, Jiamin Su, Zihao Dongfang, Yubo Gao, Yonghua Hei, Jungang Li, Junyan Zhang, Sicheng Tao, Zhuoran Gao, Xuming Hu
| Challenge: | Current physics benchmarks focus on text-only inputs or only on problem-solving . current physics reasoning benchmarks neglect critical intermediate steps of variable identification and process formulation. |
| Approach: | a new benchmark evaluates multimodal large language models in physics reasoning . the benchmark measures variables, process formulations, and solution derivation . |
| Outcome: | PhysicsArena is the first multimodal physics reasoning benchmark . it evaluates MLLMs across three critical dimensions: variable identification, process formulation, and solution derivation. |
TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for political user-level stance detection rely on noisy heuristics or distant supervision. |
| Approach: | They propose a large-scale, expert-annotated benchmark for political user-level stance detection with explicit social network structure that integrates user content and followee signals. |
| Outcome: | The proposed framework outperforms baselines in terms of quality and reliability. |
Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches focus on improving attack success rates while overlooking the need for comprehensive test case coverage. |
| Approach: | They propose a top-down approach to automated red teaming that scales up the diversity of test cases using an extensible, fine-grained risk taxonomy. |
| Outcome: | The proposed approach scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy and leverages reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner. |
Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts (2026.acl-long)
Copied to clipboard
Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang, Ke Wang, Jinbo Su, Mengshu Sun, Lei Liang, Jing Zhang
| Challenge: | Existing methods for storing key-value caches during long-horizon rollouts cause performance collapses. |
| Approach: | They propose a new training paradigm that empowers stable RL training under sparse rollouts. |
| Outcome: | The proposed model reduces rollout overhead while maintaining the performance. |
Learning to Represent Image and Text with Denotation Graph (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in learning representations of visual and language information have been a problem with many applications. |
| Approach: | They propose to extract visual expressions from images aligned with linguistic expressions that describe the images to learn representations from implicit expressions. |
| Outcome: | The proposed representations lead to stronger empirical results on downstream tasks of cross-modal image retrieval, referring expression, and compositional attribute-object recognition. |
Personalized Generation In Large Model Era: A Survey (2025.acl-long)
Copied to clipboard
Yiyan Xu, Jinghao Zhang, Alireza Salemi, Xinting Hu, Wenjie Wang, Fuli Feng, Hamed Zamani, Xiangnan He, Tat-Seng Chua
| Challenge: | Recent advances in large generative models have catalyzed a paradigm shift in content generation to Personalized Generation (PGen). |
| Approach: | They propose a multi-level taxonomy that systematically formalizes PGen's key components, core objectives, and abstract workflows. |
| Outcome: | The proposed taxonomy bridging PGen research across multiple modalities highlights open challenges and promising directions for future exploration. |
Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning (2021.acl-long)
Copied to clipboard
| Challenge: | Existing single-hop graph reasoning in Graph convolutional networks may miss some important non-consecutive dependencies. |
| Approach: | They propose a graph convolutional network with the high-order dynamic Chebyshev approximation which augments multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutionalist layer. |
| Outcome: | The proposed model improves on four transductive and inductive NLP tasks and the ablation of the existing model. |
Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Recent Large Multimodal Models (LMMs) focus on visual knowledge-dimension alignment, but ignore visual knowledge. |
| Approach: | They propose a cognitive visual-language mapper that integrates visual-linguistic knowledge alignment with a fine-grained knowledge Adapter. |
| Outcome: | The proposed model significantly improves LMMs on knowledge-based visual question answering (VQA) it also improves the performance of other models, including GPT-4V and Gemini-Pro. |
Rethinking Machine Ethics – Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to making moral judgments are mostly bottom-up and lack explainability. |
| Approach: | They propose a top-down framework to steer Large Language Models to perform moral reasoning with well-established moral theories. |
| Outcome: | The proposed framework can integrate various moral theories on moral datasets. |
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs (2026.acl-long)
Copied to clipboard
Zhenyu Liu, Xuanyu Zhang, Yunxin li, Qixun Teng, Shenyuan Jiang, Haolan Chen, Mingjun Zhao, Fanbo Meng, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang
| Challenge: | despite significant progress, full-duplex SLMs are constrained by severe modality interference, authors say . modality interferes with acoustic and semantic modeling, making them unintelligent and unnatural . authors propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers . |
| Approach: | They propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel. |
| Outcome: | The proposed method significantly advances the state of the art on full-duplex benchmarks . it decouples conflicting modalities in deep layers while preserving cross-modality coherence . |
Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)
Copied to clipboard
Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu
| Challenge: | closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges . |
| Approach: | They propose a framework that leverages collective intelligence from all large language models to evaluate each other. |
| Outcome: | a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost. |
An AMR-based Link Prediction Approach for Document-level Event Argument Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work has introduced Abstract Meaning Representation (AMR) for Document-level Event Argument Extraction (Doc-level EAE) however, in these works AMR is used only implicitly, for instance, as additional features or training signals. |
| Approach: | They propose a novel AMR-based graph structure which uses graph neural networks to find event arguments from unstructured text. |
| Outcome: | The proposed graph structure outperforms the state-of-the-art models by 3.63pt and 2.33pt F1 and reduces inference time by 56%. |
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG (2025.findings-naacl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) is widely adopted in Large Language Models, but is flat and has limitations such as a significant burden on one retriever and constant granularity limits the ceiling of retrieval performance. |
| Approach: | They propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency. |
| Outcome: | The proposed paradigm achieves comparable retrieval performance while the time overhead is reduced by nearly 40%. |
Native Hybrid Attention for Efficient Sequence Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that NHA surpasses Transformers on recall-intensive tasks. |
| Approach: | They propose a hybrid architecture of linear and full attention that integrates both into a unified layer design. |
| Outcome: | The proposed architecture surpasses Transformers and other hybrid baselines on recall-intensive and commonsense reasoning tasks. |
G-LoRA: Global-Local Decoupled Low-Rank Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) improves the fine-tuning efficiency and performance of large language models. |
| Approach: | They propose a low-rank adaptive approach that decomposes update matrix into global and local adapters and assigns them to local and global adapters. |
| Outcome: | The proposed method achieves up to 2.7% accuracy improvement over LoRA and its variants on commonsense reasoning, mathematical reasoning, and code generation. |
HiCLRE: A Hierarchical Contrastive Learning Framework for Distantly Supervised Relation Extraction (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches of distantly supervised relation extraction (DSRE) focus on sentence-level or bag-level de-noising, neglecting the explicit interaction with cross levels. |
| Approach: | They propose a hierarchical contrastive learning framework for distantly supervised relation extraction to reduce noisy sentences. |
| Outcome: | The proposed framework outperforms baselines in various mainstream DSRE datasets. |
Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to cross-document event coreference resolution are prone to learning simple co-occurrences due to the complexity of contexts. |
| Approach: | They propose a collaborative approach to cross-document event coreference resolution that leverages both a universally capable LLM and a task-specific SLM. |
| Outcome: | The proposed approach surpasses the performance of both large and small language models individually, underscoring its effectiveness in diverse scenarios. |
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)
Copied to clipboard
Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang
| Challenge: | PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks. |
| Approach: | They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks. |
| Outcome: | The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods. |
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)
Copied to clipboard
Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs . |
| Approach: | They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker. |
| Outcome: | The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics. |
TensorOpera Router: A Multi-Model Router for Efficient LLM Inference (2024.emnlp-industry)
Copied to clipboard
Dimitris Stripelis, Zhaozhuo Xu, Zijian Hu, Alay Shah, Han Jin, Yuhang Yao, Jipeng Zhang, Tong Zhang, Salman Avestimehr, Chaoyang He
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable performance across a diverse set of domain-specific tasks. |
| Approach: | They propose a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query’s requirements. |
| Outcome: | The proposed model improves query efficiency by 40% and costs by 30% while maintaining or enhancing model performance by 10%. |
Cardiverse: Harnessing LLMs for Novel Card Game Prototyping (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have enhanced the possibilities for game prototyping, but they face significant challenges. |
| Approach: | They propose a graph-based indexing method for generating novel game variations and an LLM-driven system for consistent game code generation validated by gameplay records. |
| Outcome: | The proposed framework accelerates card game prototyping, reduces human labor, and lowers barriers to entry for game developers. |
Complex Numerical Reasoning with Numerical Semantic Pre-training Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Numerical knowledge graphs (NKGs) are not limited to discrete entity-relation knowledge. |
| Approach: | They propose to combine numerical values and entities to solve multi-hop complex reasoning over incomplete knowledge graphs. |
| Outcome: | The proposed approach handles up to 102 types of complex numerical reasoning queries on three public datasets. |
ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing quality filtering methods rely on a high-quality dataset as reference . Existing methods introduce potential biases and compromise diversity . |
| Approach: | They propose a method that evaluates text quality based on the perplexity difference between two language models trained on the same data. |
| Outcome: | The proposed approach improves performance of pre-trained models without increasing training costs. |
A State-transition Framework to Answer Complex Questions over Knowledge Base (D18-1)
Copied to clipboard
| Challenge: | Existing methods for complex question answering have some limitations . existing methods employ predefined patterns or templates to understand complex questions. |
| Approach: | They propose a state transition-based approach to translate a natural language question to a semantic query graph. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on several benchmarks with two knowledge bases. |
Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective (2026.findings-acl)
Copied to clipboard
| Challenge: | Reasoning-tuned large language models (LLMs) with long Chain-of-Thought excel at single-answer tasks, yet their ability to model Human Label Variation remains underexplored. |
| Approach: | They conduct systematic disentanglement experiments to isolate the effect of reasoning text from intrinsic model priors on distribution-based tasks. |
| Outcome: | The proposed model improves distributional alignment, but distributional ranking is governed by model priors. |
REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for reproducing social science papers focus on reproducing results using provided code and data without assessing their consistency with the paper. |
| Approach: | They propose a benchmark to evaluate agentic AI systems' ability to automate reproducibility assessment. |
| Outcome: | The proposed benchmark oversimplifies real-world scenarios and lacks diversity in data formats and programming languages. |
Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction (2024.lrec-main)
Copied to clipboard
| Challenge: | Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts. |
| Approach: | They propose a framework that incorporates uncertainty into feature learning and correction stages . they propose to combine the uncertainty of multimodal features with model learning . |
| Outcome: | The proposed framework improves on three public datasets. |
Refining Source Representations with Relation Networks for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Existing neural machine translation frameworks that forget distant information and disregard relationship between source and target words are not effective. |
| Approach: | They propose to use relation networks to learn better representations of the source . they propose to associate source words with each other to help retain their relationships . |
| Outcome: | Experiments show that the proposed approach outperforms the encoder-decoder framework on several datasets. |
Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning (2025.findings-naacl)
Copied to clipboard
Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing decoding strategies for chain-of-thought reasoning do not exploit prior information about question difficulty. |
| Approach: | They propose a decoding strategy called self-consistency to improve reasoning performance by adjusting the number of samples based on the posterior distribution of a set of pre-samples. |
| Outcome: | The proposed method outperforms baseline methods on arithmetic, commonsense and symbolic reasoning tasks while achieving comparable performance. |
Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that using external knowledge such as pre-trained word embeddings or pre-train language models only achieved limited performance improvements but with huge computational overhead. |
| Approach: | They propose to incorporate external knowledge into neural topic modeling by pre-trained word embeddings (PWEs) or pre-train language models (PLMs) they propose to fine-tune the neural topic model on the target dataset and reduce the huge size of training data. |
| Outcome: | The proposed approach outperforms current state-of-the-art neural topic models and some topic modeling approaches enhanced with PWEs or PLMs on three datasets and greatly reduces the huge size of training data. |
E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition (2023.findings-acl)
Copied to clipboard
Zhen Zhang, Mengting Hu, Shiwan Zhao, Minlie Huang, Haotian Wang, Lemao Liu, Zhirui Zhang, Zhe Liu, Bingzhe Wu
| Challenge: | Named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty. |
| Approach: | They propose to introduce two uncertainty-guided loss terms to the conventional EDL and a series of uncertainty-guiding training strategies to solve these challenges. |
| Outcome: | The proposed method achieves better OOV/OOD detection performance and generalization ability on OOV entities compared to state-of-the-art methods. |
Revisiting Data Reconstruction Attacks on Real-world Dataset for Federated Natural Language Understanding (2024.lrec-main)
Copied to clipboard
Zhuo Zhang, Jintao Huang, Xiangjing Hu, Jingyuan Zhang, Yating Zhang, Hui Wang, Yue Yu, Qifan Wang, Lizhen Qu, Zenglin Xu
| Challenge: | Existing DRA methods fail to accurately recover the original text of real-world privacy data. |
| Approach: | They propose to use a real-world privacy dataset to examine the performance of federated learning (FL) methods. |
| Outcome: | The proposed method improves on a real-world privacy dataset and shows that the tokens within a recovery sentence are disordered and intertwined with tokens from other sentences in the same training batch. |
Optimizing Entity Resolution in Voice Interfaces: An ASR-Aware Entity Reference Expansion Approach (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Automatic Speech Recognition (ASR) errors in voice-based dialog systems pose significant impediments to downstream tasks. |
| Approach: | They propose an automatic speech recognition (ASR) error-aware loss function to inject failed mentions and resolved entity names into the knowledge graph to enhance its awareness of unresolved mentions. |
| Outcome: | The proposed system enhances the knowledge graph's awareness of unresolved mentions by injecting pairs of failed mentions and resolved entities into the knowledge map. |
Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | NLCO evaluates large language models for combinatorial optimization (CO) . existing evaluations emphasize relatively simple reasoning competencies . |
| Approach: | They propose a combinatorial optimization benchmark that evaluates large language models on CO reasoning. |
| Outcome: | The proposed model can handle combinatorial optimization without writing code or calling external solvers. |
Enhanced Data Synthesis for LLM through Reasoning Structures Generated by Hierarchical GFlowNet (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to optimize instruction-response pairs lack a systematic design for the underlying reasoning structure. |
| Approach: | They propose a Reasoning Structure driven data Synthesis method that leverages a coarse-to-fine directed acyclic graph to construct reasoning structures efficiently. |
| Outcome: | The proposed method outperforms existing methods in 48.50%, 84.00%, 79.90% of the synthetic datasets trained on the proposed model. |
DeFine: Decision-Making with Analogical Reasoning over Factor Profiles (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models are ideal for decision-making, but they can be difficult to process when they are verbose and include repetition, hedging, and vagueness. |
| Approach: | They propose a framework that constructs probabilistic factor profiles from complex scenarios and integrates them with analogical reasoning to guide LLMs in making decisions in new situations. |
| Outcome: | The proposed framework separates the tasks of quantifying uncertainty and incorporating it into LLM decision-making. |
CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior implicit CoT methods have underperformed in terms of efficiency and robustness by relying on natural language tokens for reasoning. |
| Approach: | They propose a training framework that compresses natural language CoT into continuous space by aligning hidden states of a designated token. |
| Outcome: | The proposed framework outperforms the existing state-of-the-art in 3.1x compression rate and 28.2% accuracy on GSM8k scale. |
How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior work on activation steering has focused on shaping reasoning traces, but it remains unclear how answer tokens actually read and integrate the reasoning to produce reliable outcomes. |
| Approach: | They propose a training-free steering method that uses self-reading quality scores to guide inference toward benign self-readiness and away from uncertain and disorganized reading. |
| Outcome: | The proposed method yields consistent accuracy gains in the reasoning traces generated by thinking LLMs. |
Towards the Law of Capacity Gap in Distilling Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Language model (LM) distillation aims at distilling knowledge in a large teacher LM to a small student one. |
| Approach: | They propose to use the law of capacity gap to distill knowledge from a large teacher to a small student model. |
| Outcome: | The proposed model outperforms other language models on a larger scale by using the law of capacity gap inducted from a preliminary study on small-scale (3B) LMs. |
Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning (2025.acl-long)
Copied to clipboard
Shaobo Wang, Xiangqi Jin, Ziming Wang, Jize Wang, Jiajun Zhang, Kaixin Li, Zichen Wen, Zhong Li, Conghui He, Xuming Hu, Linfeng Zhang
| Challenge: | Using fine-tuning on task-specific data is essential for large language models to be effective in specialized tasks. |
| Approach: | They propose a method that leverages few-shot in-context learning with the model to be fine-tuned. |
| Outcome: | The proposed method outperforms existing methods with a 3.1-point improvement and a 7.4 speedup on the Llama-3-8B-Instruct model using just 10% of the dataset. |
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots (2022.findings-acl)
Copied to clipboard
| Challenge: | Sub-Slot based task-oriented dialogs provide slot values segment by segment over multiple turns. |
| Approach: | They define a task called Sub-Slot based Task-Oriented Dialog (SSTOD) they build a Chinese dialog dataset SSD for boosting research on SSTOD. |
| Outcome: | The proposed task is called Sub-Slot based Task-Oriented Dialog (SSTOD) it includes 40K dialogs and 500K utterances from Chinese names, phone numbers, ID numbers and license plate numbers . the dataset is well annotated with sub-slot values, slot values, dialog states and actions . |
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking (2026.acl-long)
Copied to clipboard
Zechen Sun, Yuyang Sun, Zecheng Tang, Juntao Li, Wenpeng Hu, Wenliang Chen, Zhunchen Luo, Guotong Geng, Min Zhang
| Challenge: | Existing models with reasoning capabilities suffer from a severe length collapse in open-ended writing . |
| Approach: | They propose a framework that embeds a dynamic plan-write-reflect cycle into the generation process and train a model with interleaved reasoning traces. |
| Outcome: | The proposed framework achieves state-of-the-art performance on long-form benchmarks compared to other models on the same dataset. |
CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysis (D19-1)
Copied to clipboard
| Challenge: | Existing methods for aspect-specific sentiment classification are noisy and downgraded performance. |
| Approach: | They propose a constrained attention network to regularize attention for multi-aspect sentiment analysis by orthogonal regularization on multiple aspects and sparse regularization for each single aspect. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on two public datasets and extends to multi-task settings. |
Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)
Copied to clipboard
Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang
| Challenge: | Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data. |
| Approach: | They propose a framework that imposes strong typing constraints and incorporates key relationships from schema. |
| Outcome: | The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider. |
ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing explanation datasets for large language models are limited to the English language and general domain, leading to a scarcity of linguistic diversity and a lack of resources in specialized domains, such as medical. |
| Approach: | They propose to use a medical dataset to assess the interpretability of Large Language Models (LLMs) . they propose to analyze medical text and generate rationales for their decisions . |
| Outcome: | The proposed model passes the pharmacist examination with a 75.7% accuracy, while other models like ChatGPT fail. |
Youling: an AI-assisted Lyrics Creation System (2020.emnlp-demos)
Copied to clipboard
Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang
| Challenge: | Recent studies have focused on a single pass of lyrics generation with little human intervention. |
| Approach: | They propose an AI-assisted lyrics creation system that supports one pass full-text generation and interactive generation modes. |
| Outcome: | The proposed system supports full-text generation and interactive generation modes . it also provides a revision module which enables users to revise undesired lyrics repeatedly. |
A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for generating product descriptions from images are inaccurate and generic . e-commerce product descriptions are important for content marketing and increasing engagement . |
| Approach: | They propose a new setting for generating product descriptions from images, augmented by marketing keywords. |
| Outcome: | The proposed approach improves the accuracy and diversity of product descriptions by up to 3.3% on Rouge-L and 9.4% on D-5. |
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)
Copied to clipboard
Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen
| Challenge: | Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios. |
| Approach: | They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance. |
| Outcome: | The proposed framework improves model capabilities across all domains and scales. |
HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to extract relational feature signals from natural language sentences use self-supervised clustering and classification that cause gradual drift problems. |
| Approach: | They propose a framework that derives hierarchical signals from relational feature space using cross hierarchy attention and effectively optimizes relation representation of sentences under exemplar-wise contrastive learning. |
| Outcome: | The proposed framework can extract the relationship between entities from natural language sentences without prior knowledge on relation scope or distribution. |
Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)
Copied to clipboard
Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen
| Challenge: | Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval. |
| Approach: | They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs). |
| Outcome: | The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models. |
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing (2024.findings-acl)
Copied to clipboard
Jiaqi Li, Miaozeng Du, Chuanyi Zhang, Yongrui Chen, Nan Hu, Guilin Qi, Haiyun Jiang, Siyuan Cheng, Bozhong Tian
| Challenge: | Current benchmarks focus on coarse-grained knowledge, leaving the intricacies of fine-grounded knowledge unexplored. |
| Approach: | They propose a benchmark and dataset specifically designed for FG multimodal entity knowledge editing. |
| Outcome: | The proposed benchmark underscoring the complexity of FG knowledge editing in MLLMs. |
InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing image captioning metrics provide a single score to measure caption qualities, which are less explainable and informative. |
| Approach: | They propose an Informative Metric for Reference-free Image Caption evaluation to support this feedback . they propose to provide a text precision score, a vision recall score and an overall quality score . |
| Outcome: | The proposed method improves on existing metrics on multiple benchmarks and compares coarse-grained scores with human judgements. |
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)
Copied to clipboard
Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters. |
| Approach: | They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety. |
| Outcome: | The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings. |
E-VarM: Enhanced Variational Word Masks to Improve the Interpretability of Text Classification Models (2022.coling-1)
Copied to clipboard
Ling Ge, ChunMing Hu, Guanghui Ma, Junshuang Wu, Junfan Chen, JiHong Liu, Hong Zhang, Wenyi Qin, Richong Zhang
| Challenge: | Empirical studies show that our approach outperforms the SOTA methods in improving the interpretability of text classification models. |
| Approach: | They propose an enhanced variational word masks approach that exploits the Variational Information Bottleneck to obtain task-specific words. |
| Outcome: | Empirical results show that the proposed method outperforms the SOTA methods in improving the interpretability of the model. |
From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have shown impressive performance in various language tasks, but are prone to spurious correlations and illusory information. |
| Approach: | They propose to use pre-trained language models to justify decisions with formalized, coherent reasoning chains. |
| Outcome: | The proposed strategies improve coherence of rationalizations yielding state-of-the-art results on Tiered Reasoning for Intuitive Physics (TRIP). |
Semantic Reshuffling with LLM and Heterogeneous Graph Auto-Encoder for Enhanced Rumor Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Current methods struggle against complex propagation influenced by bots, coordinated accounts, and echo chambers, which fragment information and increase risks of misjudgments. |
| Approach: | They propose a framework that integrates metapath-based rumor reconstruction and narrative reordering to detect rumors. |
| Outcome: | The proposed model outperforms existing methods and is highly accurate and robust. |
Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)
Copied to clipboard
Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu
| Challenge: | Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole . |
| Approach: | They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task. |
| Outcome: | The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices. |
MCiteBench: A Multimodal Benchmark for Generating Text with Citations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work focuses on generating citations for text-only content . experimental results reveal MLLMs struggle to ground outputs reliably when handling multimodal input . |
| Approach: | They propose a benchmark to assess the ability of MLLMs to generate text with citations in multimodal contexts. |
| Outcome: | The proposed benchmark assesses the ability of MLLMs to generate text with citations in multimodal contexts. |
Exploring Model Kinship for Merging Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Model merging has become one of the key technologies for enhancing the capabilities and efficiency of Large Language Models. |
| Approach: | They propose a model merging strategy that incorporates model kinship to improve model performance. |
| Outcome: | The proposed model merging strategy can yield better performance on benchmark datasets. |
Multi-level Distillation of Semantic Knowledge for Pre-training Multilingual Language Model (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for improving multilingual models did not focus on learning the semantic structure of representation. |
| Approach: | They propose a method to improve multilingual language models by aligning parallel sentences . they propose token-, word-, sentence- and structure-level alignment objectives . |
| Outcome: | The proposed method outperforms baseline models on XNLI, PAWS-X, and XQuAD . it obtains comparable performance on low-resource languages, the authors show . |
R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms . |
| Approach: | They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding. |
| Outcome: | The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing. |
Tracing and Dissecting How LLMs Recall Factual Knowledge for Real World Questions (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have shown promising ability to perform commonsense reasoning. |
| Approach: | They propose a two-dimensional analysis framework that incorporates token back-tracing and token decoding to uncover how LLMs conduct factual knowledge recall. |
| Outcome: | The proposed framework shows that LLMs lack relevant knowledge but struggle to select the most accurate information based on context during the retrieval and rerank phase. |
SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have made great progress in text generation but suffer from hallucinations during reasoning and generation. |
| Approach: | They propose an inference-time method to help LLMs decode truthfully by selecting tokens with the lowest probabilities and concatenating them to the original context. |
| Outcome: | The proposed method improves LLaMA-7b, LLama2-7b and Mistral-7b on hallucination tasks. |
VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents (2026.findings-acl)
Copied to clipboard
Jiliang Hu, Wenfu Wang, Zuchao Li, Chenxing Li, Yiyang Zhao, Hanzhao Li, Liqiang Zhang, Meng Yu, Dong Yu
| Challenge: | despite advances in multimodal conversational systems, current benchmarks lack comprehensive evaluation across key dimensions. |
| Approach: | They propose a Chinese benchmark built exclusively on real human speech to fill this gap . they assess LALMs across three complementary axes: instruction following, knowledge understanding, robustness . |
| Outcome: | VCB Bench assesses LALMs across three complementary axes: instruction following, knowledge understanding, and robustness . VCBM Bench provides reproducible and fine-grained framework for Chinese voice chat bots . results show significant performance disparities and offer tangible insights for future improvements . |
Dynamic Energy-Based Contrastive Learning with Multi-Stage Knowledge Verification for Event Causality Identification (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for event causal identification rely on rule-based or random sampling strategies, which introduce spurious causal positives. |
| Approach: | They propose an ECI method enhanced by Dynamic Energy-based Contrastive Learning with multi-stage knowledge verification which generates high-quality contrastive samples and effectively suppresses spurious causal disturbances. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two benchmarks. |
Synergizing LLMs with Global Label Propagation for Multimodal Fake News Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can assist multimodal fake news detection by predicting pseudo labels, but their effective integration is non-trivial. |
| Approach: | They propose a global label propagation network with LLM-based pseudo labels for multimodal fake news detection which integrates LLM capabilities via label propagations. |
| Outcome: | The proposed model outperforms state-of-the-art models on benchmark datasets showing that it can propagate pseudo labels among all samples. |
RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing structured reasoning frameworks lack internal decision probability and cannot model the tree as a whole. |
| Approach: | They propose a Reinforcement Learning based Entailment Tree generation framework that is trained using the cumulative signals across the whole tree. |
| Outcome: | The proposed framework offers explicit deductions with entailment steps in a tree structure. |
Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models (2026.acl-long)
Copied to clipboard
Kai Hu, Abhinav Aggarwal, Mehran Khodabandeh, David Zhang, Eric Hsin, Li Chen, Ankit Jain, Matt Fredrikson, Akash Bharadwaj
| Challenge: | Existing approaches to red teaming are based on example-based evaluation, where a static list of specific prompts is used to define and measure "unsafe content" |
| Approach: | They propose a new automated red teaming framework that shifts from example-based to policy-based evaluation that focuses on risk coverage, semantic diversity, and fidelity. |
| Outcome: | The proposed method achieves superior, human-readable attacks against open-source and proprietary models even for unseen safety policies. |
GMFL: Efficient Global Masking for Federated LLM Fine-tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) has emerged as a prominent solution to mitigate the communication and computation costs in federated fine-tuning of Large Language Models (LLMs). |
| Approach: | They propose a plug-and-play layer freezing mechanism to integrate with existing federated fine-tuning frameworks. |
| Outcome: | The proposed solution reduces communication overhead and lowers computational costs while preserving the performance of the underlying federated fine-tuning methods. |
Hyperspherical Multi-Prototype with Optimal Transport for Event Argument Extraction (2024.acl-long)
Copied to clipboard
| Challenge: | Event Argument Extraction (EAE) aims to extract arguments for specified events from a text . previous work focused on long-distance dependencies of arguments, modeling co-occurrence relationships . |
| Approach: | They propose a model that takes inductive biases as targets to locate prototypes . they set multiple prototypes to represent each role to capture intra-class differences . |
| Outcome: | The proposed model achieves state-of-the-art on the RAMS and WikiEvents datasets. |
MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation (2025.acl-long)
Copied to clipboard
Haochen Xue, Feilong Tang, Ming Hu, Yexin Liu, Qidong Huang, Yulong Li, Chengzhi Liu, Zhongxing Xu, Chong Zhang, Chun-Mei Feng, Yutong Xie, Imran Razzak, Zongyuan Ge, Jionglong Su, Junjun He, Yu Qiao
| Challenge: | Existing multimodal large language models lack the ability to memorize, recall, and reason in sustained interactions. |
| Approach: | They propose a multimodal real-world conversation benchmark for evaluating open-ended abilities of multimodal large language models. |
| Outcome: | The proposed benchmarks show that the models perform better in open-ended conversations. |
Improving Data Annotation for Low-Resource Relation Extraction with Logical Rule-Augmented Collaborative Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Low-resource relation extraction aims to identify semantic relationships using scarce labeled data. |
| Approach: | They propose a framework that iteratively integrates high-confidence predictions of rule-enhanced relation extractors with varying scales to obtain reliable pseudo annotations from massive unlabeled samples without human supervision. |
| Outcome: | The proposed framework achieves state-of-the-art on benchmark datasets in few-shot scenarios. |
Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work has shown promise by incorporating pixel-level visual information into the reasoning process, enabling VLMs to access high-resolution visual details during their thought process. |
| Approach: | They propose a framework that dynamically determines necessary pixel-level operations based on the input query. |
| Outcome: | The proposed model achieves 73.4% accuracy on HR-Bench 4K while maintaining a tool usage ratio of only 20.1%, improving accuracy and reducing tool usage by 66.5% compared to the previous methods. |
Balancing Knowledge Breadth and Task Depth for Effective Domain Adaptation Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | a lack of knowledge breadth and task depth can hinder curriculum learning in domains such as medicine and finance. |
| Approach: | They propose a two-dimensional curriculum learning framework that coordinates model training along two orthogonal axes: the knowledge dimension and the task dimension. |
| Outcome: | The proposed framework improves accuracy on medical evaluations by 2.49% and on financial evaluations 1.2% compared with the second-best method. |
Are LLM-based Evaluators Confusing NLG Quality Criteria? (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that LLMs confuse evaluation criteria, which reduces their reliability. |
| Approach: | They propose a hierarchical classification system for 11 common aspects with corresponding different evaluation criteria. |
| Outcome: | The proposed system is based on 11 common aspects with different evaluation criteria. |
Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)
Copied to clipboard
Yiwen Qiu, Linjuan Wu, Yizhou Liu, Yuchen Yan, Jin Ma, Xu Tan, Yao Hu, Daoxin Zhang, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen
| Challenge: | Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions. |
| Approach: | They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification. |
| Outcome: | The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% . |
Systematic Generalization on gSCAN: What is Nearly Solved and What is Next? (2021.emnlp-main)
Copied to clipboard
| Challenge: | a general-purpose Transformer-based model with crossmodal attention solves most of the systematic generalization problems . current models are data inefficient given the narrow scope of commands in gSCAN . |
| Approach: | They propose to use a Transformer-based model with cross-modal attention to solve gSCAN . they propose to generate data to incorporate relations between objects in the visual environment . |
| Outcome: | The proposed model outperforms specialized approaches on most splits, and is data inefficient given the narrow scope of commands. |
OpenDelta: A Plug-and-play Library for Parameter-efficient Adaptation of Pre-trained Models (2023.acl-demo)
Copied to clipboard
| Challenge: | Existing implementations that modify the code of the backbone PTMs and hard-code specific delta tuning methods for each PTM have limited the practicality and flexibility of delta tuning. |
| Approach: | They propose an open-source library that provides a plug-and-play implementation of delta tuning methods for pre-trained models. |
| Outcome: | The proposed methods eliminate the need to modify the backbone PTMs’ code, making OpenDelta compatible with different, even novel PTM. |
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | ComfyUI-R1 is the first large reasoning model for automated workflow generation. |
| Approach: | They propose a large reasoning model for automated workflow generation that builds on curated knowledge bases and a two-stage framework to fine-tune models for cold start and reinforcement learning for incentivizing reasoning capability. |
| Outcome: | The proposed model achieves 97% format validity rate, high pass rate, node-level and graph-level F1 scores, surpassing prior state-of-the-art methods that employ leading closed-source models such as GPT-4o and Claude series. |
Leveraging Outline-Optimized Generative Interactions and Critique for Self-Refining Outlines with Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Logic-RL is a framework that transforms critique-guided outline refinement into a learnable policy through reinforcement learning. |
| Approach: | They propose a framework that transforms critique-guided outline refinement into a learnable policy through reinforcement learning. |
| Outcome: | The proposed framework improves on FreshWiki and WikiOutline . it can be iteratively applied, with improved quality continuing through three refinement rounds before diminishing returns. |
DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)
Copied to clipboard
Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, Jia Fu, Tao Wang, Junwei Jing, Zhaoxin Fan, Wei Bi, Ruiming Tang, Han Li, Guorui Zhou, Kun Gai
| Challenge: | Large Language Models (LLMs) are evolving towards autonomous agents . retrieval capabilities are well-benchmarked, but post-retrieval synthesis is under-evaluated due to open-ended writing. |
| Approach: | They propose a benchmark to evaluate information consolidation capabilities using survey papers as gold standards. |
| Outcome: | The proposed benchmark analyzes the post-retrieval synthesis stage of large language models . it leverages high-quality survey papers as gold standards and reverse-engineers research requests . the proposed benchmark outperforms single-turn generation and reduces hallucinations . |
Improving Multi-turn Dialogue Modelling with Utterance ReWriter (P19-1)
Copied to clipboard
| Challenge: | Recent research has achieved impressive results in single-turn dialogue modelling, but multi-turn models still remain challenging. |
| Approach: | They propose to rewrite human utterances as a pre-process to help multi-turn dialgoue modelling. |
| Outcome: | The proposed architecture achieves remarkably good performance on the utterance rewriting task. |
Towards Better Document-level Relation Extraction via Iterative Inference (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods only consider feature information of entity pairs, but our model exploits both feature information and previous predictions of entity pair. |
| Approach: | They propose a document-level relation extraction model with iterative inference to extract relations between entities from raw texts. |
| Outcome: | The proposed model outperforms existing methods on three commonly-used datasets. |
GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work adopts data augmentation techniques to generate pseudo-annotated sentences . existing methods neither preserve semantic consistency of original sentences nor preserve syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations. |
| Approach: | They propose a dedicated augmentation technique for relational texts, named GDA, which uses two complementary modules to preserve both semantic consistency and syntax structures. |
| Outcome: | The proposed technique can bring 2.0% F1 improvements in three datasets under low-resource setting. |
Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors (2026.acl-long)
Copied to clipboard
Zhiwei Zhang, Fei Zhao, Rui Wang, Zezhong Wang, Bin Liang, Jiakang Wang, Yao Hu, Shaosheng Cao, Kam-Fai Wong
| Challenge: | Large language models (LLMs) can call tools effectively, but they remain brittle in multi-turn execution. |
| Approach: | They propose a framework that converts execution errors into on-policy corrective supervision within the RL training loop. |
| Outcome: | The proposed framework improves the error recovery rate of Qwen3-8B by 5.7% absolute and overall accuracy by 4.0% on BFCL v4 Multi-Turn. |
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)
Copied to clipboard
Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum
| Challenge: | Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. |
| Approach: | They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window. |
| Outcome: | The proposed model scales to multi-million-token effective TTC without exceeding context limits. |
Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction (2024.acl-long)
Copied to clipboard
| Challenge: | Aspect Sentiment Quad Prediction (ASQP) aims to predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review. |
| Approach: | They propose a self-training framework with a pseudo-label scorer to assess the match between reviews and their pseudo-labels and train a generative model on it. |
| Outcome: | The proposed framework can predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review, and it can significantly improve self-training. |
NAMER: A Node-Based Multitasking Framework for Multi-Hop Knowledge Base Question Answering (2021.naacl-demos)
Copied to clipboard
| Challenge: | Using a node-based framework, knowledge base question answering systems can grasp structural mappings between questions and KB queries. |
| Approach: | They propose a node-based framework that better grasps the structural mapping between questions and KB queries by aligning the nodes in a query with their corresponding mentions in question. |
| Outcome: | The proposed framework outperforms the previous SoTA on CCKS CKBQA dataset. |
Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis. |
| Approach: | They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts . |
| Outcome: | The proposed method bridges psychological value frameworks with neuron analysis in large language models. |
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding (2024.findings-emnlp)
Copied to clipboard
Anwen Hu, Haiyang Xu, Jiabo Ye, Ming Yan, Liang Zhang, Bo Zhang, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou
| Challenge: | Existing Multimodal Large Language Models lack general structure understanding abilities for text-rich document images. |
| Approach: | They propose to use unified structure learning to boost the performance of MLLMs by encoding structure information into text-rich images. |
| Outcome: | The proposed model achieves state-of-the-art on 10 visual document understanding benchmarks. |
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)
Copied to clipboard
Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen
| Challenge: | Existing approaches to program repair are based on correctness alone. |
| Approach: | They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits. |
| Outcome: | The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing. |
DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs (2026.acl-long)
Copied to clipboard
Bo Zhang, Jiawei Zhang, Cong Gao, Bingxu Han, Minghao Hu, Jun Zhang, Yunbo Cao, Zhunchen Luo, Wen Yao, Guotong Geng, Zhong Wang
| Challenge: | Existing methods for calibration of large reasoning models (LRMs) focus on clean inputs, leaving noise unexplored. |
| Approach: | They propose a confidence calibration framework for character-level noisy inputs that extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution and integrates them via a learned calibrator. |
| Outcome: | Experiments on multiple mathematical reasoning benchmarks show that DisCal outperforms existing calibration methods under noisy inputs, reducing expected calibration error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by 31.44%. |
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for knowledge editing in multimodal large language models focus on limited scenarios due to the lack of rigorous definition of multimodal knowledge. |
| Approach: | They propose a decomposed definition of multimodal knowledge and a benchmark to evaluate it. |
| Outcome: | The proposed method reveals that it is difficult to define multimodal knowledge editing in LLMs. |
Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)
Copied to clipboard
Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan
| Challenge: | Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors. |
| Approach: | They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors. |
| Outcome: | This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies . |
mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) have improved document understanding performance but generate thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times. |
| Approach: | They propose a high-resolution document compression module to generate 324 tokens for a single document image. |
| Outcome: | The proposed module reduces first token latency by more than 50% and improves document comprehension performance. |
GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorporated external knowledge. |
| Approach: | They propose a generative paradigm for translation tasks that integrates the diverse translation versions in N-best list. |
| Outcome: | The proposed model outperforms the state-of-the-art model on speech and machine translation benchmarks on various languages. |
Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing long document question answering systems process texts as flat sequences or use heuristic chunking, which overlooks the discourse structures that guide human comprehension. |
| Approach: | They propose a discourse-aware hierarchical framework that leverages rhetorical structure theory for long document question answering. |
| Outcome: | The proposed framework exhibits strong robustness across diverse document types and linguistic settings. |
Mitigating the Alignment Tax of RLHF (2024.emnlp-main)
Copied to clipboard
Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang
| Challenge: | Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax. |
| Approach: | They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms. |
| Outcome: | The proposed method achieves the strongest alignment-forging Pareto front among competing methods. |
From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning (2026.findings-acl)
Copied to clipboard
Xiaoyu Xu, Minxin Du, Zitong LI, Zi Liang, Zhibiao Guo, Zhang Shiyu, Peizhao Hu, Qingqing Ye, Haibo Hu
| Challenge: | Currently, the evaluation of unlearning is limited due to the lack of granularity in the model. |
| Approach: | They propose a framework for synthesizing high-quality forget sets that exploits the target model per se to elicit data that matches its internal knowledge distribution through seed-guided and adversarial prompting. |
| Outcome: | The proposed framework achieves a superior balance of relevance, diversity, and efficiency across benchmarks. |
2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) tasks are a fundamental task of natural language processing (NLP). |
| Approach: | They propose a text-to-text framework for Few-Shot Named Entity Recognition (NER) that employs instruction finetuning and auxiliary tasks to enhance the model's understanding of entity types in the overall semantic context of a sentence. |
| Outcome: | The proposed framework outperforms existing Few-Shot NER methods and remains competitive with state-of-the-art NER algorithms. |
A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning (2020.coling-main)
Copied to clipboard
| Challenge: | Paraphrase generation is of great importance for many downstream tasks in natural language processing. |
| Approach: | They propose a method to generate sentences as learning objectives from the learned data distribution and employ reinforcement learning to combine these new learning objectives for model training. |
| Outcome: | The proposed method gains significant diversity and improves generation quality over state-of-the-art datasets. |
UnifEE: Unified Evidence Extraction for Fact Verification (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing models extract evidence in both sentences and table cells from Wikipedia dumps, ignoring potential connections between them. |
| Approach: | They propose a model which uses a mixed evidence graph to extract the evidence in both formats without manually designed conversion rules. |
| Outcome: | The proposed model outperforms existing models and improves the verification step. |
TruthReader: Towards Trustworthy Document Assistant Chatbot with Reliable Attribution (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Document assistant chatbots are empowered with extensive capabilities by Large Language Models (LLMs) however, they suffer from hallucinations that are difficult to verify in the context of given documents. |
| Approach: | They propose a document assistant chatbot with reliable attribution that enables users to seek relevant information from given documents. |
| Outcome: | The proposed system generates answers with detailed inline citations, which can be attributed to the original document paragraphs, facilitating verification of factual consistency of the generated text. |
Focused Large Language Models are Stable Many-Shot Learners (2024.emnlp-main)
Copied to clipboard
Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li
| Challenge: | In-Context Learning (ICL) enables large language models to achieve rapid task adaptation by learning from demonstrations. |
| Approach: | They propose a training-free method that disperses model attention from the query . they propose 'focus' search strategy that uses model perplexity to ensure sufficient attention . |
| Outcome: | The proposed method achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations. |
Enhancing Zero-Shot Time Series Forecasting in Off-the-Shelf LLMs via Noise Injection Prompting (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing work relies on fine-tuning specialized modules to bridge this gap, but a novel approach is proposed to leverage off-the-shelf LLMs without any fine- tuning whatsoever. |
| Approach: | They propose a method to inject noise into the raw time series before tokenization to induce the model to extrapolate based on robust underlying temporal patterns rather than superficial numerical artifacts. |
| Outcome: | The proposed approach overcomes the brittleness of fully frozen models by injecting noise into the raw TS before tokenization. |
Refine, Align, and Aggregate: Multi-view Linguistic Features Enhancement for Aspect Sentiment Triplet Extraction (2024.findings-acl)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) aims to extract the triplets of aspect terms, their associated sentiment and opinion terms. |
| Approach: | They propose to use multi-view linguistic features enhancement to explore the prior indication effect in the “Refine, Align, and Aggregate” learning process to enhance aspect-opinion relations. |
| Outcome: | The proposed model achieves state-of-the-art on several benchmark datasets and is robust to state- of-the art constraints. |
RESF: Regularized-Entropy-Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for tamper detection rely on model stability, not inherently stochastic models. |
| Approach: | They propose a hypothesis-testing method for black-box tamper detection for LLMs . they propose regularized entropy-sensitive fingerprinting to enable efficient fingerprinting . |
| Outcome: | The proposed method achieves 98.80% detection accuracy under challenging conditions . it is based on a first-order surrogate for KL divergence to identify prompts most responsive to parameter perturbations. |
InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)
Copied to clipboard
Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li
| Challenge: | Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs. |
| Approach: | They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time. |
| Outcome: | The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets. |
KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases (2024.emnlp-main)
Copied to clipboard
| Challenge: | Program induction (PI) is a promising paradigm for using knowledge bases (KBs) to help large language models answer complex knowledge-intensive questions. |
| Approach: | They propose a plug-and-play framework that enables large language models to induce programs over any low-resourced KB. |
| Outcome: | Experiments show that KB-Plugin outperforms SoTA low-resourced PI methods with 25x smaller backbone LLM on large-scale and domain-specific KBs and even approaches the performance of supervised methods. |
Improving Attributed Text Generation of Large Language Models via Preference Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models have been widely adopted in natural language processing, yet they produce unreliable content. |
| Approach: | They propose to model the attribution task as preference learning and introduce an automatic preference optimization framework that synthesizes attribution preference data. |
| Outcome: | The proposed method achieves state-of-the-art citation F1 with higher answer quality than existing methods. |
Two Streams, One Sarcasm: Orthogonal Expert Tuning for Holistic Multimodal Sarcasm Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for multimodal satirical cognition hinder evaluation of multimodal Sarcasm Understanding . lack of a unified benchmark for holistic satire cognition hampers evaluation of MSU . |
| Approach: | They propose a framework to decouple experts into orthogonal shared perception and private execution streams to physically block gradient interference between tasks. |
| Outcome: | The proposed framework achieves superior performance on DocMSU-PLUS. |
SCoder: Progressive Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs (2025.findings-emnlp)
Copied to clipboard
Xinyu Zhang, Changzhi Zhou, Linmei Hu, Luhao Zhang, Xiancai Chen, Haomin Fu, Yang Yang, Mengdi Zhang
| Challenge: | Existing code large language models rely on large-scale instruction data distilled from proprietary LLMs for fine-tuning, which typically incurs high costs. |
| Approach: | They propose an iterative self-distillation approach to bootstrap small-scale LLMs . they use large-scale instruction data distilled from proprietary LLM for fine-tuning . |
| Outcome: | The proposed method reduces reliance on proprietary LLMs and minimizes costs. |
Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive results in Machine Translation by following instructions, even without training on parallel data. |
| Approach: | They propose a Translate After LEarNing Textbook approach which aims to enhance LLMs’ ability to translate low-resource languages by learning from a textbook. |
| Outcome: | The proposed approach improves translation performance by 14.8% using 112 low-resource languages from FLORES-200 with two LLMs: ChatGPT and BLOOMZ. |
PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation. |
| Approach: | They propose a method that compresses the KV cache by layer-wise retaining crucial context. |
| Outcome: | The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction . |
Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on what to generate but ignore what not to generate . a template-agnostic method boosts original learning and reduces mistakes simultaneously . |
| Approach: | They propose a template-agnostic method to control the token-level generation . they introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models . |
| Outcome: | The proposed method boosts original learning and reduces mistakes simultaneously on four public datasets. |
CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)
Copied to clipboard
Wenhong Zhu, Hongkun Hao, Zhiwei He, Yun-Ze Song, Jiao Yueyang, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, Hongyuan Lu
| Challenge: | Existing methods to evaluate large language models are prone to data contamination. |
| Approach: | They propose a method which parses contaminated data and back-translates it into a candidate set. |
| Outcome: | The proposed method reduces data contamination and evaluates the LLMs more cleanly. |
StructuThink: Reasoning with Task Transition Knowledge for Autonomous LLM-Based Agents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | StructuThink framework enhances LLMs' ability to ground decisions in domain-specific scenarios. |
| Approach: | They propose a knowledge-structured reasoning framework that enhances LLM-based agents with explicit decision constraints. |
| Outcome: | The proposed framework achieves higher task success rates and more efficient action sequences than baseline methods. |
Multi-Granularity Semantic Revision for Large Language Model Distillation (2026.acl-long)
Copied to clipboard
Xiaoyu Liu, Yun Zhang, Wei Li, Simiao Li, Xudong Huang, Hanting Chen, Yehui Tang, Jie Hu, Zhiwei Xiong, Yunhe Wang
| Challenge: | Existing methods for generating large language models rely on student-generated outputs, which introduce generation errors and misguide the distillation process. |
| Approach: | They propose a multi-granularity semantic revision method for LLM distillation that corrects errors using teacher-generated tokens and re-generates the sequence to minimize errors. |
| Outcome: | The proposed method reduces errors and misguides distillation on student models and improves consistency between teacher and student outputs. |
Open-Topic False Information Detection on Social Networks with Contrastive Adversarial Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for false information detection on social networks are too harsh for actual social networks that contain both seen and unseen topics simultaneously. |
| Approach: | They propose an open-topic scenario that assumes that all test data topics are seen or unseen by the model, but which is too harsh for actual social networks that contain both seen and unseened topics simultaneously. |
| Outcome: | The proposed model improves on two benchmark datasets and a variety of graph neural networks on two social networks and shows that it is more accurate than existing models. |
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)
Copied to clipboard
Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen
| Challenge: | Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection. |
| Approach: | They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization. |
| Outcome: | The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models. |
Bridging the Granularity Gap for Acoustic Modeling (2023.findings-acl)
Copied to clipboard
Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu, Chi Hu, Xin Zeng, Tong Xiao, Anxiang Ma, Huizhen Wang, Jingbo Zhu
| Challenge: | Despite the success of speech recognition, how to encode the speech features effectively remains an open problem. |
| Approach: | They propose a Progressive Down-Sampling technique which compresses acoustic features into coarser-grained units containing more complete semantic information, like text-level representation. |
| Outcome: | The proposed method yields comparable or better results on the speech recognition task and inference speedups ranging from 1.20x to 1.47x. |
AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Recent work on learning from multiple tasks has shown that adding an extra fusion layer to implement knowledge composition is non-scalable for some applications. |
| Approach: | They propose a two-stage knowledge distillation algorithm to extract task specific knowledge by using local data to train a student adapter. |
| Outcome: | Experiments on frequently asked question retrieval in task-oriented dialog systems validate the efficiency of AdapterDistillation. |
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)
Copied to clipboard
Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu, Xintong Li, Ryan Aponte, Hanjia Lyu, Joe Barrow, Hongjie Chen, Franck Dernoncourt, Branislav Kveton, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Sungchul Kim, Zhengmian Hu, Yue Zhao, Nedim Lipka, Seunghyun Yoon, Ting-Hao Kenneth Huang, Zichao Wang, Puneet Mathur, Soumyabrata Pal, Koyel Mukherjee, Zhehao Zhang, Namyong Park, Thien Huu Nguyen, Jiebo Luo, Ryan A. Rossi, Julian McAuley
| Challenge: | Large Language Models (LLMs) have been used for selection and training of data for active learning. |
| Approach: | They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop. |
| Outcome: | The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances. |
Video-MMMU: Evaluating Knowledge Acquisition from Multidisciplinary Professional Videos (2026.acl-long)
Copied to clipboard
| Challenge: | Existing video benchmarks do not evaluate the knowledge acquisition capabilities of Large Multimodal Models (LMMs) existing video benchmark focuses on static, general visual understanding tasks, without evaluating whether models can acquire knowledge dynamically. |
| Approach: | They propose a multi-modal, multi-discipline, multitrack benchmark that evaluates Large Multimodal Models’ ability to acquire knowledge from college-level, educational videos. |
| Outcome: | The proposed benchmark reveals a substantial gap between human learners and current Large Multimodal Models (LMMs) and focuses on improving their learning efficiency. |
Generative Multimodal Entity Linking (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing Entity Linking methods focus on designing complex multimodal interaction mechanisms and require fine-tuning all model parameters. |
| Approach: | They propose a framework for multimodal entity linking based on Large Language Models (LLMs) that trains a feature mapper to enable cross-modal interactions. |
| Outcome: | The proposed framework achieves state-of-the-art on two well-established datasets with a performance gain of 7.7% on WikiDiverse and 8.8% on Wikileaks. |
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection (2026.eacl-long)
Copied to clipboard
Yuhang Liu, Pengxiang Li, Zishu Wei, Congkai Xie, Xueyu Hu, Xinchen Xu, Shengyu Zhang, Xiaotian Han, Hongxia Yang, Fei Wu
| Challenge: | Existing GUI Agents face challenges in multi-step reasoning and reliance on textual annotations, limiting their effectiveness. |
| Approach: | They propose an MLLM-based GUI Agent with a two-stage supervised fine-tuning pipeline that enhances GUI understanding and grounding. |
| Outcome: | InfiGUIAgent achieves competitive performance on several GUI benchmarks, highlighting the impact of native reasoning skills in enhancing GUI interaction for automation tasks. |
MEVTR: A Multilingual Model Enhanced with Visual Text Representations (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models that generate multilingual text representations perform poorly on low-resource languages due to lack of representation space and model capacity. |
| Approach: | They propose a multilingual model enhanced with visual text representations which complements textual representations and extends multilingual representation space with visual representations. |
| Outcome: | The proposed model outperforms state-of-the-art models on zero-shot cross-lingual transfer tasks without the target language adapter. |
Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models . |
| Approach: | They analyze methods based on generation strategies and refinement mechanisms . they examine deployment strategies across computing environments and explore applications spanning text, images, and speech generation. |
| Outcome: | The proposed frameworks can be used to improve the quality of autoregressive models. |
1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Low-rank approximation compresses the model by retaining its essential structure with minimal information loss. |
| Approach: | They propose a method that leverages the strengths of pruning and low-rank approximation for LLMs. |
| Outcome: | The proposed methods surpass the existing methods on LLaMA and Qwen2.5 models. |
SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, but their effectiveness in ECI remains limited due to biases in causal reasoning. |
| Approach: | They propose a structural example retrieval framework that leverages LLMs’ few-shot learning capabilities to help LLM models in ECI. |
| Outcome: | The proposed framework leverages LLMs’ few-shot learning capabilities to guide LLM models in causal reasoning, mitigating bias and improving accuracy. |
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)
Copied to clipboard
Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu
| Challenge: | Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios. |
| Approach: | They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity. |
| Outcome: | The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues. |
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference (2021.findings-acl)
Copied to clipboard
| Challenge: | Multilingual transformers have been shown to have remarkable transfer skills in zero-shot settings. |
| Approach: | They investigate cross-lingual transfer abilities of XLM-R for Chinese and English natural language inference using a large scale Chinese dataset. |
| Outcome: | The proposed model trains on Chinese and English natural language inference datasets. |
MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods for complex multi-shot video are anchored to single-shot paradigms, lacking comprehensive story assets and cross-shot metrics. |
| Approach: | They propose a framework that synergizes the high-level semantic reasoning of Large Multimodal Models with the fine-grained perceptual rigor of domain-specific expert models. |
| Outcome: | The proposed framework synergizes the high-level semantic reasoning of Large Multimodal Models with the fine-grained perceptual rigor of domain-specific expert models. |
MTLS: Making Texts into Linguistic Symbols (2024.emnlp-main)
Copied to clipboard
| Challenge: | In linguistics, all languages can be considered as symbolic systems . most work overlooks the properties of languages as symbol systems - aaron et al., 1989). |
| Approach: | They propose a method to make texts into linguistic symbols to improve multilingual capability . they use a pre-training method to replace pre-trained language models with a vocabulary map . |
| Outcome: | The proposed method improves multilingual capabilities on multilingual tasks using BERT and RoBERTa as the backbone. |
MTP-RL: Acceleration of Reinforcement Learning Rollouts with Policy-Aligned Multi-Token Prediction (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) is widely applied to boost the performance of pretrained models, yet its training efficiency is severely constrained by rollout generation. |
| Approach: | They propose a framework that accelerates the rollout phase for diverse models by equipping a pipeline to equip the multi-layer parameter-sharing MTP for all models and an advantage-aware MTP optimization strategy. |
| Outcome: | The proposed framework achieves stable growth of acceptance length during RL training, and also accelerates RL rollouts, achieving an average 23.1%–55.3% reduction in rollout time compared to baselines. |
ZoomRAG: Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG (2026.findings-acl)
Copied to clipboard
Xianming Hu, Jingyang Chen, Bin Tang, Yihe Liu, Yihong Huang, Hongbo Zhao, Nuoyi Chen, Jie Zhang, Ping Li, Kai Zhang
| Challenge: | retrieval-augmented generation (RAG) is a powerful tool for NLP applications . but it is challenging to encode large knowledge bases as compact offline structures . |
| Approach: | They propose a coarse-to-fine hierarchical graph inference method that uses random walks to retrieve information from a corpus of documents. |
| Outcome: | The proposed method reduces offline indexing costs and accelerates retrieval. |
A Black-Box Attack on Code Models via Representation Nearest Neighbor Search (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating adversarial code examples face challenges such as limted availability of substitute variables and the creation of adversarials with noticeable perturbations. |
| Approach: | They propose a search seed based on historical attacks to find adversarial substitutes . they employ a pre-trained variable name encoder to map the search seed to a continuous vector space . |
| Outcome: | The proposed approach outperforms baseline methods in terms of ASR and QT. |
Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have explored the working mechanisms of In-Context Learning (ICL) however, they mainly focus on classification and simple generation tasks, limiting their broader application to more complex generation tasks in practice. |
| Approach: | They propose an efficient Progressive In-Context Alignment method that embeds the task function learned from demonstrations into the separator token representation. |
| Outcome: | The proposed method surpasses vanilla ICL and achieves comparable performance to other alignment tuning methods. |
Token-level Inference-Time Alignment for Vision-Language Models (2026.findings-acl)
Copied to clipboard
Kejia Chen, Junjun Zheng, Jiawen Zhang, Manxi Lin, Xiao Pan, Jiacong Hu, Jian Lou, Zunlei Feng, Mingli Song
| Challenge: | Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity . despite widespread adoption, VLMs often exhibit a critical failure mode: hallucination . |
| Approach: | They propose a framework for Token-level Inference-Time Alignment that steers the decoding process without updating the base model parameters. |
| Outcome: | The proposed framework improves performance on 13 benchmarks across architectures . it boosts LLaVA-1.5-7B by 8.6% on MMVet and achieves a 74.0 MMStar score . |
COMPKE: Complex Question Answering under Knowledge Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for knowledge editing do not accurately evaluate how well models apply knowledge in real-life situations. |
| Approach: | They propose a benchmark to evaluate how well updated models apply new knowledge in real-life situations. |
| Outcome: | The proposed method achieves 39.47 accuracy on GPT-4o-mini but drops significantly to 3.83 on Qwen2.5-3B. |
Domain-Specific NER via Retrieving Correlated Samples (2022.coling-1)
Copied to clipboard
| Challenge: | Successful Named Entity Recognition models fail on texts from some special domains, for example, Chinese addresses and e-commerce titles. |
| Approach: | They propose to enhance NER models with correlated samples to help the text understanding . they draw correlated texts by the sparse BM25 retriever from large-scale in-domain unlabeled data . |
| Outcome: | Empirical results show that NER models can be enhanced with correlated samples . the proposed model can be used to reason out the correct answer on hard cases . |
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development (2025.acl-demo)
Copied to clipboard
Zhenran Xu, Yangxue Yangxue, Yiyu Wang, Qingli Hu, Zijiao Wu, Baotian Hu, Longyue Wang, Weihua Luo, Kaifu Zhang
| Challenge: | ComfyUI-Copilot is a large language model-powered plugin for AI-driven art creation. |
| Approach: | They propose a large language model-powered plugin to enhance the usability of ComfyUI. |
| Outcome: | The new plugin improves the usability and efficiency of ComfyUI . it offers intelligent node and model recommendations and automated one-click workflow construction. |
MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent text-to-image models achieve impressive visual quality but still face challenges in precise controllability, balancing multimodal inputs, and high training cost for multimodal image generation. |
| Approach: | They propose an autoregressive framework with a two-stage training paradigm for controllable multimodal image generation. |
| Outcome: | Extensive experiments on DreamBench++ and DreamBech show that the proposed framework achieves a strong balance between textual and visual guidance for controllable image generation. |
MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)
Copied to clipboard
Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Existing preference learning methods for safety alignment are monolingual and struggle with noisy multilingual data. |
| Approach: | They propose a multilingual reward gaP optimization approach that leverages the well-aligned safety capabilities of the dominant language to improve safety alignment across multiple languages. |
| Outcome: | Extensive experiments on three LLMs, LLaMA-3.1, Gemma-2 and Qwen2.5, validate MPO’s efficacy in multilingual safety alignment without degrading general multilingual utility. |
MELA: Multilingual Evaluation of Linguistic Acceptability (2024.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks on linguistic acceptability have been used to evaluate language models' ability to distinguish between acceptable and unacceptable sentences. |
| Approach: | They present the largest benchmark to date on linguistic acceptability: MELA . they establish LLM baselines on this benchmark and investigate cross-lingual transfer in acceptability judgements with XLM-R. |
| Outcome: | The proposed model outperforms open-source models on cross-lingual transfer in acceptability judgements. |
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)
Copied to clipboard
Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu
| Challenge: | Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression. |
| Approach: | They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks. |
| Outcome: | The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks. |
Simple but Effective Compound Geometric Operations for Temporal Knowledge Graph Completion (2024.acl-long)
Copied to clipboard
Rui Ying, Mengting Hu, Jianfeng Wu, Yalan Xie, Xiaoyi Liu, Zhunheng Wang, Ming Jiang, Hang Gao, Linlin Zhang, Renhong Cheng
| Challenge: | Current methods embed factual knowledge into continuous vector space and apply geometric operations to learn potential patterns in temporal knowledge graphs. |
| Approach: | They propose a temporal knowledge graph completion method that uses two geometric operations to learn missing facts in temporal graphs. |
| Outcome: | The proposed method significantly outperforms existing temporal knowledge graph embedding models. |
CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models have significantly improved reasoning and generation tasks by leveraging joint vision-language representations. |
| Approach: | They propose a framework that reconciles inconsistencies across knowledge sources . they use a four-stage pipeline to generate an internal response from parametric knowledge . |
| Outcome: | Experiments on KB-VQA show that CoRe-MMRAG achieves performance gains of 5.6% and 9.3% over baseline methods. |
RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)
Copied to clipboard
Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai
| Challenge: | RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images . |
| Approach: | They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a . |
| Outcome: | The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images. |
Minos: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation models struggle to achieve consistent performance across image-to-text (I2T) and text-to image (T2I) tasks. |
| Approach: | They construct a multimodal evaluation model using a large multimodal dataset and rigorous quality control strategies to train it. |
| Outcome: | The proposed model achieves state-of-the-art evaluation performance across 16 out-of domain datasets covering both I2T and T2I tasks among all open-source multimodal evaluation models and remain competitive with closed-source models. |
SETSum: Summarization and Visualization of Student Evaluations of Teaching (2022.naacl-demo)
Copied to clipboard
| Challenge: | Student Evaluations of Teaching (SETs) are used in colleges and universities to assess student perceptions about their courses. |
| Approach: | They propose a system that leverages sentiment analysis, aspect extraction, summarization and visualization techniques to provide organized illustrations of SET findings to instructors and other reviewers. |
| Outcome: | The proposed system can be used by 10 professors from diverse departments to analyze SET results. |
STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)
Copied to clipboard
Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma
| Challenge: | Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation. |
| Approach: | They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset. |
| Outcome: | The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations. |
A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Structured belief states are crucial for goal tracking and database query in task-oriented dialog systems. |
| Approach: | They propose a probabilistic dialog model where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs. |
| Outcome: | The proposed model outperforms supervised-only and semi-supervised baselines on three benchmark datasets. |
PEPE: Long-context Extension for Large Language Models via Periodic Extrapolation Positional Encodings (2025.findings-emnlp)
Copied to clipboard
Jikun Hu, Dongsheng Guo, Yuli Liu, Qingyao Ai, Lixuan Wang, Xuebing Sun, Qilei Zhang, Quan Zhou, Cheng Luo
| Challenge: | Long-context extension attempts to extend contextual window in pre-trained LLMs . primary method involves expanding initial positional encodings, disrupting positional learning . |
| Approach: | They propose a new extension strategy based on Rotary Position Embedding to extend contextual window in pre-trained large language models. |
| Outcome: | The proposed method can extend the contextual window in pre-trained large language models . expansion disrupts positional encodings learned during pre-training, authors show . |
Tiny Budgets, Big Gains: Parameter Placement Strategy in Parameter Super-Efficient Fine-Tuning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods such as LoRA and VeRA use memory-efficient methods to fine-tune large language models. |
| Approach: | They propose a method that uses only 1–5% of the standard LoRA parameters and achieves state-of-the-art performance across a wide range of tasks. |
| Outcome: | The proposed method achieves state-of-the-art performance across a wide range of tasks using only 1–5% of the standard LoRA parameters. |
Visually-Guided Policy Optimization for Multimodal Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing RLVRs lack visual faithfulness due to text-dominated reasoning . a novel framework to reinforce visual focus during policy optimization is proposed . |
| Approach: | They propose a framework to reinforce visual focus during policy optimization using visual attention compensation mechanism. |
| Outcome: | The proposed framework exhibits better visual activation and superior performance in multimodal reasoning and visual-dependent tasks. |
Multi-matrix Factorization Attention (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing variants for Multi-Head Attention (MHA) fail to maintain strong performance under stringent Key-Value cache (KV cache) constraints. |
| Approach: | They propose to use multi-matrix factorization attention and MFA-Key-reuse attention architectures to increase model capacity under tight KV cache constraints. |
| Outcome: | The proposed architecture outperforms existing methods while reducing KV cache usage by 56% and 93.7% in large-scale experiments. |
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang
| Challenge: | Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question . |
| Approach: | They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance . |
| Outcome: | The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered . |
Enhancing Event Causality Identification with LLM Knowledge and Concept-Level Event Relations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to identify causal relationships between events often overlook the dependencies between similar events. |
| Approach: | They propose an ECI method enhanced by LLM Knowledge and Concept-Level Event Relations (LKCER) the method constructs a conceptual-level heterogeneous event graph by leveraging local contextual information of related event mentions. |
| Outcome: | The proposed method outperforms previous state-of-the-art methods on both benchmarks, EventStoryLine and Causal-TimeBank. |
Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to extract relation facts from limited labeled corpora are laborintensive to obtain . Existing approaches use self-training to generate pseudo labels that will cause gradual drift problem or leverage meta-learning scheme which does not solicit feedback explicitly. |
| Approach: | They propose a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate gradient descent direction on labeled data and bootstrap its optimization capability through trial and error. |
| Outcome: | The proposed method handles two major scenarios in low-resource relation extraction when no unlabeled data is available. |
StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding (2026.findings-acl)
Copied to clipboard
Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, Zichen Wen, Xuming Hu, Zhiyu li, Linfeng Zhang
| Challenge: | StreamMeCo is an efficient Stream Agent Memory Compression framework for video understanding. |
| Approach: | They propose an efficient Stream Agent Memory Compression framework that evicts redundant memory nodes and introduces a time-decay memory retrieval mechanism to mitigate performance degradation. |
| Outcome: | The proposed framework achieves 1.87 speedup in memory retrieval while delivering an average accuracy improvement of 1.0% on three challenging benchmark datasets. |
Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Achieving consistent high-quality machine translation across diverse domains remains a challenge due to limited and imbalanced parallel training data available in various domains. |
| Approach: | They propose a domain Chain of Thought technique that uses the multi-domain intelligence of LLMs to improve translation performance. |
| Outcome: | The proposed method achieves significant improvements in translation accuracy and domain robustness over traditional fine-tuning on a small dataset of four domains. |
TRUST: Towards Robust Social Bot Detection via Uncertainty-Guided Pseudo-Labeling and Graph Structure Purification (2026.findings-acl)
Copied to clipboard
Ruixuan Xu, Mengting Hu, Zhunheng Wang, Ming Jiang, Rui Ying, Zhen Zhang, Hang Gao, Shuaipeng Liu, Renhong Cheng
| Challenge: | Existing graph-based detection models are vulnerable to deceptive message propagation, where bots deliberately interact with legitimate users. |
| Approach: | They propose a framework to mitigate deceptive message propagation by node-level uncertainty estimation and graph structure purification. |
| Outcome: | The proposed framework improves on three benchmark datasets and six GNN backbones on real-world social bots. |
Data-Efficient Selection via Grammatical Complexity in Continual Pre-training of Domain-Specific LLMs (2025.emnlp-main)
Copied to clipboard
Yizhou Ying, Geng Zhang, Cui Danxin, Chengyu Du, Guanglei Yue, Sihang Jiang, Jiaqing Liang, Yifei Fu, Hailin Hu, Yanghua Xiao
| Challenge: | Existing data selection strategies for continual pre-training of large language models often rely on scarce labeled data or computationally expensive LLMs. |
| Approach: | They propose an annotation-independent data selection framework for CPT that evaluates grammatical complexity using lexical diversity and syntactic complexity. |
| Outcome: | The proposed framework outperforms baselines on a financial dataset and surpasses full-data training by 1.7% using only 20% of the data. |
All That Glitters is Not Gold: Improving Robust Retrieval-Augmented Language Models with Fact-Centric Preference Alignment (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to learn adaptive retrieval for noisy documents lack prior filtering and may lead to the loss of crucial information. |
| Approach: | They propose a method to improve retrieval performance without prior filtering . they use LLMs self-generated synthetic data as training data without manual annotation . |
| Outcome: | The proposed method performs positive document mining based on factual consistency and uses LLMs self-generated synthetic data as training data without manual annotation. |
Leibniz: Theory-of-Mind Driven Neuro-Symbolic Logical Reasoning via Multi-Agent Collaboration (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for logical reasoning with large language models suffer from insufficient rule semantic grounding and weak rule application mechanisms. |
| Approach: | They propose a theory-of-mind driven neuro-symbolic reasoning framework that integrates natural language and symbolic representations throughout the reasoning process. |
| Outcome: | The proposed model surpasses state-of-the-art models in reasoning accuracy and flexibility. |
Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reasoning ability is a defining capability of Large Language Models (LLMs), but RLVR training suffers from policy entropy collapse, hindering exploration and limiting reasoning performance. |
| Approach: | They propose a framework that dynamically balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment. |
| Outcome: | The proposed framework outperforms baselines on multiple mathematical reasoning benchmarks. |
SAFER: A Controllable Safeguard for LLMs against Backdoor Attacks (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing inference-time defenses lack explicit control over false acceptance rate (FAR) existing inference time defenses aim to mitigate poisoned inputs but lack explicit FAR control . |
| Approach: | They propose a framework that provides explicit control over false acceptance rate without prior knowledge of backdoor samples. |
| Outcome: | The proposed framework outperforms existing inference-time defenses on three benchmark datasets . it provides explicit and provable control over false acceptance rate without prior knowledge of backdoor samples . |
SudokuFill: A Multi-Agent Progressive Filling Framework for Document-Level Scientific Information Extraction (2026.findings-acl)
Copied to clipboard
Yang Li, Yajiao Wang, Yu Zhang, Yuanzhe Zhang, Maodi Hu, Mengting Zhang, Xi Sun, Hua Yue, Zhixiong Zhang
| Challenge: | Scientific information extraction (SciIE) is a key bottleneck for turning unstructured papers into computable knowledge bases. |
| Approach: | They propose a scientific information extraction framework that solves a Sudoku problem as a progressive filling problem. |
| Outcome: | The proposed framework outperforms the GPT-4o model on a document-level adjuvant dataset. |
mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent multilingual pretrained language models encode strong language-specific signals, which are not explicitly provided during pretraining. |
| Approach: | They propose a language similarity measure that induces similarities across languages from mPLMs using multi-parallel corpora. |
| Outcome: | The proposed measure exhibits moderately high correlations with linguistic similarity measures, and more accurate similarity results on low correlation languages. |
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)
Copied to clipboard
Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan
| Challenge: | Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages . |
| Approach: | They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models . |
| Outcome: | The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English . |
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference (2020.emnlp-main)
Copied to clipboard
Bang An, Jie Lyu, Zhenyi Wang, Chunyuan Li, Changwei Hu, Fei Tan, Ruiyi Zhang, Yifan Hu, Changyou Chen
| Challenge: | Existing studies show that multi-head attention is an effective module in deep neural networks, but there are no explicit mechanisms guaranteeing this property. |
| Approach: | They propose a non-parametric approach that explicitly improves the repulsiveness in multi-head attention and consequently strengthens model’s expressiveness. |
| Outcome: | The proposed approach improves the repulsiveness in multi-head attention and strengthens model’s expressiveness. |
Beyond Task-Level Context: Class-Conditional Context Vectors for Implicit In-Context Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches aggregate demonstrations from all classes into a shared, task-level context vector, capturing global task information but without explicitly preserving fine-grained, class-conditional semantic distinctions. |
| Approach: | They propose a class-conditional context vector extension to implicit in-context learning that explicitly models class-specific contextual information by constructing separate context vectors for each class. |
| Outcome: | The proposed extension outperforms task-level context vector baselines and achieves higher average accuracy than conventional few-shot learning on most models. |
CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System (2025.acl-long)
Copied to clipboard
Li Hu, Guoqiang Chen, Xiuwei Shang, Shaoyin Cheng, Benlong Wu, LiGangyang LiGangyang, Xu Zhu, Weiming Zhang, Nenghai Yu
| Challenge: | CompileAgent is the first LLM-based agent framework dedicated to repo-level compilation. |
| Approach: | They propose a LLM-based agent framework dedicated to repo-level compilation. |
| Outcome: | The proposed method significantly improves compilation success rate, ranging from 10% to 71%. |
Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)
Copied to clipboard
Bojian Xiong, Yikun Lei, Xikai Liu, Shaowei Zhang, Pengyun Zhu, Yan Liu, Yongqi Leng, Ling Shi, Meizhi Zhong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong
| Challenge: | Large language models suffer from multiple-file coding scenarios with strong inter-file dependencies . experimental results show that large language models exhibit inadequate performance in multi-file scenarios . |
| Approach: | They propose a retrieval-augmented reasoning framework for repository-level code repair . they use a dataset to generate standardized patches based on the key snippets . |
| Outcome: | The proposed framework improves retrieval accuracy and repair success on SWE-bench Lite . it surpasses models with larger size in managing extensive code contexts and fixing bugs spanning across multiple files. |
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)
Copied to clipboard
Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong
| Challenge: | Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure. |
| Approach: | They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction. |
| Outcome: | The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models. |
UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Table structure recognition technology is a critical tool for processing and analyzing large volumes of tabular data. |
| Approach: | They propose a framework for table structure parsing based on the image-to-text model and a vision guider to refine the model’s capability to understand textual semantics in table images. |
| Outcome: | The proposed framework improves on a dataset of PubTabNet, PubTables1M, WTW, and iFLYTAB and will be made publicly available. |
Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval (2024.lrec-main)
Copied to clipboard
Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu
| Challenge: | Existing methods for video-text retrieval capture fine-grained semantic concepts . however, they lack the ability to capture finer-grain concepts such as objects and actions. |
| Approach: | They propose a dual-encoder architecture for fast video-text retrieval that learns lexicon representations to capture fine-grained semantics. |
| Outcome: | The proposed framework outperforms existing methods with 4.8% and 8.2% improvement on MSR-VTT and DiDeMo respectively. |
MARCH: Multi-Agent Reinforced Check for Hallucination (2026.acl-long)
Copied to clipboard
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie Hu, Yu Qin, null Erchao.zec, Xiaoxi Jiang, null Guanjunjiang
| Challenge: | Existing methods to detect hallucinations suffer from inherent confirmation bias, where the verifier inadvertently reproduces the errors of the original generation. |
| Approach: | They propose a framework that enforces rigorous factual alignment by leveraging deliberate *information asymmetry* by combining a pipeline of three specialized agents: a Solver, a Proposer, and a Checker. |
| Outcome: | Extensive experiments across hallucination benchmarks demonstrate that MARCH substantially reduces hallucinism rates. |
Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models (2026.findings-acl)
Copied to clipboard
Xiaomeng Hu, Yixuan Tang, Haoze Li, Hao Chen, Qi Zhang, Zhanming Shen, Yiming Zhang, Haobo Wang, Junbo Zhao
| Challenge: | Prior work focused on data preprocessing, focusing on filtering and cleaning data . a study aimed to improve fine-grained scheduling of data order in epochs . |
| Approach: | They propose a fine-grained scheduling method of data order in epochs to fill this gap . they define data difficulty based on relevance between data and model . |
| Outcome: | The proposed method improves on pre-training and small-scale fine-tuning experiments 2.4% over baselines. |
CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations (2025.coling-main)
Copied to clipboard
Jiahao Zhao, Jingwei Zhu, Minghuan Tan, Min Yang, Renhao Li, Yang Di, Chenhao Zhang, Guancheng Ye, Chengming Li, Xiping Hu, Derek F. Wong
| Challenge: | CPsyExam prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios. |
| Approach: | They propose a psychological benchmark, CPsyExam, constructed from questions from Chinese examination systems. |
| Outcome: | The proposed benchmark prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios. |
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection rely on static and isolated representations, overlooking their dynamic evolution across layers. |
| Approach: | They propose a method which captures the cross-layer evolution of hidden states and propose 'ICR Probe' which capture the evolution of the hidden states. |
| Outcome: | The proposed method achieves superior performance with significantly fewer parameters and ablation studies offer deeper insights into the underlying mechanism of the method, improving its interpretability. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation (2024.emnlp-main)
Copied to clipboard
Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Mahong Xia, Zhang Li, Boxing Chen, Hao Yang, Bei Li, Tong Xiao, JingBo Zhu
| Challenge: | Existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset. |
| Approach: | They propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR). |
| Outcome: | The proposed method outperforms Alpaca's existing methods by 32.1% in GPT-4 evaluations. |
A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)
Copied to clipboard
Yikang Liu, Yeting Shen, Hongao Zhu, Lilong Xu, Zhiheng Qian, Siyuan Song, Kejia Zhang, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang, Hai Hu
| Challenge: | Using sub-linear length normalized log-probabilities (SLLN-LP), we find unequal lengths of sentences in minimal pairs difficult for LMs even up to 32B parameters. |
| Approach: | They propose to use ZhoBLiMP as a linguistic minimal pair benchmark for Chinese language models to mitigate biases. |
| Outcome: | The proposed metric mitigates biases in Chinese language models with over 100 paradigms . Anaphor, Quantifiers, and Ellipsis are difficult for LMs even up to 32B parameters . |
Suggest-Verify-Revise: A Three-Stage Document-Level Event Causality Identification with Narrative Consistency (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for document-level Event Causality Identification rely on local semantic similarity for independent event-pair discrimination . Existing approaches ignore the influence of the overall narrative backbone in the propagation of causal dependencies and the role differentiation of events within multi-cause/multi-effect structures. |
| Approach: | They propose a suggest-verify-revise approach for document-level Event Causality Identification with narrative consistency (SVRECI) they integrate heuristic causal suggestions generated by an LLM with structural suggestions derived from hypergraph modeling . |
| Outcome: | The proposed approach outperforms existing methods on event-storylines and Causal-TimeBank datasets. |
Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for hallucination mitigation are based on external dependency and require external annotations or auxiliary models for preference data collection. |
| Approach: | a new method is proposed to help model-generated hallucinations without external dependencies. |
| Outcome: | a new method that self-injects hallucinations into a generated response improves halluuutations mitigation. |
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)
Copied to clipboard
Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang
| Challenge: | Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information. |
| Approach: | They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format. |
| Outcome: | The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots. |
EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models (2025.findings-acl)
Copied to clipboard
Jiamin Su, Yibo Yan, Fangteng Fu, Zhang Han, Jingheng Ye, Xiang Liu, Jiahao Huo, Huiyu Zhou, Xuming Hu
| Challenge: | Automated Essay Scoring (AES) systems face three major challenges: reliance on handcrafted features that limit generalizability, difficulty in capturing fine-grained traits like coherence and argumentation, and inability to handle multimodal contexts. |
| Approach: | They propose a multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering. |
| Outcome: | The proposed system can evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering. |
MovieUN: A Dataset for Movie Understanding and Narrating (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Automatic movie narration generation and narration grounding are important to provide a true movie experience for the blind and visually impaired. |
| Approach: | They propose to use movie clips as a benchmark to support automatic movie narration generation and narration grounding tasks. |
| Outcome: | The proposed methods are effective in supporting two movie-based tasks for the blind and visually impaired. |
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)
Copied to clipboard
Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen
| Challenge: | Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities. |
| Approach: | They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance. |
| Outcome: | The proposed method achieves a superior balance between downstream learning and general capability retention. |
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)
Copied to clipboard
Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu
| Challenge: | Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves. |
| Approach: | They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop. |
| Outcome: | The proposed framework yields more stable training and higher long-horizon task success across open-world environments. |
Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings (2025.findings-acl)
Copied to clipboard
Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu
| Challenge: | Recent studies show that character substitutions in toxic Chinese text can confuse state-of-the-art LLMs. |
| Approach: | They propose a taxonomy of 3 perturbation strategies and 8 specific approaches in Chinese text to assess if they can detect perturbed Chinese toxic contents. |
| Outcome: | The proposed model can detect perturbed Chinese text with 8 different approaches . the proposed model is compared with 9 other LLMs from the US and China . |
DSCD: Large Language Model Detoxification with Self-Constrained Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for decoding large language models (LLMs) are based on external constraints and require additional resource overhead and loss of generation fluency. |
| Approach: | They propose a method for LLMs detoxification without parameter fine-tuning that strengthens the inner token distribution while weakening that of hallucination and toxic layer during output generation. |
| Outcome: | Extensive experiments on open-source LLMs and public datasets demonstrate DSCD's state-of-the-art (SOTA) performance in detoxification and generation fluency, with superior efficiency compared to existing methods. |
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)
Copied to clipboard
Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models. |
| Approach: | They propose a method that conducts customized evaluation tailored to each target model. |
| Outcome: | The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models. |
LitVISTA: A Benchmark for Narrative Orchestration in Literary Text (2026.acl-long)
Copied to clipboard
Mingzhe Lu, Yiwen Wang, Yanbing Liu, Qi You, Chong Liu, Ruize Qin, Haoyu Dong, Wenyu Zhang, JiaRui Zhang, Yue Hu, Yunpeng Li
| Challenge: | Existing large language models focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives. |
| Approach: | They propose a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space. |
| Outcome: | The proposed framework unifies human and model perspectives while jointly characterizing narrative function and structure in a common space. |
MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MultiPL is a special case of multiple natural languages and requires limited computational resources to generate multilingual code. |
| Approach: | They propose to extend LLMs by combining two paired experts to optimize expert selection at token and segment levels. |
| Outcome: | The proposed extension improves the performance of the base LLMs while retaining the most popular ones using limited computational resources. |
Datasets for Scientific Literature Understanding: A Survey (2026.findings-acl)
Copied to clipboard
| Challenge: | Empowering machines to understand scientific literature is crucial for accelerating scientific discovery and advancing the AI for Science paradigm. |
| Approach: | They propose a systematic taxonomy that organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning. |
| Outcome: | The proposed taxonomy organizes resources spanning structural understanding, text understanding, multimodal understanding and pre-training/instruction fine-tuning. |
Code Generation From Flowcharts with Texts: A Benchmark Dataset and An Approach (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, researchers focus on generating codes from requirement documents. |
| Approach: | They propose to generate source code from flowcharts with texts instead of directly translating requirements into codes. |
| Outcome: | The proposed model improves on the baselines by transforming flowcharts into pseudo-code . the proposed model is based on 320 flowchartes with their corresponding source codes . |
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu
| Challenge: | Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains. |
| Approach: | They propose a training framework that operationalizes this principle through coarse-to-fine budgeting. |
| Outcome: | Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines. |
Federated Model Decomposition with Private Vocabulary for Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train federated learning (FL) for natural language processing require sensitive data to leave local devices. |
| Approach: | They propose a fedrated model decomposition method that protects the privacy of vocabularies . they propose an adaptive updating technique to improve the performance of local models . |
| Outcome: | The proposed method protects the privacy of vocabularies in federated learning tasks . it maintains competitive performance and provides better privacy-preserving capacity compared to status quo methods. |
Improving Knowledge Graph Completion with Structure-Aware Supervised Contrastive Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing contrastive methods focus on individual triples, overlooking the broader structural connectivities and topologies of KGs. |
| Approach: | They propose a new contrastive learning framework that incorporates four tasks specifically tailored to KG data: Vertex-level CL, Neighbor-level Cl, Path-levelCL, and Relation composition level CL. |
| Outcome: | The proposed framework achieves SOTA performance under standard supervised and low-resource settings. |
Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)
Copied to clipboard
Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu
| Challenge: | Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling. |
| Approach: | They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space. |
| Outcome: | The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks. |
Localized Low-Rank Adaptation within Clustered Parameter Subspaces (2026.acl-long)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) for large language models has been successful in various domains. |
| Approach: | They propose to perform low-rank updates within clustered parameter subspaces . they group rows/columns of update matrix into locally coherent, uncorrelated subspace blocks . |
| Outcome: | Empirical results show that low-rank Adaptation (LoRA) is better than global adaptations in various domains. |
Causal Intervention for Abstractive Related Work Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability. |
| Approach: | They propose a Causal Intervention Module for Related Work Generation (CaM) that captures causal relationships in related work generation and implements causal interventions to mitigate the negative impact of spurious correlations. |
| Outcome: | The proposed framework improves the quality and coherence of generated related work by capturing causalities in the generation process. |
ELAD: Explanation-Guided Large Language Models Active Distillation (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are hindered by their memory inefficiency, computational demands, and the high costs of API inferences. |
| Approach: | They propose an Explanation-Guided LLMs Active Distillation framework that employs an active learning strategy to optimize the balance between annotation costs and model performance. |
| Outcome: | The proposed framework significantly improves the efficiency of LLMs knowledge distillation. |
EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning (2026.acl-long)
Copied to clipboard
Chuanrui Hu, Xingze Gao, Zuyi Zhou, Dannong Xu, Yi Bai, Xintong Li, Hui Zhang, Tong Li, Chong Zhang, Lidong Bing, Yafeng Deng
| Challenge: | Existing memory systems for LLMs store isolated records and retrieve fragments . Existing systems store isolated data and fragments, limiting their ability to consolidate evolving experience and resolve conflicts. |
| Approach: | They propose an engram-inspired memory operating system that implements an 'engram'-inspired lifecycle for computational memory. |
| Outcome: | Experiments on LoCoMo, LongMemEval, and PersonaMeM-v2 show that EverMemeOS outperforms state-of-the-art methods on memory-augmented reasoning tasks. |
Exploiting Abstract Meaning Representation for Open-Domain Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work attempts to address these challenges using Pretrained Language Models (PLMs) but the diversity of surface form expressions can hinder the model’s ability to capture accurate correlations, especially when the context is lengthy and complex. |
| Approach: | They propose a method known as Graph-as-Token (GST) to incorporate AMRs into PLMs to assist the model in understanding complex semantic information. |
| Outcome: | The proposed method outperforms existing methods and significantly improves performance on both Natural Questions and TriviaQA. |
LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing retrieval-based methods compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning. |
| Approach: | They propose a method that preserves local semantic coherence through boundary-aware chunking and constructs a recursive hierarchical index rooted in the triangle inequality. |
| Outcome: | The proposed method achieves 3.6 end-to-end inference speedup with negligible degradation in model performance. |
TEF: Causality-Aware Taxonomy Expansion via Front-Door Criterion (2025.coling-main)
Copied to clipboard
| Challenge: | Existing research still faces spurious query-anchor matching due to unobserved factors. |
| Approach: | They propose a model that uses the front-door criteria to decompose the expansion process into a parser module and a connector to isolate confounding effects. |
| Outcome: | Extensive experiments on three benchmarks validate the effectiveness of the proposed model. |
SubTokenTest: A Practical Benchmark for Real-World Sub-token Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks have highlighted character-level tasks as lacking practical relevance . many real-world applications rely heavily on precise sub-token understanding . |
| Approach: | They propose a benchmark that assesses sub-token understanding through practical tasks . they examine the impact of test-time scaling on sub-word reasoning . |
| Outcome: | The proposed benchmark assesses sub-token understanding through practical tasks . it includes ten tasks across four domains and isolates tokenization-related failures . |
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism (2025.findings-emnlp)
Copied to clipboard
Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu
| Challenge: | Large language models struggle with complex reasoning tasks, such as mathematical problem-solving. |
| Approach: | They constructed a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models when solving the task through direct answering and Chain-of-Thought (CoT) reasoning. |
| Outcome: | The proposed algorithm improves on 7 multi-step reasoning datasets, while introducing only 132 trainable parameters. |
Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)
Copied to clipboard
Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu
| Challenge: | Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols. |
| Approach: | They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations. |
| Outcome: | The proposed method reveals local knowledge conflicts invisible to existing benchmarks. |
“Yes, My LoRD.” Guiding Language Model Extraction with Locality Reinforced Distillation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for model extraction attacks on large language models are inadequate . existing methods neglect the inconsistency between training tasks and LLM alignment . |
| Approach: | They propose a model extraction algorithm that uses a policy-gradient-style training task to guide the crafting of preference for the local model. |
| Outcome: | The proposed algorithm reduces query complexity while mitigating watermark protection . it can extract various state-of-the-art commercial LLMs while minimizing query complexity . |
Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a method for user targeting is developed to identify online users to whom an ad should be targeted. |
| Approach: | They propose a method for automatic augmentation of positive and negative clickthrough data for user targeting models. |
| Outcome: | The proposed method can increase positive and negative instances of positive training instances on two datasets. |
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a problem of data contamination is now almost inevitable during the development of large language models, with the training data often integrating evaluation benchmarks even unintentionally. |
| Approach: | They propose a framework to restore model performance prior to data contamination on potentially leaked datasets by using contamination detection and disruption operation. |
| Outcome: | The proposed framework restores model performance prior to contamination on potentially leaked datasets. |
GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to generate data using LLMs are limited by sampling from the center of original content distribution. |
| Approach: | They propose a task-agnostic data generation and knowledge distillation framework for LLMs that employs an iterative out-of-distribution-guided feedback mechanism to generate data. |
| Outcome: | The proposed framework outperforms prior arts and the LLM on 10 different classification tasks and noisey generated data. |
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing text-to-image (T2I) synthesis diffusion models raise misuse concerns, particularly in creating prohibited or not-safe-for-work (NSFW) images. |
| Approach: | They propose a method which uses zeroth order optimization to procure gradient approximations and harnesses both C-PRV and D-PRv to enhance attack prompts within a discrete prompt space. |
| Outcome: | The proposed method achieves an 8.5% higher average attack success rate than previous works on multiple state-of-the-art safety mechanisms. |
Explicit Role Interaction Network for Event Argument Extraction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods extract arguments of each role independently, ignoring the relationship between different roles. |
| Approach: | They propose a neural model that captures the correlations between different argument roles within an event. |
| Outcome: | Extensive experiments on the benchmark dataset ACE2005 show the superiority of the proposed model over existing methods. |
Multimodal Dialogue Response Generation (2022.acl-long)
Copied to clipboard
Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang
| Challenge: | Existing studies focus on multimodal dialogue models but neglect generation methods. |
| Approach: | They propose a multimodal dialogue response generation task which requires multimodal dialogs containing both texts and images which are difficult to obtain. |
| Outcome: | Experiments show that the proposed model can generate informative text and high-resolution image responses. |
Cautious Next Token Prediction (2025.findings-acl)
Copied to clipboard
Yizhou Wang, Lingzhi Zhang, Yue Bai, Mang Tik Chiu, Zhengmian Hu, Mingyuan Zhang, Qihua Dong, Yu Yin, Sohrab Amirghodsi, Yun Fu
| Challenge: | Existing methods for decoding autoregressive models are temperature scaling and nucleus sampling to balance diversity and coherence. |
| Approach: | They propose a training-free decoding strategy that uses a model with a low perplexity score to select the trial with the lowest perplexities as the most probable and reliable path. |
| Outcome: | The proposed approach outperforms existing standard decoding strategies consistently by a clear margin. |
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases (2025.naacl-long)
Copied to clipboard
Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu, Zhicheng Zhang, Fei Wang, Michael Qizhe Shieh, Wenmeng Zhou
| Challenge: | Large Language Models excel in stand-alone code tasks but struggle with handling entire code repositories. |
| Approach: | They propose a system that integrates LLM agents with graph database interfaces extracted from code repositories. |
| Outcome: | The proposed system integrates LLM agents with graph database interfaces extracted from code repositories. |
Reduce Redundancy Then Rerank: Enhancing Code Summarization with a Novel Pipeline Framework (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing code summarization models lack redundant tokens and are plagued by exposure bias. |
| Approach: | They propose a pipeline framework to reduce redundancy then rerank that eliminates redundant information in code representation space and a re-ranking model to select more suitable summary candidates. |
| Outcome: | The proposed framework overrides state-of-the-art approaches on six datasets from the CodeSearchNet benchmark. |
ComfyFlow: Benchmarking LLMs for AIGC Workflow Generation (2026.findings-acl)
Copied to clipboard
Zhenran Xu, Yiyu Wang, Yunxin li, Muyang Ye, null Yangxue, Kai Chen, Longyue Wang, Weihua Luo, Baotian Hu, Min Zhang
| Challenge: | Large language models (LLMs) have shown promising advances in tackling human-level tasks, but generating workflows for collaborative AI systems remains a critical and challenging step. |
| Approach: | They propose a benchmark to evaluate LLMs’ ability to generate executable and instruction-following AIGC workflows in ComfyUI. |
| Outcome: | The proposed benchmarks show that LLMs can generate executable and instruction-following AIGC workflows in ComfyUI. |
What Factors Affect LLMs and RLLMs in Financial Question Answering? (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on large language models and reasoning large language model (RLLMs) however, there are few studies that explore what methods can fully unlock the performance of LLMs and RLLM in the financial domain. |
| Approach: | They examine the effects of prompting methods, agentic frameworks, and multilingual alignment methods on financial question-answering tasks. |
| Outcome: | The results show that prompting methods and agent frameworks improve LLMs' performance . the authors suggest that these frameworks can be used to enhance LLM performance if they are implemented in financial domains. |
TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token Merging (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that multimodal large language models can be useful for chart understanding, but their size limits their use in resource-constrained environments. |
| Approach: | They propose an efficient multimodal large language model with only 3B parameters for chart understanding. |
| Outcome: | The proposed model outperforms several chart-understanding MLLMs with up to 13B parameters on ChartQA, Chart-to-Text, Chart to Table, OpenCQA, and ChartX. |
LaMemo: Language Modeling with Look-Ahead Memory (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to model long-term dependencies are limited to long texts with thousands of words. |
| Approach: | They propose a look-ahead memory that augments the recurrence memory by attending to the right-side tokens and interpolating with the old memory states to maintain long-term information in the history. |
| Outcome: | Experiments on widely used language modeling benchmarks show that LaMemo outperforms baseline models with recurrence memory. |
WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing web agents struggle with complex tasks due to rigid planning strategies and hallucination-prone reasoning. |
| Approach: | They propose a task-uncertainty-driven Adaptive Planning Mechanism that adaptively selects planning modes to navigate unknown environments. |
| Outcome: | The proposed framework performs better on the WebArena and WebVoyager benchmarks than existing frameworks. |
UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions (2025.findings-acl)
Copied to clipboard
Xunzhi Wang, Zhuowei Zhang, Gaonan Chen, Qiongyu Li, Bitong Luo, Zhixin Han, Haotian Wang, Zhiyu Li, Hang Gao, Mengting Hu
| Challenge: | Existing methods for benchmarking the uncertainty of large language models face challenges . existing methods require internal model access, additional training, or high computational costs . |
| Approach: | They propose a new benchmark for evaluating the uncertainty of large language models based on confidence intervals . UBench encompasses 11,978 multiple choice questions spanning knowledge, language, understanding, and reasoning capabilities. |
| Outcome: | The proposed method outperforms existing methods for benchmarking the uncertainty of large language models. |
GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models (2025.findings-acl)
Copied to clipboard
Mufan Qiu, Xinyu Hu, Fengwei Zhan, Sukwon Yun, Jie Peng, Ruichen Zhang, Bhavya Kailkhura, Jiekun Yang, Tianlong Chen
| Challenge: | Foundation models for single-cell RNA sequencing ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals. |
| Approach: | They propose a framework that integrates multi-scale gene regulatory networks into RNA foundation model training. |
| Outcome: | The proposed framework improves on state-of-the-art models on three downstream tasks . it integrates multi-scale gene regulatory networks (GRNs) from multi-omics data into training . |
Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior studies have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information. |
| Approach: | They propose to conduct a fine-grained analysis of large language models using a dataset Biography-Reasoning and QA and knowledge reasoning tasks to understand their findings. |
| Outcome: | The proposed model is able to perform a range of downstream tasks without requiring a large amount of knowledge and is compared with a control dataset. |
LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)
Copied to clipboard
Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu
| Challenge: | Large language model (LLM) routing assigns each query to the best suitable model from an ensemble. |
| Approach: | They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation . |
| Outcome: | The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing. |
Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multitask learning fail to address task interference issues . Existing methods focus on task balancing or probabilistic modeling but fail to learn sufficient representations for all target tasks. |
| Approach: | They propose a multi-task representation alignment framework to achieve task-specific alignment and self-alignment on shared representations from a mutual information perspective. |
| Outcome: | The proposed framework outperforms 13 representative MTL methods under label-noisy and data-constrained conditions. |
Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for low-resource dialogue summarization neglect the difference between dialogues and conventional articles. |
| Approach: | They propose a multi-source pretraining paradigm to leverage external summary data . they exploit large-scale in-domain non-summary data to separate dialogue encoder and summary decoder . |
| Outcome: | The proposed model can be used to better leverage external summary data. |
SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model (2024.emnlp-demo)
Copied to clipboard
Dayong Wu, Jiaqi Li, Baoxin Wang, Honghong Zhao, Siyuan Xue, Yanjie Yang, Zhijun Chang, Rui Zhang, Li Qian, Bo Wang, Shijin Wang, Zhixiong Zhang, Guoping Hu
| Challenge: | Large language models (LLMs) have shown remarkable achievements across various language tasks. |
| Approach: | They propose a scientific literature LLM and a knowledge service system based on it . they collect scientific literature and then pre-train it using autoregressive training . |
| Outcome: | The proposed system provides literature investigation, paper reading, and academic writing functions. |
From Remembering to Metacognition: Do Existing Benchmarks Accurately Evaluate LLMs? (2025.findings-emnlp)
Copied to clipboard
Geng Zhang, Yizhou Ying, Sihang Jiang, Jiaqing Liang, Guanglei Yue, Yifei Fu, Hailin Hu, Yanghua Xiao
| Challenge: | Existing benchmark datasets focus on low-level cognitive tasks while providing limited coverage of higher-level reasoning skills. |
| Approach: | They analyze the cognitive depth of popular LLM benchmarks using Bloom’s Taxonomy to evaluate both the cognitive and knowledge dimensions. |
| Outcome: | The results show that incorporating higher-level cognitive instructions into the current instruction fine-tuning process improves model performance. |
ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models (2025.findings-acl)
Copied to clipboard
Hao Chen, Haoze Li, Zhiqing Xiao, Lirong Gao, Qi Zhang, Xiaomeng Hu, Ningtao Wang, Xing Fu, Junbo Zhao
| Challenge: | Prior research has focused on optimizing general-purpose large language models to downstream tasks . however, these approaches inherently introduce data dependency, which hinders generalization and reusability. |
| Approach: | They propose an algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs. |
| Outcome: | The proposed algorithm achieves 2% performance improvement over baselines on three tasks while localizing the most task-sensitive attention heads. |
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)
Copied to clipboard
Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong
| Challenge: | Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models. |
| Approach: | They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. |
| Outcome: | The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. |
DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision (2025.emnlp-industry)
Copied to clipboard
Yongqi Leng, Yikun Lei, Xikai Liu, Meizhi Zhong, Bojian Xiong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong
| Challenge: | Recent advances in outcome-supervised reinforcement learning (RL) have shown strong performance, but this approach still suffers from inefficient exploration, sparse reward signals, and ambiguous global reward feedback. |
| Approach: | They propose a model that models RAG as a Markov Decision Process (MDP) and introduces an efficient pruning strategy to optimize data expansion. |
| Outcome: | The proposed model outperforms existing methods and achieves an average performance improvement of 6.2% across six datasets. |
CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling (2024.findings-acl)
Copied to clipboard
Chenhao Zhang, Renhao Li, Minghuan Tan, Min Yang, Jingwei Zhu, Di Yang, Jiahao Zhao, Guancheng Ye, Chengming Li, Xiping Hu
| Challenge: | Existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence. |
| Approach: | They propose a report-based multi-turn dialogue reconstruction framework for Chinese psychological counseling that uses large language models to assist counseling. |
| Outcome: | The proposed framework is open-source and can be used in future research. |
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)
Copied to clipboard
| Challenge: | End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it. |
| Approach: | They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency . |
| Outcome: | The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks. |
Nature-Inspired Population-Based Evolution of Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | a new framework for population-based evolution of large language models is emerging . a population-driven evolution of LLMs is a key component of evolution, authors say . |
| Approach: | They propose a framework that allows for population-based evolution of large language models . they start with a population of parent LLMs and allow this population to evolve . |
| Outcome: | The proposed framework outperforms existing methods on 12 datasets. |
AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking (2025.findings-emnlp)
Copied to clipboard
Ding-Chu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu, Xiao-Wen Yang, Zhi Zhou, Baixuan Li, Yu-Feng Li, Xing Shi, Wei Lin
| Challenge: | Existing automated generation methods exhibit Weak Applicability and Weak Scalability . existing methods are limited by their reliance on metadata from specific corpora . |
| Approach: | They propose an approach to generate scalable RAG benchmarks using corpus-agnostic methods . they propose a difficulty-guided metric that directs query evolution process . |
| Outcome: | The proposed approach evolves queries significantly more challenging than existing methods . it is able to dynamically increase difficulty, limiting scalability of the query . |
Let’s Simplify Step by Step: Guiding LLM Towards Multilingual Unsupervised Proficiency-Controlled Sentence Simplification (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models demonstrate limited capability in proficiency-controlled sentence simplification when simplifying across large readability levels. |
| Approach: | They propose a framework that decomposes complex simplifications into manageable steps through dynamic path planning, semantic-aware exemplar selection, and chain-of-thought generation with conversation history for coherent reasoning. |
| Outcome: | The proposed framework reduces computational steps while improving simplification effectiveness on five languages across two benchmarks. |
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing RAG performance rely on heuristic-based augmentation . Existing approaches rely heavily on a heuriistic-driven approach, resulting in poor generalization and skews in the evidence length. |
| Approach: | They propose a model-based evidence extraction learning framework that optimizes a vanilla model as an evidence extractor with desired properties through self-aligned learning. |
| Outcome: | The proposed method reduces the evidence length by 9.25 times and improves reliability and reliability. |
TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Industry Systems (2024.emnlp-industry)
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
| 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. |
Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking (2025.acl-long)
Copied to clipboard
Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Shaokai Chen, Mengshu Sun, Binbin Hu, Zhiqiang Zhang, Lei Liang, Wen Zhang, Huajun Chen
| Challenge: | Existing methods to integrate external knowledge into LLMs focus on specific problems, lacking a comprehensive exploration of the generalization and capability boundaries of SKP. |
| Approach: | They propose a new paradigm for structural knowledge prompting to integrate external structural knowledge into LLMs by incorporating structural representations. |
| Outcome: | The proposed benchmark SUBARU enables the evaluation of the generalization capabilities of SKP from four perspectives. |
TWEET-FID: An Annotated Dataset for Multiple Foodborne Illness Detection Tasks (2022.lrec-1)
Copied to clipboard
| Challenge: | Approximately 1 in 6 Americans (or 48 million people) are sickened by foodborne illness each year. |
| Approach: | They propose to use Twitter's TWEET-FID dataset to create annotated datasets for multiple foodborne illness incident detection tasks. |
| Outcome: | The proposed dataset is the first publicly available annotated dataset for multiple foodborne illness incident detection tasks. |
TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing auto-regressive pre-trained language models are challenged by recent emerging numerical reasoning datasets due to the error-prone implicit calculation. |
| Approach: | They propose a pre-computation tool to pre-compute aggregation/arithmetic results for the table in advance, so they are handy and readily available for PLMs to answer numerical reasoning questions. |
| Outcome: | The proposed model improves on TAT-QA and T5 and BART-large on multiple benchmarks. |
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing routing strategies rely on local token probabilities or post-hoc verification, introducing significant inference overhead. |
| Approach: | They propose a step-wise collaboration framework that generates only the first token of each reasoning step and routes it to a larger model only when initial token entropy exceeds a threshold. |
| Outcome: | The proposed approach reduces inference latency while preserving accuracy. |
QueryLink: Leveraging Query-Memory Alignment for Long-Term Reasoning in LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to integrating external memory prioritize memory organization while overlooking a critical semantic gap between implicit, intent-driven queries and explicit, narrative-based memories. |
| Approach: | They propose a framework that leverages Query-Memory Alignment to project both queries and memories into a shared semantic space. |
| Outcome: | The proposed framework significantly outperforms SOTA methods on the LoCoMo and LongMemEval benchmarks and can be integrated as a plug-and-play component to boost existing vector-based systems like A-MEM. |
Multi 3 WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems (2023.tacl-1)
Copied to clipboard
Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen
| Challenge: | Task-oriented dialog (TOD) is one of the central objectives, hallmarks, and applications of machine intelligence. |
| Approach: | They propose a multilingual, multi-domain, multiparallele ToD dataset that offers culturally adapted dialogs in 4 languages for training and evaluation of multilingual and cross-lingual systems. |
| Outcome: | The proposed dataset is large-scale and culturally adapted to enable training and evaluation of multilingual and cross-lingual ToD systems. |
Unveiling the Potential of BERT-family: A New Recipe for Building Scalable, General and Competitive Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Generative large language models (LLMs) have significantly influenced various aspects of society, reshaping how we access and interact with information and knowledge. |
| Approach: | They propose a pre-training task that helps BERT-family excel in wider applications . they also explore the integration of cutting-edge technologies into their models to further enhance their capabilities. |
| Outcome: | The proposed model exhibits performance levels comparable to current SOTA LLMs across a spectrum of tasks. |
Bootstrapping Code Translation with Weighted Multilanguage Exploration (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve code translation depend on abundant parallel code of high quality, which may not always be available. |
| Approach: | They propose a method that leverages functional invariance and cross-lingual portability of test suites to serve as universal verification oracles for multilingual reinforcement learning. |
| Outcome: | The proposed method leverages functional invariance and cross-lingual portability of test suites to serve as universal verification oracles for multilingual reinforcement learning (RL) training. |
Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)
Copied to clipboard
Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao
| Challenge: | Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs . |
| Approach: | They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained . |
| Outcome: | The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency. |
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)
Copied to clipboard
Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song
| Challenge: | Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage. |
| Approach: | They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality. |
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. |
LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models (2025.findings-naacl)
Copied to clipboard
Kaichen Zhang, Bo Li, Peiyuan Zhang, Fanyi Pu, Joshua Adrian Cahyono, Kairui Hu, Shuai Liu, Yuanhan Zhang, Jingkang Yang, Chunyuan Li, Ziwei Liu
| Challenge: | Current large foundational models have demonstrated transformative capabilities, approaching or surpassing human-level performances in many tasks. |
| Approach: | They propose a unified and standardized multimodal benchmark framework with over 50 tasks and more than 10 models to promote transparent and reproducible evaluations. |
| Outcome: | The proposed framework has 50 tasks and more than 10 models to promote transparent and reproducible evaluations. |
TrojanSQL: SQL Injection against Natural Language Interface to Database (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on text-to-SQL systems have not investigated its security aspects . however, how to implement such attacks remains an open question. |
| Approach: | They propose a backdoor-based SQL injection framework for text-to-SQL systems that uses boolean-based injection and union-based injecting techniques to exploit SQL injection vulnerabilities. |
| Outcome: | The proposed framework can produce harmful SQL statements invalidating user queries or compromise sensitive information about the database. |
Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties (2024.emnlp-main)
Copied to clipboard
| Challenge: | Emergent In-context Learning on Videos induces in-contact learning over video and text . eILeV-trained models outperform other off-the-shelf VLMs in few-shot video narration for novel, rare actions. |
| Approach: | They implement Emergent In-context Learning on Videos (EILeV) that induces in-contact learning over video and text by capturing key properties of pre-training data. |
| Outcome: | The proposed training paradigm outperforms off-the-shelf VLMs in few-shot video narration for novel, rare actions. |
Integrating Semantic Scenario and Word Relations for Abstractive Sentence Summarization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing graph-based methods only consider word relations or structure information, which neglect the correlation between them. |
| Approach: | They propose a Dual Graph network for Abstractive Sentence Summarization that captures word relations and structure information from sentences. |
| Outcome: | The proposed model outperforms state-of-the-art methods on two popular benchmark datasets. |
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)
Copied to clipboard
Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li
| Challenge: | Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). |
| Approach: | They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning. |
| Outcome: | The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks. |
Knowledge-Centric Hallucination Detection (2024.emnlp-main)
Copied to clipboard
Xiangkun Hu, Dongyu Ru, Lin Qiu, Qipeng Guo, Tianhang Zhang, Yang Xu, Yun Luo, Pengfei Liu, Yue Zhang, Zheng Zhang
| Challenge: | Large Language Models (LLMs) have shown impressive capabilities but a tendency to hallucinate. |
| Approach: | They propose a framework that introduces claim-triplets to represent claims in LLM responses and evaluates them against a reference. |
| Outcome: | The proposed framework outperforms prior methods by 18.2 to 27.2 points on a benchmark spanning various NLP tasks and annotated 11k claim-triplets from 2.1k responses by seven LLMs. |
FEDLEGAL: The First Real-World Federated Learning Benchmark for Legal NLP (2023.acl-long)
Copied to clipboard
| Challenge: | federated learning (FL) is a promising technique for preserving data privacy . however, there is no work on applying FL to legal NLP . |
| Approach: | They propose to use federated learning to train models in a collaborative way without sharing data . they propose to test the FL benchmark on real-world legal data from Chinese courts . |
| Outcome: | The proposed benchmark combines five legal NLP tasks and one privacy task on Chinese courts. |
DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)
Copied to clipboard
Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability. |
| Approach: | They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence. |
| Outcome: | The proposed model outperforms baselines on three real-world datasets. |
Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future (2026.acl-long)
Copied to clipboard
Sihong Wu, Owen Jiang, Yilun Zhao, Tiansheng Hu, Yiling Ma, Kaiyan Zhang, Manasi Patwardhan, Arman Cohan
| Challenge: | Recent advances in large language models (LLMs) motivated methods that assist or automate different stages of peer review pipeline. |
| Approach: | They synthesize techniques to enhance peer review generation and after-review tasks aligned to reviews. |
| Outcome: | The proposed methods improve the peer review process by fine-tuning strategies, agent-based systems, and emerging paradigms. |
MoDification: Mixture of Depths Made Easy (2025.naacl-long)
Copied to clipboard
Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song
| Challenge: | Long-context efficiency is a trending topic in large language model (LLM) serving. |
| Approach: | They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory. |
| Outcome: | The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications. |
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation (2026.acl-long)
Copied to clipboard
Xi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu, Zhuxuanzi Wang, Yanshu Li, Lin Zhao, Guosheng Hu, Tianyang Wang, Hao Xu
| Challenge: | Low-Rank Adaptation (LoRA) is a key parameter-efficient fine-tuning method . however, its effectiveness is hampered by semantic drift and structural incoherence . |
| Approach: | They propose a low-rank Adaptation framework that tackles semantic drift and structural incoherence by pruning task-irrelevant directions. |
| Outcome: | Experiments on large language models, vision models, and vision models show that the proposed framework outperforms LoRA and advanced dynamic rank allocation and sparsity-based methods. |
Reinforcement Learning for Large Language Models via Group Preference Reward Shaping (2025.emnlp-main)
Copied to clipboard
Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Zhimeng Guo, Shijie Zhou, Shuyue Hu, Vasant G. Honavar
| Challenge: | Existing methods for fine-tuning Large Language Models (LLMs) are expensive and sensitive to reward model quality. |
| Approach: | They propose a method that leverages preference-based comparisons rather than precise numerical rewards. |
| Outcome: | Experiments show that GPRS outperforms critic-model-free RL algorithms on RLHF and reasoning tasks. |
RECAL: Sample-Relation Guided Confidence Calibration over Tabular Data (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Various machine learning methods for tabular data lack accurate confidence estimation, which is needed for high-risk sensitive applications such as credit modeling and financial fraud detection. |
| Approach: | They propose a general post-training confidence calibration framework to calibrate the confidence of current machine learning models by employing graph neural networks to model the relationships between different samples. |
| Outcome: | The proposed framework improves the confidence estimation on tabular datasets by using graph neural networks to model the relationships between different samples. |
Adaptive Zooming via Relevance-Informed Positional Resource Allocation for Training-free LLM Context Extension (2026.findings-acl)
Copied to clipboard
Hongbo Zhao, Huibin Wang, Bin Tang, Xianming Hu, Yihong Huang, Yijun Shen, Nuoyi Chen, Ping Li, Kai Zhang
| Challenge: | Existing training-free methods for extrapolating beyond training context lengths are semantics-agnostic . Existing methods that focus on relative token distances can indiscriminately blur semantically relevant and irrelevant tokens . |
| Approach: | They propose an adaptive positional zooming method that uses semantic relevance to extrapolate beyond training context lengths. |
| Outcome: | Experiments show that RiPRA outperforms existing training-free extrapolation methods . relevant tokens get higher positional resolution, while irrelevant tokens are compressed . |
Speeding up Transformer Decoding via an Attention Refinement Network (2022.coling-1)
Copied to clipboard
| Challenge: | Extensive experiments on ten WMT machine translation tasks show that the proposed model yields an average of 1.35x faster (with almost no decrease in BLEU) |
| Approach: | They propose a weighted residual network which reconstructs attention by reusing the features across layers. |
| Outcome: | The proposed model is 1.35x faster than the state-of-the-art inference model on translation tasks compared to AAN and SAN models with fewer parameter numbers . |
An Unsupervised Multiple-Task and Multiple-Teacher Model for Cross-lingual Named Entity Recognition (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models for named entity recognition only consider the potential transferability between two identical tasks across both domains. |
| Approach: | They propose to use a similarity metric model to improve cross-lingual named entity recognition task on target domain. |
| Outcome: | Empirical studies on 7 different languages confirm the effectiveness of the proposed model. |
Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods (2026.acl-long)
Copied to clipboard
| Challenge: | Large Vision-Language Models (LVLMs) excel at visual understanding but face severe computational bottlenecks when processing high-resolution images and long videos due to massive visual token counts. |
| Approach: | They propose a taxonomy categorizing methods into vision-side, LLM-side and hybrid paradigms and analyze token selection mechanisms and pruning strategy. |
| Outcome: | The proposed method selectively removes less informative tokens while maintaining performance. |
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)
Copied to clipboard
Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context. |
| Approach: | They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts. |
| Outcome: | The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context. |
Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective (2025.coling-main)
Copied to clipboard
| Challenge: | Enabling LLMs to handle lengthy context is currently a research hotspot . a notable challenge limiting further customization is the inability of LLM to utilize context beyond pretrained length due to the inherent flaw of rotary position embedding (RoPE). |
| Approach: | They propose to extend the RoPE from an attention perspective and on two benchmarking tasks. |
| Outcome: | The proposed extension of the RoPE improves extrapolation and retrieval errors. |
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)
Copied to clipboard
Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu
| Challenge: | Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability . |
| Approach: | They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR . |
| Outcome: | The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks. |
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents (2025.findings-emnlp)
Copied to clipboard
Pengzhou Cheng, Haowen Hu, Zheng Wu, Zongru Wu, Tianjie Ju, Daizong Ding, Zhuosheng Zhang, Gongshen Liu
| Challenge: | MLLM-powered GUI agents expose multiple interaction-level triggers, causing backdoor attacks . backdoor injection maximizes feature difference across sample classes, improving flexibility . |
| Approach: | They propose a framework for red-teaming backdoor attacks using MLLMs . they construct composite triggers by combining goal and interaction levels . |
| Outcome: | The proposed framework is effective and stealthy for red-teaming backdoor attacks. |
UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)
Copied to clipboard
Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang
| Challenge: | Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. |
| Approach: | They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances . |
| Outcome: | The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks. |
Beyond the Surface: Measuring Self-Preference in LLM Judgments (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods measure self-preference bias by comparing the scores a judge model assigns to its own responses with those assigned to other models. |
| Approach: | They propose to use gold judgments as proxies for the actual quality of responses . they propose to measure self-preference bias as the difference between the judge model's own and other models' scores . |
| Outcome: | The proposed method can assess self-preference bias across large language models . it uses gold judgments as proxies for the ground truth scores of the judge model . |
P3: Prompts Promote Prompting (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in prompt optimization have shown effectiveness of using multiple components to optimize models . however, such unilateral approaches often yield suboptimal results due to interdependent nature of these components. |
| Approach: | They propose a self-improvement framework that optimizes both system and user prompts . they use offline optimized prompts to promote online prompt optimization . |
| Outcome: | The proposed framework improves performance on general and reasoning tasks. |
Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains (2026.acl-long)
Copied to clipboard
Zhonghang Yuan, Zhefan Wang, Fang Hu, Zihong Chen, Jinzhe Li, Gang Li, Jie Ying, Huanjun Kong, Songyang Zhang, Nanqing Dong
| 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. |
Revisiting Sparse Retrieval for Few-shot Entity Linking (2023.emnlp-main)
Copied to clipboard
| Challenge: | Entity linking (EL) aims to link ambiguous mentions to their corresponding entities in a knowledge base. |
| Approach: | They propose an ELECTRA-based keyword extractor to denoise the mention context and construct a better query expression. |
| Outcome: | The proposed method outperforms state-of-the-art models on the ZESHEL dataset by a significant margin. |
Improving Multilingual Sign Language Translation with Automatically Clustered Language Family Information (2025.coling-main)
Copied to clipboard
| Challenge: | Recent research has focused on bilingual translation models, but multilingual sign language translation presents unique challenges due to the diversity of sign languages across nations. |
| Approach: | They propose a method that leverages sign language families to improve MSLT performance. |
| Outcome: | The proposed approach can achieve balance between translation accuracy and computational cost by regulating the number of language families. |
How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have validated that large language models (LLMs) are capable of solving some KBQA problems, but there has been little discussion on the differences in LLMs’ proficiency in formal languages used in semantic parsing. |
| Approach: | They propose to evaluate the understanding and generation ability of large language models (LLMs) to deal with differently structured logical forms by examining the inter-conversion of natural and formal language through in-context learning of LLMs. |
| Outcome: | The proposed model can understand formal languages as well as humans, but generating correct logical forms remains a challenge. |
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal retrieval-augmented generation rely on semantic relevance or surface-level similarity, which are often misaligned with the actual utility of visual evidence for downstream reasoning. |
| Approach: | They propose a latent notion of evidence usefulness and propose 'surrogate-accelerated' framework that efficiently estimates evidence utility using lightweight multimodal models. |
| Outcome: | The proposed framework outperforms state-of-the-art models while achieving substantial reductions in computational cost. |
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)
Copied to clipboard
Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun
| Challenge: | Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks. |
| Approach: | They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions. |
| Outcome: | The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. |
FastSeq: Make Sequence Generation Faster (2021.acl-demo)
Copied to clipboard
Yu Yan, Fei Hu, Jiusheng Chen, Nikhil Bhendawade, Ting Ye, Yeyun Gong, Nan Duan, Desheng Cui, Bingyu Chi, Ruofei Zhang
| Challenge: | Transformer-based models have made tremendous impact in natural language generation, but inference speed is still a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. |
| Approach: | They propose an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O to accelerate sequence generation without loss of accuracy. |
| Outcome: | The proposed framework can accelerate the sequence generation by 4x to 9x with a simple one-line code change for a set of widely used and diverse models. |
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on syntactically controlled paraphrase generation rely on large-scale parallel data. |
| Approach: | They propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder which can generate texts in a specified syntastic structure. |
| Outcome: | The proposed model can generate diverse paraphrases with specified syntactic structure using non-parallel data. |
TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | specialized language models do not show simultaneous memory saving and inference speedup at deployment time. |
| Approach: | They develop a layer-wise specialization technique that reduces the depth of LLMs by progressive layer dropping and compares it to other algorithms for inference. |
| Outcome: | The proposed model retains LLMs’ capacity in specific domains and achieves inference speedup irrespective of hardware and deep learning frameworks. |
CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on “factual statements” that rephrase source materials, but ignore “cognitive statements” . evaluating and detecting "faithfulness hallucinations" remains challenging . |
| Approach: | They propose a framework to assess faithfulness of cognitive statements and introduce a dataset to scale easily across models. |
| Outcome: | The proposed framework assesses faithfulness of cognitive statements and scales easily across models. |
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design (2026.acl-industry)
Copied to clipboard
| Challenge: | a novel extension of neural scaling laws to Mixture-of-Experts models is proposed . a ratio of expert-attention compute is crucial for efficient MoE models . |
| Approach: | They propose an extension of neural scaling laws to Mixture-of-Experts (MoE) models . they define the ratio r as the fraction of total FLOPs per token dedicated to expert and attention layers . |
| Outcome: | The proposed model can be tuned beyond size and data with the proposed model. |
Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)
Copied to clipboard
Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang
| Challenge: | Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking. |
| Approach: | They propose an iterative adversarial training method that incorporates three key innovations to address these challenges. |
| Outcome: | Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%. |
A Decoupled Multi-Agent Framework for Complex Text Style Transfer (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for text style transfer struggle with complex styles . existing models perform well on simple styles like sentiment and formality . |
| Approach: | They propose a multi-agent self-check framework that includes a large language model as a planner for disentangling subtasks and expert agents for executing the subtask. |
| Outcome: | The proposed framework significantly improves style strength and content preservation on simple and complex style datasets. |
Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches involve models iterating and improving their previous responses based on internal reflection ability or external feedback. |
| Approach: | They propose a reflection framework that leverages meta-thoughts and self-consistency to enhance the iterative reflection capability of Large LanguageModels. |
| Outcome: | The proposed framework achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability. |
RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on social media text processing do not focus on responsive emotion analysis. |
| Approach: | They propose a Chinese dataset named ResEmo for responsive emotion analysis, including 3813 posts with 68,781 comments collected from Weibo, the largest social media platform in China. |
| Outcome: | The proposed dataset includes 3813 posts with 68,781 comments collected from weibo, the largest social media platform in China. |
ReEfBench: Quantifying the Reasoning Efficiency of LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Chain-of-Thought evaluations do not distinguish between genuine reasoning and mere verbosity. |
| Approach: | They propose a framework for the non-intrusive, comprehensive process-centric evaluation of reasoning grounded in First-Order Logic. |
| Outcome: | The proposed framework identifies four distinct behavioral prototypes and diagnoses the failure modes. |
D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering (2025.emnlp-main)
Copied to clipboard
Guangze Gao, Zixuan Li, Chunfeng Yuan, Jiawei Li, Wu Jianzhuo, Yuehao Zhang, Xiaolong Jin, Bing Li, Weiming Hu
| Challenge: | Existing approaches to Knowledge Graph Question Answering (KGQA) use Retrieval-Augmented Generation (RAG) but subgraph selection process is non-differentiable, preventing end-to-end training of the retriever and the generator. |
| Approach: | They propose a Differentiable RAG approach that optimizes the retriever and the generator for KGQA. |
| Outcome: | The proposed approach outperforms state-of-the-art approaches on WebQSP and CWQ. |
FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)
Copied to clipboard
Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Shuaiyu Zhang, Shiyang Feng, Xiangchao Yan, Shufei Zhang, Wenlong Zhang, Lei Bai, Bo Zhang
| Challenge: | FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. |
| Approach: | They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. |
| Outcome: | The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download. |
Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing non-simultaneous sign language translation methods suffer from inherent inference delays in real-time scenarios. |
| Approach: | They propose an adaptive policy for simultaneous sign language translation that progressively converts incrementally received sign video into its corresponding natural sentence. |
| Outcome: | The proposed policy excels in situations requiring extremely low latency. |
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models face quadratic computational costs, information forgetting, and context fragmentation . current methodologies diverge into three paradigms, each facing inherent trade-offs between Equal contribution. |
| Approach: | They propose a framework that enables efficient long-context inference via chunk-wise compression and selective memory recall. |
| Outcome: | The proposed framework reduces peak GPU memory usage and speeds up inference on multi-hop reasoning benchmarks. |
DataSciBench: An LLM Agent Benchmark for Data Science (2026.findings-acl)
Copied to clipboard
Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, Yisong Yue
| Challenge: | Existing benchmarks focus on single task, simple evaluation metrics, and readily available ground truth (GT) DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT. |
| Approach: | They propose a benchmark for evaluating Large Language Models in data science that integrates LLM-based self-consistency and human verification to ensure accuracy. |
| Outcome: | The proposed framework outperforms open-source models in all metrics and offers rigorous insights into LLM strengths and weaknesses. |
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback (2025.findings-emnlp)
Copied to clipboard
Minda Hu, Tianqing Fang, Jianshu Zhang, Jun-Yu Ma, Zhisong Zhang, Jingyan Zhou, Hongming Zhang, Haitao Mi, Dong Yu, Irwin King
| Challenge: | Web agents powered by Large Language Models lack the ability to perform in uncertain web environments. |
| Approach: | They propose to reconstruct web agents' reasoning skills into chain-of-thought rationales by fine-tuning their LLM backbone into a web-based model. |
| Outcome: | The proposed approach significantly improves the agent self-improving benchmark OpenWebVoyager, demonstrating that it can be used to improve the agent's reasoning skills. |
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models with seq2seq framework lack ability to effectively manage concept transitions . lack of concept management strategies might lead to incoherent dialogue due to loosely connected concepts . |
| Approach: | They propose a concept-guided non-autoregressive model for open-domain dialogue generation that learns to identify multiple associated concepts from a conceptual graph and a customized Insertion Transformer to perform concept-directed generation to complete a response. |
| Outcome: | The proposed model outperforms state-of-the-art models in automatic and human evaluations with substantially faster inference speed. |
Inductive Relation Prediction with Logical Reasoning Using Contrastive Representations (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for relation prediction in knowledge graphs (KGs) are limited by the inductive setting because entities in training process are finite. |
| Approach: | They propose a graph convolutional network-based model LogCo with logical reasoning by contrastive representations that extracts subgraphs and relational paths between two entities to supply the entity-independence. |
| Outcome: | The proposed model outperforms existing methods on twelve inductive datasets. |
Tackling Long Code Search with Splitting, Encoding, and Aggregating (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing pretraining models take the first 256 tokens of code snippets by default, limiting the input length to 512. |
| Approach: | They propose a baseline SEA model which splits long code into code blocks and aggregates them to obtain a comprehensive long code representation. |
| Outcome: | The proposed model can model long code without changing their internal structure and re-pretraining. |
WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing GUI agents perform poorly on multi-application tasks, stalling at early sub-goals. |
| Approach: | They propose to assess GUI Agents on complex multi-step tasks that mirror real-world professions. |
| Outcome: | The proposed benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. |
Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation (2026.acl-short)
Copied to clipboard
| Challenge: | Large reasoning models such as DeepSeek-R1 and their distilled variants achieve impressive performance on complex reasoning tasks, yet their costs remain substantial. |
| Approach: | They propose a skill-centric distillation framework that efficiently transfers reasoning ability to weaker models with two components: (1) Skill-based data selection, which prioritizes examples targeting the student model’s weaker skills, and (2) Skillaware fine-tuning, which encourages explicit skill decomposition during problem solving. |
| Outcome: | The proposed framework surpasses baselines on Qwen3-4B and Qwend3-8B and focuses on skills emphasized during training. |
DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models (2024.emnlp-main)
Copied to clipboard
Ranchi Zhao, Zhen Thai, Yifan Zhang, Shengding Hu, Jie Zhou, Yunqi Ba, Jie Cai, Zhiyuan Liu, Maosong Sun
| Challenge: | Large Language Models (LLMs) are pre-trained on vast datasets composed of billions of tokens harvested from diverse text sources. |
| Approach: | They propose a data engineering method to refine the pretraining corpus through data rating, tagging and editing. |
| Outcome: | The proposed method improves the quality of the pretraining corpus by enhancing 100 billion tokens of the training corpus. |
CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for proximal policy optimization discard valuable gradient signals from low-probability tokens due to the clipping mechanism. |
| Approach: | They propose an algorithm that reintroduces gradients from clipped tokens in native PPO in a gentle and bounded manner. |
| Outcome: | The proposed algorithm outperforms strong baselines on reasoning benchmarks on different model scales. |
UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)
Copied to clipboard
Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang
| Challenge: | Recent advances in large language models (LLMs) have expanded their potential applications in finance. |
| Approach: | They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions. |
| Outcome: | The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios. |
HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy (2026.acl-industry)
Copied to clipboard
| Challenge: | relying on large language models for information has raised concerns about reliability and accuracy of outputs. |
| Approach: | They propose a hallucination taxonomy with 11 categories for various NLG tasks and propose HAllucination Detection models which integrate hallucinism detection, span-level identification, and correction into a single inference process. |
| Outcome: | The proposed models outperform baselines on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility. |
CycleOIE: A Low-Resource Training Framework For Open Information Extraction (2025.coling-main)
Copied to clipboard
Zhihong Jin, Chunhong Zhang, Zheng Hu, Jibin Yu, Ruiqi Ma, Qingyun Chen, Xiaohao Liao, Yanxing Zhang
| Challenge: | Open Information Extraction (OpenIE) models rely heavily on large amounts of annotated data. |
| Approach: | They propose a training framework that maximizes data efficiency through a cycle-consistency mechanism. |
| Outcome: | The proposed approach improves the quality of training data by curating low-quality datasets annotated by a large language model. |
Query-based Instance Discrimination Network for Relational Triple Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent approaches to extract relational triples from open domain texts suffer from error propagation, relation redundancy and lack of high-level connections. |
| Approach: | They propose a query-based approach to construct instance-level representations for relational triples . they use query embeddings and token embeddables to extract all types of triples in one step . |
| Outcome: | The proposed method achieves state-of-the-art on five widely used benchmarks. |
M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database (2022.acl-long)
Copied to clipboard
| Challenge: | Existing data resources to support multimodal affective analysis in dialogues are limited in scale and diversity. |
| Approach: | They propose a multimodal multi-scene multi-label Emotional Dialogue dataset, M3ED, which contains 990 dyadic emotional dialogues from 56 different TV series. |
| Outcome: | The proposed dataset contains 990 dyadic emotional dialogues from 56 different TV series, a total of 9,082 turns and 24,449 utterances. |
LaMPE: Length-aware Multi-grained Positional Encoding for Adaptive Long-context Scaling Without Training (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE). |
| Approach: | They propose a training-free method that remaps out-of-distribution (OOD) positions into the in-distance range with fixed mapping strategies, ignoring the dynamic relationship between input length and effective context window. |
| Outcome: | Experiments on three representative LLMs across five mainstream long-context benchmarks show that the proposed method achieves significant performance improvements compared to existing methods. |
A Generation-based Deductive Method for Math Word Problems (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing generation methods suffer from repeated sub-expression generation and deductive methods are restricted to dealing with binary operations. |
| Approach: | They propose a multivariate directed acyclic graph (mDAG) which generates the topological ordering of mDAg by equipping a generation model with a re-encoder to keep the deductive property but avoid the expensive enumeration of deductive methods. |
| Outcome: | The proposed model performs well on the widely used benchmarks and solves multivariate operators on the CMWPA benchmark. |
Movie101: A New Movie Understanding Benchmark (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to narrate movies with no actors are difficult to implement in real situations . a new metric is proposed to provide the best correlation with human evaluation . |
| Approach: | They propose a large-scale Chinese movie benchmark to help visually impaired enjoy movies . they propose metric called Movie Narration Score (MNScore) which achieves best correlation with human evaluation. |
| Outcome: | The proposed method outperforms baselines and the existing methods. |
Can We Steer Reasoning Direction by Thinking Intervention? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Reason Models suffer from overthinking and erroneous reasoning problems due to the lack of fine-grained control over their reasoning behaviors. |
| Approach: | They propose a paradigm to enable fine-grained control over LRMs’ reasoning behaviors by aligning reasoning trajectories with specific cognitive patterns. |
| Outcome: | The proposed paradigm achieves integration intervention throughout model reasoning processes. |
Dual Cache for Long Document Neural Coreference Resolution (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies show the effectiveness of cache-based neural coreference resolution models on long documents. |
| Approach: | They propose a hybrid cache that integrates two eviction policies to capture global and local entities separately and improves F1 score of coreference by 0.7 5.7pt. |
| Outcome: | The proposed model outperforms existing models on four benchmarks while saving up to 83% of inference time. |
Learning Architectures from an Extended Search Space for Language Modeling (2020.acl-main)
Copied to clipboard
Yinqiao Li, Chi Hu, Yuhao Zhang, Nuo Xu, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li
| Challenge: | Neural architecture search (NAS) has advanced in recent years but most NAS systems restrict search to learning architectures of a recurrent or convolutional cell. |
| Approach: | They propose a general approach to learn both intra-cell and inter-cell architectures . they implement their approach in a differentiable architecture search system . |
| Outcome: | The proposed approach outperforms the baseline on PTB and WikiText data and shows good transferability to other systems. |
DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Speculative decoding (SD) has proven to be effective for autoregressive generation in large language models (LLMs), however its application to vision-language models (VLMs) remains relatively unexplored. |
| Approach: | They propose a Speculative Decoding framework for vision-language models that integrates a neural architecture search framework and target-aware supernet training to identify optimal interaction strategies. |
| Outcome: | DREAM-S achieves 3.85 speedup compared to baselines on well-established vision-language models. |
Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations (P19-1)
Copied to clipboard
Rui Zhang, Caitlin Westerfield, Sungrok Shim, Garrett Bingham, Alexander Fabbri, William Hu, Neha Verma, Dragomir Radev
| Challenge: | Experimental results show that our model outperforms competitive translation-based baselines on cross-lingual relevance ranking tasks. |
| Approach: | They propose to match queries and documents in both source and target languages with deep bilingual query-document representations. |
| Outcome: | The proposed model outperforms translation-based baselines on English-Swahili, English-Tagalog, and English-Somali cross-lingual retrieval tasks. |
Dialogue Meaning Representation for Task-Oriented Dialogue Systems (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on dialogue meaning representations is limited in scalability for complex expressions. |
| Approach: | They propose a pliable and easily extendable representation for task-oriented dialogue . they propose an inheritance hierarchy mechanism focusing on domain extensibility . |
| Outcome: | The proposed representation can be easily extended to a task-oriented dialogue dataset. |
A Read-and-Select Framework for Zero-shot Entity Linking (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on the candidate retrieval stage and ignore the essential candidate ranking stage, which disambiguates among entities and makes the final linking prediction. |
| Approach: | They propose a read-and-select framework that models the main components of entity disambiguation . they use mention context to output mention-aware entity representations . |
| Outcome: | The proposed framework achieves state-of-the-art performance on established zero-shot entity linking dataset ZESHEL with 2.55% micro-average accuracy gain, with no need for laborious multi-phase pre-training used in most of the previous work. |
Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for predicting sentiment polarity of aspects are susceptible to interference caused by irrelevant contexts and lack sentiment knowledge at a data-specific level. |
| Approach: | They propose a novel Aspect-based sentiment analysis method that leverages attention scores to model the relationships between aspects and contexts. |
| Outcome: | The proposed method is able to predict sentiments from a set of five benchmark datasets. |
Visually Grounded Concept Composition (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to visual grounding do not explicitly model compositional structures of text expressions. |
| Approach: | They propose a concept-relation Graph and a composition neural network to combine CRGs . they propose to align CRG-based concepts with images to learn visually grounded concepts . |
| Outcome: | The proposed model can model grounded concepts forming at sentence level and word level. |
Beyond Modality Collapse: Taming Guided Modality Entropy for Omni-modal Emotion Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | EmoOmni is a data paradigm for omni-modal large language models that can be used for emotion reasoning. |
| Approach: | They propose a data paradigm that interleaves guided tokens into reasoning traces to enforce structured evidence extraction. |
| Outcome: | The proposed paradigm over-relys on a dominant modality while neglecting complementary cues. |
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multi-role dialogue summarization favor surface-level imitation of references rather than genuine gains in faithfulness or alignment with human preferences. |
| Approach: | They propose a framework that couples explicit cognitive-style reasoning with reward-based optimization for multi-role dialogue summarization. |
| Outcome: | The proposed framework matches strong baselines on ROUGE and BERTScore, while in-depth analysis on SAMSum shows clear gains in factual faithfulness and model-based preference alignment. |
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query. |
| Approach: | They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. |
| Outcome: | The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO. |
Text2World: Benchmarking Large Language Models for Symbolic World Model Generation (2025.findings-acl)
Copied to clipboard
Mengkang Hu, Tianxing Chen, Yude Zou, Yuheng Lei, Qiguang Chen, Ming Li, Yao Mu, Hongyuan Zhang, Wenqi Shao, Ping Luo
| Challenge: | Recent studies have encountered limitations in leveraging large language models to generate symbolic world models. |
| Approach: | They propose a benchmarking framework based on planning domain definition language (PDDL) that employs multi-criteria, execution-based metrics for a more robust evaluation. |
| Outcome: | The proposed model outperforms models trained with large-scale reinforcement learning, but lacks the robustness needed to perform in world modeling. |
Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models (2025.findings-acl)
Copied to clipboard
Haoyang Li, Xuejia Chen, Zhanchao Xu, Darian Li, Nicole Hu, Fei Teng, Yiming Li, Luyu Qiu, Chen Jason Zhang, Li Qing, Lei Chen
| Challenge: | Existing benchmarks focus on linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios. |
| Approach: | They propose a benchmark to evaluate numerical capabilities for large language models . they use a dataset to assess number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning. |
| Outcome: | The proposed benchmark evaluates six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning. |
GRAG: Graph Retrieval-Augmented Generation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and is not suitable for networked documents. |
| Approach: | They propose a novel divide-and-conquer strategy that retrieves optimal subgraph structure in linear time. |
| Outcome: | The proposed approach outperforms current state-of-the-art methods on graph reasoning benchmarks. |
Improving Knowledge Production Efficiency With Question Answering on Conversation (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing researches on conversation-based QA focus on document-based tasks . current researche focuses on document based tasks, but there is a lack of researche on conversation based qa . |
| Approach: | They propose a multi-span extraction model on conversation-based QA and introduce continual pre-training and multi-task learning schemes to further improve model performance. |
| Outcome: | The proposed model outperforms baseline on two Chinese datasets and will be released for research purposes. |
LoRaDA: Low-Rank Direct Attention Adaptation for Efficient LLM Fine-tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in parameter-efficient fine-tuning techniques allow for adjustments to only a minor fraction of the parameters of language models. |
| Approach: | They propose a low-rank direct attention adapted method for efficient LLM fine-tuning . they propose LMAM, which can bring negative attention to self-attention modules . |
| Outcome: | The proposed method outperforms the full fine-tuning method by 2.1% on GLUE benchmark. |
SplitThenMerge: Token-Level Skill-Compositional Sparse Mixture-of-Experts for Complex Domain-Specific Tasks (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing domain adaptation methods train heterogeneous skills together, making it difficult to reliably coordinate multiple skills when solving complex tasks. |
| Approach: | They propose a framework that decomposes domain competence into atomic skills and composes them dynamically during generation. |
| Outcome: | The proposed framework decomposes domain competence into atomic skills, trains them independently, and composes them dynamically during generation. |
TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation (2024.acl-long)
Copied to clipboard
| Challenge: | e.g., GPT-4 still lag behind humans in effective multitasking, a study finds . current textual simulations do not adequately address the notion of time . |
| Approach: | They propose a textual simulated environment that incorporates complex temporal dynamics and constraints that better reflect real-life planning scenarios. |
| Outcome: | The proposed model incorporates complex temporal dynamics and constraints that better reflect real-life planning scenarios. |
Narrative Order Aware Story Generation via Bidirectional Pretraining Model with Optimal Transport Reward (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing storytelling systems suffer from insufficient understanding of event correlations and inadequate awareness of event temporal order. |
| Approach: | They propose a narrative order aware framework to generate coherent stories with flashbacks . they propose 'bidirectional pretraining model with Optimal Transport Reward' to improve quality . |
| Outcome: | The proposed framework generates coherent stories with flashbacks with a novel optimal transport reward. |
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)
Copied to clipboard
Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current medical benchmarks have limitations in question design, data sources and evaluation methods. |
| Approach: | They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records . |
| Outcome: | The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios. |
Learning Action Conditions from Instructional Manuals for Instruction Understanding (2023.acl-long)
Copied to clipboard
| Challenge: | a weakly supervised task is proposed to extract mentions of preconditions and postconditions of actions from instructional manuals. |
| Approach: | They propose a task dubbed action condition inference which extracts mentions of preconditions and postconditions of actions from instructional manuals. |
| Outcome: | The proposed approach improves on the existing models, but still far behind human performance. |
MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing multimodal question answering models rely on sequential retrieval and reasoning, but this single-path paradigm makes them vulnerable to errors due to misleading intermediate steps. |
| Approach: | They propose a multimodal multi-hop question answering framework guided by an Adaptive Planning Graph . they propose modality-specific strategies that dynamically adapt to distinct data types . |
| Outcome: | The proposed framework outperforms existing models that rely on training. |
FRVA: Fact-Retrieval and Verification Augmented Entailment Tree Generation for Explainable Question Answering (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for generating a entailment tree exhibit the reasoning chains from knowledge facts to predicted answers, but they have large fact search spaces and error accumulation problems resulting in the generation of invalid steps. |
| Approach: | They propose a Fact-Retrieval and Verification Augmented bidirectional entailment tree generation method that contains two systems. |
| Outcome: | The proposed method outperforms existing models and achieves state-of-the-art performance in fact selection and structural correctness. |
Temporal Knowledge Question Answering via Abstract Reasoning Induction (2024.acl-long)
Copied to clipboard
| Challenge: | a new method to enhance temporal knowledge reasoning in large language models addresses this challenge . Abstract Reasoning Induction (ARI) framework provides factual knowledge support to LLMs . |
| Approach: | They propose an abstract reasoning induction framework which divides temporal reasoning into two phases: Knowledge agnostic and Knowledge-based. |
| Outcome: | The proposed method achieves significant gains on two temporal QA datasets. |
CANDY: Benchmarking LLMs’ Limitations and Assistive Potential in Chinese Misinformation Fact-Checking (2025.findings-emnlp)
Copied to clipboard
| Challenge: | CANDY is a benchmark to evaluate the capabilities and limitations of large language models (LLMs) for fact-checking misinformation. |
| Approach: | a team of researchers develop a benchmark to evaluate the capabilities and limitations of large language models in fact-checking misinformation in Chinese. |
| Outcome: | CANDY is a benchmark to evaluate the capabilities and limitations of large language models in fact-checking misinformation in China. |
Adaptive Threshold Selective Self-Attention for Chinese NER (2022.coling-1)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a computationally difficult task in Chinese since there is no natural delimiter between words in sentences. |
| Approach: | They propose a data-driven Adaptive Threshold Selective Self-Attention mechanism to select the most relevant characters to enhance Transformer architecture for Chinese named entity recognition. |
| Outcome: | Experiments on four benchmark Chinese NER datasets show the proposed mechanism improves performance. |
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models (2024.emnlp-main)
Copied to clipboard
Xinrong Zhang, Yingfa Chen, Shengding Hu, Xu Han, Zihang Xu, Yuanwei Xu, Weilin Zhao, Maosong Sun, Zhiyuan Liu
| Challenge: | Large language models (LLMs) are increasingly permeating daily lives and require real-time interactions that mirror human conversations. |
| Approach: | They propose to use time-division-multiplexing to process queries and responses pseudo-simultaneously. |
| Outcome: | The proposed model can listen to users while generating output and adjust to provide instant feedback. |
Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Rapid adoption of LLMs has overshadowed the potential advantages of traditional BERT-like models in text classification. |
| Approach: | They compare BERT-like models fine-tuning, LLM internal state utilization, and LLM zero-shot inference across six datasets. |
| Outcome: | The proposed method outperforms LLMs on six challenging datasets. |
Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for unsupervised text style transfer lack parallel data and difficulties in content preservation. |
| Approach: | They propose a neural approach to unsupervised text style transfer using non-parallel data. |
| Outcome: | The proposed approach can be trained end-to-end on two widely-used public datasets. |
FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture (2024.emnlp-main)
Copied to clipboard
Wenyan Li, Crystina Zhang, Jiaang Li, Qiwei Peng, Raphael Tang, Li Zhou, Weijia Zhang, Guimin Hu, Yifei Yuan, Anders Søgaard, Daniel Hershcovich, Desmond Elliott
| Challenge: | FoodieQA is a manually curated, fine-grained image-text dataset capturing the intricate features of food cultures across various regions in China. |
| Approach: | They evaluate vision–language Models and large language models on unseen food images and corresponding questions. |
| Outcome: | The proposed dataset evaluates vision–language Models and large language models on unseen food images and corresponding questions. |
NILE: Internal Consistency Alignment in Large Language Models (2025.emnlp-main)
Copied to clipboard
Minda Hu, Qiyuan Zhang, Yufei Wang, Bowei He, Hongru Wang, Jingyan Zhou, Liangyou Li, Yasheng Wang, Chen Ma, Irwin King
| Challenge: | Recent advances show that the world knowledge in the Instruction Fine-Tuning (IFT) dataset, which is incompatible with LLMs’ internal knowledge, can greatly hurt the IFT performance. |
| Approach: | They propose a framework to optimize the effectiveness of IFT by carefully aligning the world and internal knowledge of LLMs. |
| Outcome: | The proposed framework can significantly improve performance across multiple LLM ability evaluation datasets. |
Beyond Output Confidence: Epistemic-Aware Hallucination Detection with Answer-Level Signals (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting hallucinations are confounded by epistemic uncertainty and cannot distinguish genuine uncertainty from fabricated content. |
| Approach: | They propose a model-agnostic metric that captures epistemic boundary deviations by measuring answer-level stability across multiple stochastic forward passes. |
| Outcome: | The proposed metric outperforms strong uncertainty-only baselines and can be used to detect hallucinations on open-domain question answering, dialogue generation, and code completion. |
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)
Copied to clipboard
Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu
| Challenge: | Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs. |
| Approach: | They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics. |
| Outcome: | The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility. |
A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing document-level relation extraction methods focus on fully supervised scenarios but in real-world, incomplete labeling is a common problem because the number of entity pairs grows quadratically with the number. |
| Approach: | They propose a positive-unlabeled learning framework for document-level relation extraction (RE) that uses shift and squared ranking loss positive- unlabeles (SSR-PU) learning to solve incomplete labeling problem. |
| Outcome: | The proposed framework outperforms state-of-the-art methods under fully supervised and extremely unlabeled conditions and achieves 14 F1 points over the baseline with incomplete labeling. |
UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs (2024.acl-demos)
Copied to clipboard
Chaoqun He, Renjie Luo, Shengding Hu, Ranchi Zhao, Jie Zhou, Hanghao Wu, Jiajie Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing evaluation platforms are complex and poorly modularized, hindering seamless incorporation into researcher’s workflows. |
| Approach: | They propose a lightweight evaluation framework characterized by lightweight, comprehensiveness, modularity, and efficiency that integrates models, data, and metrics into a unified evaluation workflow. |
| Outcome: | The proposed evaluation framework is lightweight, comprehensive, modular, and efficient. |
Is Compound Aspect-Based Sentiment Analysis Addressed by LLMs? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) aims to predict aspect-based elements from text . large language models (LLMs) have impressive abilities in handling human instructions . |
| Approach: | They propose a framework to evaluate LLMs' ability to handle complex ABSA tasks . they use constrained prompts to automatically organize the returned predictions . |
| Outcome: | The proposed framework outperforms supervised methods in some cases, but it is still lacking in other areas. |
Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)
Copied to clipboard
Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases. |
| Approach: | They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases. |
| Outcome: | The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases. |
Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on extracting multi-granularity visual features for integration or designing model architectures for better message passing across various modalities. |
| Approach: | They propose to decompose the informative visual signals into two parts: source-specific information and target-specific info. |
| Outcome: | The proposed method can enhance the visual awareness of MMT models against strong baselines. |
Improving Distantly-Supervised Relation Extraction with Joint Label Embedding (D19-1)
Copied to clipboard
| Challenge: | Existing methods for relation extraction treat labels as independent and meaningless one-hot vectors, which cause a loss of potential label information for selecting valid instances. |
| Approach: | They propose a multi-layer attention-based model to improve relation extraction with joint label embedding by gating integration and using the embeddable entities as an atten- tion. |
| Outcome: | The proposed model significantly outperforms state-of-the-art methods in relation extraction with joint label embedding. |
Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese (2025.emnlp-main)
Copied to clipboard
Yikang Liu, Wanyang Zhang, Yiming Wang, Jialong Tang, Pei Zhang, Baosong Yang, Fei Huang, Rui Wang, Hai Hu
| Challenge: | Translationese is a linguistic property that is often introduced in the translation process that is different from those of original texts. |
| Approach: | They propose to use synthesized translations and translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments. |
| Outcome: | The proposed measure can generalize to unseen genres, authors, and language pairs. |
Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)
Copied to clipboard
Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang
| Challenge: | Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations. |
| Approach: | They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation. |
| Outcome: | The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement. |
Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models (2025.coling-main)
Copied to clipboard
Haoran Lian, Junmin Chen, Wei Huang, Yizhe Xiong, Wenping Hu, Guiguang Ding, Hui Chen, Jianwei Niu, Zijia Lin, Fuzheng Zhang, Di Zhang
| Challenge: | Recent studies show that Large language models struggle with handling long token sequences due to limited training context size. |
| Approach: | They propose a single-stage continual pretraining method to equip LLMs with long context modeling capabilities. |
| Outcome: | The proposed method outperforms existing methods on 4 language modeling benchmarks. |
AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for LLM alignment optimize tokens using a sparse, response-level reward or preference annotation. |
| Approach: | They propose an RLHF-equivalent distillation method for token-level reward optimization that incorporates the reward learned by DPO into the RLHG objective and builds a token-based teacher distribution. |
| Outcome: | The proposed method bridges the accuracy gap between the reward from the DPO model and the pure reward model by building a contrastive DPO reward with a normal and a reverse DPO. |
OTExtSum: Extractive Text Summarisation with Optimal Transport (2022.findings-naacl)
Copied to clipboard
| Challenge: | Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary. |
| Approach: | They propose to formulate extractive text summarisation as an Optimal Transport (OT) problem and use it to obtain an optimal summary that minimises the transportation cost to a given document. |
| Outcome: | The proposed method outperforms state-of-the-art methods and learning-based methods on multiNews, PubMed, BillSum, and CNN/DM datasets. |
SaCa: A Highly Compatible Reinforcing Framework for Knowledge Graph Embedding via Structural Pattern Contrast (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge Graph Embedding approaches lack structural semantics of knowledge graphs . structure-aware calibration (SaCa) is a framework designed to calibrate KGEs based on global structural patterns. |
| Approach: | a new framework is designed to calibrate knowledge graphs using global structural patterns. |
| Outcome: | a new framework can calibrate KGE models using global structural patterns . the framework consistently boosts performance across ten models on link prediction and entity classification tasks . |
Automated Molecular Concept Generation and Labeling with Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Concept-based models lack explainability and need predefined concepts and manual labeling in molecular science. |
| Approach: | They propose a framework that leverages Large Language Models to generate and label predictive molecular concepts without human input. |
| Outcome: | The proposed framework outperforms existing models on several benchmarks while maintaining explainability and allowing easy intervention. |
Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for relational triple extraction ignore implicit triples that lack explicit expressions, leading to incomplete knowledge graphs. |
| Approach: | They propose a binary pointer network to extract explicit and implicit relational triples from sentences and to retain the information of extracted triples in an external memory. |
| Outcome: | The proposed framework extracts overlapping triples relevant to each word sequentially and retains the information of extracted triples in an external memory. |
CloneMem: Benchmarking Long-Term Memory for AI Clones (2026.acl-long)
Copied to clipboard
| Challenge: | Existing memory benchmarks rely on user–agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories. |
| Approach: | They propose a benchmark for evaluating long-term memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years. |
| Outcome: | Experiments show that existing memory benchmarks struggle in this setting, highlighting open challenges for life-grounded personalized AI. |
Mind’s Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achieved significant advances in natural language processing, but their scale and computational demands pose challenges to their practical application. |
| Approach: | They propose a method for distilling the self-evaluation capability from LLMs into SLMs and advocate for more comprehensive thinking by incorporating multiple distinct CoTs and self-estimation outputs. |
| Outcome: | The proposed method significantly improves the performance of distilled SLMs on three NLP benchmarks. |
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)
Copied to clipboard
Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu
| Challenge: | Existing sparsification methods like pruning can lose model knowledge through parameter removal. |
| Approach: | They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks. |
| Outcome: | The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints. |
Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Existing studies show that LLMs can confidently state non-existent facts rather than answering "I don't know". |
| Approach: | They propose a multi-source evidence fusion enhanced hallucination detection and correction framework that fuses evidence from multiple sources and iteratively revises the hallucinous content. |
| Outcome: | The proposed framework detects whether the generated content contains factual errors, provides the rationale behind the judgment, and iteratively revises the hallucinated content. |
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)
Copied to clipboard
Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie
| Challenge: | Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. |
| Approach: | They propose a ranking-oriented induction model to learn personalized mapping function for each word. |
| Outcome: | The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages. |
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing research has proposed a variety of training-free and post-training methods for selecting critical key-value pairs at each generation step. |
| Approach: | They propose to use local (sliding-window) and global (compression/selective) attention across layers to enlarge long-context modeling. |
| Outcome: | Experiments on models from 340M to 1.3B parameters show that the proposed method matches or exceeds full attention and native sparse attention in both common-sense reasoning and long-context understanding tasks. |
TMID: A Comprehensive Real-world Dataset for Trademark Infringement Detection in E-Commerce (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Annually, e-commerce platforms incur substantial financial losses due to trademark infringements. |
| Approach: | They propose a dataset to detect trademark infringement in merchant registrations . they use legal rules and contextual information from Alipay to gather contextual information with annotations from legal experts. |
| Outcome: | The proposed dataset is sourced from Alipay, one of the world’s largest e-commerce and digital payment platforms. |
Dynamic Heterogeneous-Graph Reasoning with Language Models and Knowledge Representation Learning for Commonsense Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for QA use knowledge graphs, but they ignore subgraph optimization and subgraph deepening. |
| Approach: | They propose a dynamic heterogeneous-graph reasoning method with LMs and knowledge representation learning that optimizes the structure and knowledge representing of the HKG using a two-stage pruning strategy and knowledge-representation learning. |
| Outcome: | The proposed method improves on existing methods at CommonsenseQA and OpenBookQA. |
HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection (2025.emnlp-main)
Copied to clipboard
Yiheng Jing, Mingming Zhang, Yong Zhuang, Jiacheng Guo, Juan Wang, Xiaoyang Xu, Wenzhe Yi, Keyan Guo, Hongxin Hu
| Challenge: | Existing methods for hateful video detection rely on unimodal analysis or feature fusion . Existing tools struggle to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor . |
| Approach: | They propose a reasoning-based hateful video detection framework with multimodal large language models . they integrate Chain-of-Thought reasoning to enhance multimodal interaction modeling . |
| Outcome: | The proposed framework outperforms existing tools on two public datasets covering English and Chinese. |
ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large language models struggle to align user intent with tool semantics or generalize to unseen tools. |
| Approach: | They propose a framework that enables LLMs for open-world tool use by proactive retrieval and grounded execution within a reasoning loop. |
| Outcome: | The proposed framework surpasses baselines in retrieval and execution efficiency by +10.8%. |
SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to improve numerical and logical reasoning of Large Language Models are limited . existing approaches rely on prompt engineering and pretrained knowledge to ensure correctness . |
| Approach: | They propose to train LLMs with process-based reasoning using a dynamic value margin . they use the Bellman optimality equation to derive a value margin for step-level preference optimization . |
| Outcome: | The proposed method is equivalent to on-policy policy gradient methods under constrained reward functions. |
SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)
Copied to clipboard
Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Zhiqiang Hu, Chenhui Shen, Yew Ken Chia, Xingxuan Li, Jianyu Wang, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing
| Challenge: | Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages. |
| Approach: | They propose a series of language models that specifically focuses on Southeast Asian languages. |
| Outcome: | SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations . |
Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks have exposed patterns and may not truly assess generalization ability of Large Language Models (LLMs). |
| Approach: | They propose a “Generalization Stress Test” to assess Large Language Models’ generalization ability under slight and controlled perturbations, including option length, problem types, and irrelevant noun replacements. |
| Outcome: | The proposed test shows that LLMs exhibit severe accuracy drops and unexpected biases when faced with minor but content-preserving modifications. |
Incorporating Argument-Level Interactions for Persuasion Comments Evaluation using Co-attention Model (C18-1)
Copied to clipboard
| Challenge: | Existing research explores different text features of reply comments on word level and ignores interactions between participants. |
| Approach: | They propose a co-attention mechanism based neural network to capture interactions between participants on argument level to better model dialogical argumentation. |
| Outcome: | The proposed model outperforms state-of-the-art methods on a publicly available dataset showing that it extracts interactive argument pairs from the original post and the reply. |
CFlowPsyD: An Analysis-Enhanced Dataset for Asynchronous Psychological Counseling through Self-Optimizing Multi-Agent Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Asynchronous psychological counseling (APC) is a crucial mental health service modality that transcends temporal and spatial constraints. |
| Approach: | They propose a self-optimizing multi-agent framework for counseling dialogue generation, CFlowPsy, which utilizes real anonymized counseling cases as seed data to synthesize diverse problem-solving-oriented APC conversations through large language models. |
| Outcome: | The proposed framework synthesizes diverse problem-solving-oriented APC conversations through large language models. |
MEraser: An Effective Fingerprint Erasure Approach for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have raised critical concerns about model ownership and intellectual property protection. |
| Approach: | They propose a method for effectively removing backdoor-based fingerprints from LLMs . they propose deleting backdoor fingerprints using a transferable erasure mechanism . |
| Outcome: | The proposed method removes backdoor-based fingerprints while maintaining model performance. |
ESF: Efficient Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly utilized in diverse applications, including code generation, legal document analysis, medical diagnosis, and decision-making. |
| Approach: | They propose a fingerprinting method tailored for black-box tamper detection of large language models. |
| Outcome: | The proposed method detects tampering with a 99.2% detection rate using 5 fingerprint samples across state-of-the-art LLMs. |
Debate-of-Thoughts: Resolving Knowledge Conflicts in LLMs Through Internal Deliberation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for retrieval augmented generation are based on a simplistic binary choice of relying on external contexts or memory. |
| Approach: | They propose a framework that transforms conflict resolution into an active deliberation process by incorporating contradictions as opportunities for deeper reasoning. |
| Outcome: | Experiments show that DoT outperforms state-of-the-art methods while generating transparent debate transcripts that explain its decisions. |
CoLAKE: Contextualized Language and Knowledge Embedding (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models for integrating factual knowledge into pre-trained language models are shallow, static, and separately pre-train entities. |
| Approach: | They propose a method which integrates knowledge contexts from large-scale knowledge bases into a unified data structure. |
| Outcome: | The proposed model outperforms existing models on knowledge-driven tasks and knowledge probing tasks. |
BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to construct knowledge graphs are limited to a small set of relations due to manual cost or restrictions in text corpus. |
| Approach: | They propose to automatically construct knowledge graphs (KGs) of diverse new relations from pretrained language models that accept knowledge queries with prompts. |
| Outcome: | The proposed framework extracts knowledge of over 400 new relations from pretrained language models, including RoBERTaNet, with minimal input of a relation definition and a few shot of example entity pairs. |
KET-QA: A Dataset for Knowledge Enhanced Table Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing datasets that ignore the challenge of missing knowledge in TableQA are limited in their use. |
| Approach: | They propose to use a knowledge base as the external knowledge source for TableQA and construct a dataset with fine-grained gold evidence annotation. |
| Outcome: | The proposed model achieves remarkable performance improvements on three different settings, but still lags behind the human-level performance. |
DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models for text-to-speech (TTS) synthesize speech with acoustic features . autoregressive models have problems with word skipping and repeated reading . non-autoregressive acustic models lack probabilistic modeling and unimodal characteristics of Gaussian distribution don't conform to true distribution of aural features, which restricts the diversity of generated prosodic features. |
| Approach: | They propose a multi-speaker acoustic model that hierarchically models speech prosodic features and controls different prosodic styles to guide prosody prediction. |
| Outcome: | The proposed method outperforms baseline models in naturalness and achieves superior synthesis speed compared to baseline models. |
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems (2023.emnlp-main)
Copied to clipboard
Songbo Hu, Han Zhou, Moy Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić
| Challenge: | Existing systems trained for Arabic or Turkish using annotated data fully parallel to English ToD data still exhibit diminished ToD task performance. |
| Approach: | They define new quantitative measures of absolute and relative equivalence in system performance, capturing disparities across languages and within individual languages. |
| Outcome: | The proposed measures capture disparities across languages and within individual languages. |
FAIRGAMER: Evaluating Social Biases in LLM-Based Video Game NPCs (2026.acl-long)
Copied to clipboard
Bingkang Shi, Jen-tse Huang, Luo Long, Tianyu Zong, Hongzhu Yi, Yuanxiang Wang, Songlin Hu, Xiaodan Zhang, Zhongjiang Yao
| Challenge: | Large Language Models (LLMs) have enhanced or replaced traditional non-player characters in video games. |
| Approach: | They propose a benchmark to evaluate social biases across three interaction patterns: transaction, cooperation, and competition. |
| Outcome: | The proposed benchmark assesses four bias types across transaction, cooperation, and competition using a novel metric, FairMCV. |
COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing paradigms treat facts independently or employ myopic search, failing to optimize collective subgraph utility. |
| Approach: | They propose a framework that formalizes evidence retrieval as a constrained submodular maximization problem. |
| Outcome: | The proposed framework captures the trade-off between information relevance and structural complexity. |
Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction (2026.findings-acl)
Copied to clipboard
Hao Zhang, Jiahao Wang, Zhenke Duan, Xin Yin, Haichuan Hu, Hualong Chen, null Suyi, Congqing He, Yike Tan, Yu-N Cheah
| Challenge: | Existing methods lack explainability and generalization, making it difficult to justify inference decisions and detect implicit sentiment across domains and varied expression patterns. |
| Approach: | They propose an explainable multi-path tree-guided chain-of-thought framework specifically designed for ASQP. |
| Outcome: | Experiments on benchmark datasets show that Tree-CoT-RT outperforms baselines. |
A Data-Centric Framework for Composable NLP Workflows (2020.emnlp-demos)
Copied to clipboard
Zhengzhong Liu, Guanxiong Ding, Avinash Bukkittu, Mansi Gupta, Pengzhi Gao, Atif Ahmed, Shikun Zhang, Xin Gao, Swapnil Singhavi, Linwei Li, Wei Wei, Zecong Hu, Haoran Shi, Xiaodan Liang, Teruko Mitamura, Eric Xing, Zhiting Hu
| Challenge: | Empirical natural language processing (NLP) systems involve interoperation among multiple components . a wealth of NLP toolkits exist ( 4), such as spaCy, DKPro, CoreNLP. |
| Approach: | They propose a unified open-source framework that supports fast development of NLP workflows . framework includes processors for NLP tasks, visualization, and annotation . |
| Outcome: | The framework offers processors for NLP tasks, visualization, and annotation, and is extensible . it is delivered through two modularized yet integratable open-source projects, Forte and Stave . |
A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for conditional inference on joint textual and visual clues lack multimodal context reasoning capability. |
| Approach: | They propose a multi-modal context reasoning approach that embeds textual semantics and objective image information into the pretrained language model to perform context reasoning. |
| Outcome: | The proposed approach improves on two data sets and shows 4.8% gain on the PMR. |
MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang
| Challenge: | Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. |
| Approach: | They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments. |
| Outcome: | Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning. |
DAC-Bench: A Decision-Aware Benchmark for Compositional Mobile GUI Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on short, linear workflows and step-level accuracy, highlighting performance degradations. |
| Approach: | They propose a decision-aware benchmark with compositional tasks comprising 830 episodes and 11,345 action steps across 35 applications on Android and iOS. |
| Outcome: | The proposed benchmarks show performance degradation and branch correctness issues in 7 different GUI agents. |
More than Text: Multi-modal Chinese Word Segmentation (2021.acl-short)
Copied to clipboard
| Challenge: | Currently, word segmentation is performed in many languages without word delimiters. |
| Approach: | They propose to combine the multi-modality to perform Chinese word segmentation . they propose a time-dependent multi-module interactive model to integrate multi-modality information . |
| Outcome: | The proposed model integrates multi-modal information for word sequence labeling with Chinese language as target . the proposed model performs well on three training sets on Chinese and other languages without word delimiters. |
SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)
Copied to clipboard
Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang
| Challenge: | Large language models (LLMs) have many advantages but they also pose significant safety risks. |
| Approach: | They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions . |
| Outcome: | The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets. |
A Multi-modal Debiasing Model with Dynamical Constraint for Robust Visual Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that many well-developed Visual Question Answering systems suffer from bias problem. |
| Approach: | They propose a way to mitigate bias problem by subtracting bias score from standard VQA base score. |
| Outcome: | The proposed method improves on the VQA v2.0 and VQA-CP V2,0 datasets. |
Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show the promise of large language models for few-shot tabular classification but highlight challenges due to the variability in structured data. |
| Approach: | They propose a framework that distills data into actionable insights to enable robust and effective classification by large language models. |
| Outcome: | The proposed framework integrates rule summarization, strategic exemplification, and insight reflection through deep collaboration between LLMs and data modeling techniques. |
Confidence Estimation for LLMs in Multi-turn Interactions (2026.findings-acl)
Copied to clipboard
Caiqi Zhang, Ruihan Yang, Xiaochen Zhu, Chengzu Li, Tiancheng Hu, Yijiang River Dong, Deqing Yang, Nigel Collier
| Challenge: | Despite recent progress, most prior work studies confidence in single-turn question answering. |
| Approach: | They propose a logit-based probe that measures confidence in multi-turn dialogues . they propose 'infoECE' and a "hinter-guesser" paradigm for generating controlled evaluations based on data . |
| Outcome: | The proposed framework is grounded in calibration and monotonicity of confidence as more information becomes available. |
Adversarial Metric Learning for Fine-Grained Emotion Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in fine-grained emotion classification relied on contrastive learning with hard-pair mining. |
| Approach: | They propose an adversarial metric learning framework that replaces fixed similarity metrics with a learnable metric family and trains representations to remain discriminative under worst-case similarity distortions. |
| Outcome: | The proposed framework trains a pairwise discriminator to maximally confuse two hard pair types while training the encoder to remain discriminative under worst-case similarity distortions. |
Improving Factual Consistency in Abstractive Summarization with Sentence Structure Pruning (2024.lrec-main)
Copied to clipboard
Dingxin Hu, Xuanyu Zhang, Xingyue Zhang, Yiyang Li, Dongsheng Chen, Marina Litvak, Natalia Vanetik, Qing Yang, Dongliang Xu, Yanquan Zhou, Lei Li, Yuze Li, Yingqi Zhu
| Challenge: | Abstractive summarization models suffer from factual inconsistency problem . post-editing methods focus on replacing suspicious entities, failing to modify incorrect content hidden in sentence structures. |
| Approach: | They propose to use sentence pruning operation to correct possible errors . they propose to apply sentence pruning operations to the syntactic dependency tree . |
| Outcome: | The proposed method improves factual consistency on the FRANK dataset compared with baselines . it is model-independent and can serve as the final step in ensuring factual consistentness. |
From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current research on long-form context in Large Language Models (LLMs) focuses on understanding of long-contexts, but the open-ended Long Text Generation (Open-LTG) remains underexplored. |
| Approach: | They propose a method that uses data synthesis and a reward signal to enhance model performance. |
| Outcome: | The proposed method outperforms GPT-4-Turbo and improves performance by 20% on the Open-LTG task. |
DAMON: A Dialogue-Aware MCTS Framework for Jailbreaking Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for multi-turn attacks mainly utilize a predefined dialogue pattern, limiting their effectiveness in realistic situations. |
| Approach: | They propose a multi-turn jailbreak attack method that leverages Monte Carlo Tree Search to explore multi-turned conversational spaces and identifies sub-instruction sequences that induce harmful responses. |
| Outcome: | The proposed method can induce undesired behaviors across five LLMs and three datasets. |
Mitigating Shortcut Learning via Smart Data Augmentation based on Large Language Model (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to improve shortcut learning performance are limited by manual definition of shortcuts and inherent confirmation bias during model training. |
| Approach: | They propose a method of Smart Data Augmentation based on Large Language Models to identify shortcuts and generate their anti-shortcut counterparts. |
| Outcome: | The proposed method shows an improvement of 5.61% across various natural language processing tasks. |
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation (2026.acl-long)
Copied to clipboard
Fangda Ye, Kuicai Dong, Xie Zhifei, Yuxin Hu, Yihang Yin, Shurui Huang, Shikai Dong, Chen Zhang, Jianzhu Bao, Shuicheng Yan
| Challenge: | Recent agentic search frameworks are text-centric, overlooking multimodal evidence . a pressing task is multimodal long-form generation, a new paper argues . |
| Approach: | They propose a unified agentic framework for grounded multimodal long-form generation. |
| Outcome: | The proposed framework is based on a unified agentic framework for grounded multimodal long-form generation. |
GUI Agents: A Survey (2025.findings-acl)
Copied to clipboard
Dang Nguyen, Jian Chen, Yu Wang, Gang Wu, Namyong Park, Zhengmian Hu, Hanjia Lyu, Junda Wu, Ryan Aponte, Yu Xia, Xintong Li, Jing Shi, Hongjie Chen, Viet Dac Lai, Zhouhang Xie, Sungchul Kim, Ruiyi Zhang, Tong Yu, Mehrab Tanjim, Nesreen K. Ahmed, Puneet Mathur, Seunghyun Yoon, Lina Yao, Branislav Kveton, Jihyung Kil, Thien Huu Nguyen, Trung Bui, Tianyi Zhou, Ryan A. Rossi, Franck Dernoncourt
| Challenge: | Large Foundation Models (LFMs) have transformed the landscape of AI research and day-to-day life. |
| Approach: | They propose a framework that delineates GUI agents' perception, reasoning, planning, and acting capabilities. |
| Outcome: | The proposed framework delineates their perception, reasoning, planning, and acting capabilities. |
MirrorCAPTCHA: Wild CAPTCHA, Wild Distribution, Wild Web-based Platform Meet Multimodal LLM Agents (2026.acl-long)
Copied to clipboard
Xiangyu Wu, Yuwei Hu, Tianyu Cui, Yueying Tian, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Yang Yang, Jianfeng Lu
| Challenge: | Existing agent benchmarks fail to evaluate an agent's real-world capacity to handle CAPTCHA . Existing benchmarks ignore this practical challenge, failing to evaluate agents' ability to handle complex visual CAPTchas. |
| Approach: | They propose a benchmark annotated with Weighted Pass Rate and a new metric to measure agent's ability to handle CAPTCHA. |
| Outcome: | The proposed benchmark outperforms current state-of-the-art closed-source models on mirrorCAPTCHA and achieves 9.4% higher average weighted pass rate and 2.13% higher average Completion degree. |
Cause-CSD: A Challenge Multimodal Conversational Stance Cause Detection Dataset and Effective Method (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing stance detection methods treat opinions as surface-level labels, overlooking conversational evidence behind stance expressions. |
| Approach: | They propose a task that jointly identifies stance polarity and contextual evidence . they propose stance-cause Detection language model that leverages explicit context reasoning . |
| Outcome: | The proposed task outperforms baseline methods on text-only and multimodal subtasks. |
WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem (2026.findings-acl)
Copied to clipboard
Chengyou Wang, Mingchen Shao, Jingbin Hu, Zeyu Zhu, Hongfei Xue, Bingshen Mu, Xin Xu, Xingyi Duan, Binbin Zhang, Zhu Pengcheng, Chuang Ding, Xiaojun Zhang, Hui Bu, Lei Xie
| Challenge: | despite its linguistic significance, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models. |
| Approach: | They propose to use WenetSpeech-Wu as a large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect of Chinese. |
| Outcome: | The proposed dataset includes 8,000 hours of speech data and strong open-source models . the proposed dataset is competitive and empirically validated . |
From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)
Copied to clipboard
Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications. |
| Approach: | They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis. |
| Outcome: | The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability. |
ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases. |
| Approach: | They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage. |
| Outcome: | The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance. |
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement (2026.acl-long)
Copied to clipboard
Shengji Tang, Jianjian Cao, Weihao Lin, Jiale Hong, Bo Zhang, Shuyue Hu, Lei Bai, Tao Chen, Wanli Ouyang, Peng Ye
| Challenge: | Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks. |
| Approach: | They propose a Scalable Multi-LLM Collaboration System to coordinate multiple open-source LLMs. |
| Outcome: | The proposed system outperforms prevailing closed-source LLMs on eight mainstream benchmarks on multiple tasks. |
Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering (2025.acl-long)
Copied to clipboard
| Challenge: | Existing work finds that long CoT reasoning can be efficiently elicited by tuning on only a few examples and can easily transfer to other tasks. |
| Approach: | They propose a representation engineering method to unleash the general long CoT reasoning capabilities of LLMs. |
| Outcome: | The proposed method is effective in in-domain and cross-domain scenarios. |
Compare to The Knowledge: Graph Neural Fake News Detection with External Knowledge (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fake news detection rely on linguistic and semantic features from news content and do not exploit external knowledge. |
| Approach: | They propose a graph neural model which compares news to knowledge base through entities for fake news detection. |
| Outcome: | The proposed model significantly outperforms state-of-the-art methods on two benchmark datasets. |
Open-Set Semi-Supervised Text Classification via Adversarial Disagreement Maximization (2024.acl-long)
Copied to clipboard
| Challenge: | Open-Set Semi-Supervised Text Classification (OSTC) aims to train a classification model on a limited set of labeled texts along with plenty of unlabeled examples. |
| Approach: | They propose to train a classification model on a limited set of labeled texts alongside plenty of unlabeled examples that include both in-distribution and out-of-difference examples. |
| Outcome: | The proposed model improves on outlier detection and abnormal example detection and calibration. |
Trust Within? Seek Beyond? Knowledge Boundary Aware Policy Optimization for Agentic Search (2026.acl-long)
Copied to clipboard
Tao Feng, Xinke Jiang, Xinyan Hu, Yonggang Zhang, Zhen Tao, Wentao Zhang, Boyang Liu, Wenhao Jiang, Chao Wu
| Challenge: | Existing approaches to augment large language models with external knowledge suffer from a lack of calibration regarding the model’s knowledge boundary. |
| Approach: | They propose a reinforcement learning framework that explicitly aligns retrieval decisions with quantified knowledge states. |
| Outcome: | The proposed framework outperforms strong baselines while exhibiting reduced hallucination rates. |
Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges (2025.findings-acl)
Copied to clipboard
Hongru Wang, Wenyu Huang, Yufei Wang, Yuanhao Xi, Jianqiao Lu, Huan Zhang, Nan Hu, Zeming Liu, Jeff Z. Pan, Kam-Fai Wong
| Challenge: | Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use focus on stateless, single-turn interactions or partial evaluations, overlooking the inherent stateful nature of interactions in multi-turn applications. |
| Approach: | They propose a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use across six key tasks in three stages . they also build VirtualMobile – an embodied virtual mobile evaluation environment to simulate API calls and assess the robustness of the created APIs. |
| Outcome: | The proposed dataset evaluates 13 open- and closed-source LLMs and provides detailed analysis at each stage. |
RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction (2026.findings-acl)
Copied to clipboard
Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen
| Challenge: | Existing benchmarks focus on casual conversation or task-oriented dialogue, failing to capture “long-term project-oriented” interactions where agents must track evolving goals. |
| Approach: | They propose a benchmark that simulates the dynamic evolution of memory in real-world projects. |
| Outcome: | The proposed benchmarks simulate the dynamic evolution of memory in real-world projects. |
Cross-domain Rumor Detection via Test-Time Adaptation and Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches focus on within-domain tasks, resulting in suboptimal performance in cross-domain scenarios due to domain shifts. |
| Approach: | They propose a framework that incorporates both single-domain model and target graph adaptation strategies tailored to the unique requirements of cross-domain rumor detection. |
| Outcome: | The proposed framework surpasses existing methods in rumor detection on social media. |
VHASR: A Multimodal Speech Recognition System With Vision Hotwords (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that incorporate audio-related image information do not improve speech recognition performance. |
| Approach: | They propose a novel approach utilizing audio-related image information and set up a multimodal speech recognition system that uses vision as hotwords to enhance the model’s speech recognition capability. |
| Outcome: | The proposed model outperforms unimodal ASR model and achieves SOTA among existing image-based multimodal ASL models. |
Unlocking Speech Instruction Data Potential with Query Rewriting (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing LLMs lack datasets and biased training tasks to follow speech instructions. |
| Approach: | They propose a query rewriting framework that uses multiple agents to annotate and validate the synthesized speech. |
| Outcome: | The proposed framework can transform text instructions into distributions more suitable for TTS models for speech synthesis without human annotation. |
PathwiseRAG: Multi-Dimensional Exploration and Integration Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing retrieval-augmented generation systems employ rigid retrieval strategies . static retrieval produces knowledge blind spots, missing connections between quantum algorithms and encryption vulnerabilities . |
| Approach: | PathwiseRAG addresses these challenges through intent-aware strategy selection . it constructs a directed acyclic graph of interconnected sub-problems and explores multiple reasoning trajectories . |
| Outcome: | The proposed framework achieves higher accuracy and better reliability than current systems. |
Sentiment Interpretable Logic Tensor Network for Aspect-Term Sentiment Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Aspect-term sentiment analysis (ATSA) is a fine-grained task that aims to infer the sentiment towards the given aspect-terms. |
| Approach: | They propose a novel ATSA method that is interpretable and has high accuracy . they propose SILTN, which is a neurosymbolic formalism, to improve the accuracy based on syntax knowledge distillation. |
| Outcome: | The proposed method is interpretable because it is a neurosymbolic formalism and a computational model that supports learning and reasoning about data with a differentiable first-order logic language. |
MultiSkill: Evaluating Large Multimodal Models for Fine-grained Alignment Skills (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation settings for large multimodal models focus on coarse-grained evaluation without considering skill composition required by specific instructions. |
| Approach: | They propose an evaluation protocol that assesses large multimodal models across multiple fine-grained skills for alignment with human values. |
| Outcome: | The proposed evaluation protocol decomposes coarse-level scoring to fine-grained skill set-level score tailored to each instruction. |
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)
Copied to clipboard
Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples. |
| Approach: | They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes. |
| Outcome: | The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance. |
Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to generate counterfactual data augmentation are limited due to imbalance and biases in real-world training data. |
| Approach: | They propose a self-improved method for generating high-quality counterfacts using large language models. |
| Outcome: | The proposed method generates high-quality counterfacts on the natural language inference task using lightweight and task-specific LLMs. |
Automatic Marketing Theme and Commodity Construction System for E-commerce (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing recommendation system invites experts to write marketing themes and select relevant commodities, which suffer from difficulty in mass production, poor timeliness and low online indicators. |
| Approach: | They propose to use pretrained language model to generate marketing themes and commodity consistency module to select relevant commodities for the generative theme. |
| Outcome: | The proposed system can generate popular marketing themes and select relevant commodities automatically and improve theme online effectiveness compared with state-of-the-art methods. |
Syntax Encoding with Application in Authorship Attribution (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to extract syntactic features from text or sentences are limited by the loss of rich structural information contained in the syntax tree. |
| Approach: | They propose to embed the syntax parse tree of sentence into a learnable distributed representation . they show that the approach improves upon the prior art and achieves new performance records . |
| Outcome: | The proposed approach improves upon the prior art and achieves new performance records on five benchmarking data sets. |
MedCite: Can Language Models Generate Verifiable Text for Medicine? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. |
| Approach: | They propose a framework that facilitates the design and evaluation of LLM citations for medical tasks and a retrieval-citation method that generates high-quality citation. |
| Outcome: | The proposed method achieves superior citation precision and recall improvements compared to strong baseline methods and correlates well with annotation results from professional experts. |
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)
Copied to clipboard
Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu
| Challenge: | a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide. |
| Approach: | They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions . |
| Outcome: | The proposed agents are based on operating systems (OS) and operating systems frameworks. |
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) is effective in Large Language Models (LLMs). However, retrieval noises undermine the quality of LLMs’ generation, necessitating the development of denoising mechanisms. |
| Approach: | They propose a model which integrates reasoning and extracting into one unified trajectory, followed by knowledge token masking to avoid information leakage. |
| Outcome: | Extensive experiments on five benchmark datasets show the superiority of EviOmni, which provides compact and high-quality evidence, enhances the accuracy of downstream tasks, and supports both traditional and agentic RAG systems. |
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)
Copied to clipboard
Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao
| Challenge: | Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL). |
| Approach: | They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
| Outcome: | The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
Toward Fully Exploiting Heterogeneous Corpus:A Decoupled Named Entity Recognition Model with Two-stage Training (2021.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a fundamental and widely used task in natural language processing. |
| Approach: | They propose a decoupled NER model with two-stage training to take advantage of heterogeneous corpus, including dictionaries, distantly supervised instances, and human-annotated instances. |
| Outcome: | Empirical results show that the proposed model improves against baselines and can be scaled to a large extent. |
MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property (2024.lrec-main)
Copied to clipboard
Shiwen Ni, Minghuan Tan, Yuelin Bai, Fuqiang Niu, Min Yang, Bowen Zhang, Ruifeng Xu, Xiaojun Chen, Chengming Li, Xiping Hu
| Challenge: | Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks. |
| Approach: | They propose a benchmark for the evaluation of large language models in the IP domain . they also propose supervised multilingual large language model called MoZi . |
| Outcome: | The proposed model outperforms four well-known LLMs on the MoZIP benchmark . the most powerful ChatGPT does not reach the passing level . |
Overcoming Catastrophic Forgetting by Exemplar Selection in Task-oriented Dialogue System (2024.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that HESIT effectively alleviates catastrophic forgetting by exemplar selection, and achieves state-of-the-art performance on the largest CL benchmark of ToDs in terms of all metrics. |
| Approach: | They propose a method to overcome catastrophic forgetting in task-oriented dialogue systems by tracing their hyper-gradients and a retraining strategy that uses influential exemplars for periodic retrains. |
| Outcome: | The proposed method achieves state-of-the-art on the largest CL benchmark of ToDs in terms of all metrics. |
HyperMem: Hypergraph Memory for Long-Term Conversations (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to long-term memory management rely on pairwise relations, causing fragmented retrieval. |
| Approach: | They propose a hypergraph-based hierarchical memory architecture that explicitly models high-order associations using hyperedges. |
| Outcome: | Experiments show that HyperMem achieves state-of-the-art performance with 92.73% accuracy for long-term conversations. |
Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for large language models (LLMs) have been used to prompt different reasoning thoughts, such as Chain of Thought and Program of Though. |
| Approach: | They propose a framework that prompts large language models with diverse reasoning thoughts by iterating between different prompting methods. |
| Outcome: | The proposed framework is able to generate multiple reasoning thoughts in 10 popular math reasoning datasets and is orthogonal to recent work that makes improvements on single reasoning methods and can generalise to logical reasoning domain. |
Multi-Document Event Extraction Using Large and Small Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to multi-document event extraction have limited attention . despite its practical significance, this task has inherent challenges . |
| Approach: | They propose a collaborative framework that integrates large language models for multi-step reasoning and fine-tuned small language models to handle key subtasks. |
| Outcome: | The proposed framework outperforms existing methods and provides new insights into collaborative reasoning to tackle the complexities of multi-document event extraction. |
Semi-supervised Relation Extraction via Incremental Meta Self-Training (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods suffer from the gradual drift problem, where noisy pseudo labels are incorporated during training. |
| Approach: | They propose a method that uses pseudo labels to assess quality on unlabeled samples . they use a relation label generation network to learn from successful and failed attempts . |
| Outcome: | Experimental results show the proposed method can improve on two public datasets. |
WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning (2024.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that Code Large Language Models can address a wide range of code-related tasks. |
| Approach: | They propose a method to generate widespread and versatile instruction data from open source code datasets and use it to train code-related models. |
| Outcome: | The proposed model outperforms open-source models in generalization ability across code-related tasks. |
Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries. |
| Approach: | They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios. |
| Outcome: | The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities. |
Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to producing presentation slides rely on fixed templates or executable code . Existing methods rely only on predefined templates and emit executable codes . |
| Approach: | They propose a hierarchical slides generation workflow DeepSlides that organizes slide design tasks without any predefined template or style. |
| Outcome: | The proposed framework outperforms baseline methods on evaluated metrics and achieves superior performance in human preference evaluations. |
REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning (D19-1)
Copied to clipboard
| Challenge: | Existing metrics for image captioning evaluation provide an overall quality score, which is difficult to infer specific description errors. |
| Approach: | They propose a fine-grained evaluation method REO for automatically measuring the performance of image captioning systems. |
| Outcome: | The proposed method achieves higher consistency with human judgments and provides more intuitive evaluation results than other metrics. |
PerSphere: A Comprehensive Framework for Multi-Faceted Perspective Retrieval and Summarization (2025.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that the main challenge lies in long context and perspective extraction. |
| Approach: | They propose a benchmark to facilitate multi-faceted perspective retrieval and summarization . they propose measurable metrics to evaluate the comprehensiveness of the retrieval pipeline . |
| Outcome: | The proposed system breaks free from information silos by combining two opposing claims . it can be used to extract multiple perspectives and improve performance on the platform . |
Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues (2025.emnlp-main)
Copied to clipboard
Jinfeng Zhou, Yuxuan Chen, Jianing Yin, Yongkang Huang, Yihan Shi, Xikun Zhang, Libiao Peng, Rongsheng Zhang, Tangjie Lv, Zhipeng Hu, Hongning Wang, Minlie Huang
| Challenge: | Existing approaches to cognitive restructuring (CR) are limited by entrenched cognitive distortions, emotional resistance, and individual differences. |
| Approach: | They propose a framework that structures CR as theory-grounded multi-stage multi-turn dialogue and a multi-channel loop mechanism to account for diverse individual distortions. |
| Outcome: | The proposed framework integrates supportive strategies for emotional management and a multi-channel loop mechanism to account for diverse individual distortions. |
Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition (D19-1)
Copied to clipboard
| Challenge: | Neural architecture search (NAS) is a popular approach for finding new models and freeing researchers from the hard work of designing network architectures. |
| Approach: | They propose differentiable neural architecture search methods for natural language processing . they remove the softmax-local constraint and apply it to named entity recognition . |
| Outcome: | The proposed method outperforms strong baselines on the language modeling task. |
MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings (2026.acl-long)
Copied to clipboard
| Challenge: | Multi-turn, long-horizon tasks require dozens of sequential model calls per episode. |
| Approach: | They propose a cost-aware multi-turn LLM routing tool which encodes interaction history and candidate models into joint history–model embeddings and learns an outcome estimator from logged trajectories to predict turn-level model utility. |
| Outcome: | The proposed model reduces cost and performance by 58.7% on ScienceWorld and on Humanity’s Last Exam (HLE) and even reduces costs for held-out tasks. |
SAM Decoding: Speculative Decoding via Suffix Automaton (2025.acl-long)
Copied to clipboard
| Challenge: | Speculative decoding (SD) methods are inefficient and rely on single retrieval resources. |
| Approach: | They propose a retrieval-based speculative decoding method that adapts the suffix automaton for efficient draft generation by utilizing the generating text sequence and static text corpus. |
| Outcome: | The proposed method can find the longest suffix match and can be integrated with existing methods to generalize to broader domains. |
VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension (2025.acl-long)
Copied to clipboard
| Challenge: | Existing video evaluation benchmarks focus on a single language, typically English, and feature videos rooted in Western cultural contexts. |
| Approach: | They propose a video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension. |
| Outcome: | The proposed video evaluation benchmark bridges cultural, linguistic, and domain divides . existing benchmarks only feature videos from YouTube, Shutterstock, or established video datasets based on cultural diversity . |
Beyond the Answer: Advancing Multi-Hop QA with Fine-Grained Graph Reasoning and Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations of multi-hop question answering systems focus on comparing final answers of reasoning method and given ground-truths. |
| Approach: | They propose a "Planner-Executor-Reasoner" architecture that evaluates reasoning . they propose PER-DP and PER QA architectures that provide ground-truths . |
| Outcome: | The proposed model improves the performance of multi-hop question answering systems. |
Sparse Frame Grouping Network with Action Centered for Untrimmed Video Paragraph Captioning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for paragraph captioning videos without event ground truths generate one sentence for each event, but without event labels, it is difficult to locate the transitions between events and minimize repetition. |
| Approach: | They propose a module that dynamically groups event information with the help of action information for the entire video and excludes redundant frames within pre-defined clips. |
| Outcome: | The proposed module outperforms the state-of-the-art methods on all metrics. |
Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent years have witnessed significant advancements in large language models (LLMs) but still struggle with integrating vision and audio. |
| Approach: | They propose a self-knowledge distillation method to improve vision-audio capabilities of OLLMs by learning from the vision-text components. |
| Outcome: | The proposed method improves vision-audio capabilities of OLLMs by learning from vision-text components, which improves interaction between audio and images and results in improved performance on multimodal tasks. |
GraphNarrator: Generating Textual Explanations for Graph Neural Networks (2025.acl-long)
Copied to clipboard
| Challenge: | Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis. |
| Approach: | They propose to use a generative language model to map input-output pairs to explanations reflecting the model’s decision-making process to generate a model that generates pseudo-labels that capture the model's decisions from saliency-based explanations. |
| Outcome: | Extensive experiments show that GraphNarrator produces human-preferred explanations that are faithful, concise, and human-like. |
Removal of Hallucination on Hallucination: Debate-Augmented RAG (2025.acl-long)
Copied to clipboard
| Challenge: | erroneous or biased retrieval can mislead generation, compounding hallucinations. |
| Approach: | They propose a framework that integrates multi-agent debates into retrieval and generation stages to improve retrieval reliability. |
| Outcome: | The proposed framework improves retrieval reliability, reduces hallucinations and significantly improves overall factual accuracy. |
Value of Information: A Framework for Human–Agent Communication (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to large language model (LLM) agents fail to account for stakes of different decisions. |
| Approach: | They propose a framework that balances task risk, query ambiguity, user effort . they use a value-of-information framework to dynamically weigh the expected utility gain . |
| Outcome: | The proposed model matches or exceeds the best manually-tuned baselines in four domains . it explicitly balances task risk, query ambiguity, and user effort . |
Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model (2025.findings-acl)
Copied to clipboard
Cong Gao, Bo Zhang, Linkang Yang, Minghao Hu, Zhunchen Luo, Xiaoying Bai, Guotong Geng, Jun Zhang, Yunhua Xue
| Challenge: | Existing red-teaming methods require expensive fine-tuning, especially for large LLMs. |
| Approach: | They propose a red-teaming method that uses an ‘evil score’ to evaluate the potential of tokens to contribute to harmful outputs during decoding. |
| Outcome: | The proposed method achieves an ASR of 92.83% on the Llama-3.2-3B-Instruct model, compared to 83.48% with adversarial fine-tuning while using less computational resources. |
OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)
Copied to clipboard
Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou
| Challenge: | Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs. |
| Approach: | They propose a framework that integrates dialogue, reasoning, and personalized recommendation. |
| Outcome: | Experiments across public benchmarks show state-of-the-art performance. |
Why Can Distillation Work with Limited Resources? A Systematic Study (2026.findings-acl)
Copied to clipboard
Xiao Hu, Xingyu Lu, Liyuan Mao, YiFan Zhang, Tianke Zhang, Bin Wen, Fan Yang, Tingting Gao, Guorui Zhou
| Challenge: | Recent advances in large language models have driven reasoning performance . low-resource distillation can boost models' performance, but a framework is missing . |
| Approach: | They conduct a controlled experiment to find out why low-resource distillation can boost model performance . they find that distillation enhances the presence of advanced cognitive behaviors . |
| Outcome: | The proposed model shows more flexible reasoning, the authors show . they show that distillation enhances the presence of advanced cognitive behaviors . |
BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data (2026.eacl-long)
Copied to clipboard
Jaap Jumelet, Abdellah Fourtassi, Akari Haga, Bastian Bunzeck, Bhargav Shandilya, Diana Galvan-Sosa, Faiz Ghifari Haznitrama, Francesca Padovani, Francois Meyer, Hai Hu, Julen Etxaniz, Laurent Prevot, Linyang He, María Grandury, Mila Marcheva, Negar Foroutan, Nikitas Theodoropoulos, Pouya Sadeghi, Siyuan Song, Suchir Salhan, Susana Zhou, Yurii Paniv, Ziyin Zhang, Arianna Bisazza, Alex Warstadt, Leshem Choshen
| Challenge: | prevailing trend in language modeling research is to prioritize scaling, authors say . from infancy to maturity, English learners acquire language through exposure to less than 100M words . |
| Approach: | They propose a multilingual collection of datasets modeling the language a person observes from birth until they acquire a native language. |
| Outcome: | The proposed models outperform models trained on a fixed, developmentally plausible English corpus on various benchmarks. |
CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in conversational IR systems have seen a resurgent interest in conversation . generative query rewrite generates reconstructed query based on the conversation history . |
| Approach: | They propose to use unlabeled data to make further improvements using contrastive co-training paradigm. |
| Outcome: | The proposed model is robust to noise and language style shift under few-shot and zero-shot scenarios. |
Knowledge Association with Hyperbolic Knowledge Graph Embeddings (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for knowledge graphs (KGs) depend on high embedding dimensions and hierarchical structures to achieve expressiveness. |
| Approach: | They propose a hyperbolic relational graph neural network for KG embedding and capture knowledge associations with a high-dimensional transformation. |
| Outcome: | Experiments on entity alignment and type inference show the proposed method is effective and efficient. |
Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation (2026.findings-acl)
Copied to clipboard
Zhen Bi, Zhenlin Hu, Xueshu Chen, Mingyang Chen, Cheng Deng, Yida Xue, Zhen Wang, Qing Shen, Ningyu Zhang, Jungang Lou
| Challenge: | Existing data-centric paradigms equate quality with factuality or diversity and ignore the internal logical complexity of training samples. |
| Approach: | They propose a density-aware re-cognizing optimization strategy that prioritizes high-density logical samples to align training with the model's reasoning boundary. |
| Outcome: | The proposed metric outperforms existing methods and improves reasoning performance without increasing total data volume. |
A Knowledge-Guided Framework for Frame Identification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing frameworks for frame identification are limited to only a few types of frame knowledge. |
| Approach: | They propose a Knowledge-Guided Frame Identification framework that integrates frame knowledge to learn better frame representation. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on two benchmark datasets. |
Bi-Tuning with Collaborative Information for Controllable LLM-based Sequential Recommendation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize sequential recommendation systems rely on item ID sequences, but they lack collaborative knowledge and limited controllability. |
| Approach: | They propose a simple bi-tuning framework with collaborative information for controllable Large Language Model-based Sequential Recommendation (Laser) they incorporate learnable virtual tokens at prefix and suffix of input text to adapt LLMs with collaborative knowledge . |
| Outcome: | The proposed framework outperforms state-of-the-art recommendations on real-world datasets. |
StitchLLM: Serving LLMs, One Block at a Time (2025.acl-long)
Copied to clipboard
Bodun Hu, Shuozhe Li, Saurabh Agarwal, Myungjin Lee, Akshay Jajoo, Jiamin Li, Le Xu, Geon-Woo Kim, Donghyun Kim, Hong Xu, Amy Zhang, Aditya Akella
| Challenge: | Existing techniques like distillation and pruning are not efficient for large language models. |
| Approach: | They propose a dynamic model routing framework that uses a powerful bottom model to process all queries and a lightweight routing mechanism to allocate computational resources appropriately. |
| Outcome: | The proposed framework improves system throughput while minimizing performance degradation. |
Beyond Dynamic Quantization: An Efficient Static Hierarchical Mix-precision Framework for Near-Lossless LLM Compression (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for dynamic quantization are hardware-unfriendly and often lead to large quantization errors in static scenarios. |
| Approach: | They propose a Static Hierarchical Mix-precision Quantization method which quantifies both inter-layer and intra-layer sensitivity through unified derivations involving Hessian. |
| Outcome: | The proposed method achieves 75.58% on zero-shot reasoning tasks while yielding average speedup of 2.86. |
SPARK: Simulating the Co-evolution of Stance and Topic Dynamics in Online Discourse with LLM-based Agents (2025.emnlp-main)
Copied to clipboard
| Challenge: | a new framework for topic evolution and stance dynamics is needed to understand online discourse . topic evolution is central to understanding fragmentation of debates, spread of misinformation . |
| Approach: | They propose a stance and topic evolution reasoning framework for co-evolution of topics and stances through natural language interactions. |
| Outcome: | The proposed framework captures key empirical patterns across five real-world domains. |
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)
Copied to clipboard
Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang
| Challenge: | Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction. |
| Approach: | They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack. |
| Outcome: | The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses. |
ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks (2025.findings-acl)
Copied to clipboard
Jiamu Zhang, Jiayi Yuan, Andrew Wen, Hoang Anh Duy Le, Yu-Neng Chuang, Soo-Hyun Choi, Rui Chen, Xia Hu
| Challenge: | Large Language Models (LLMs) are increasingly adopted across real-world applications . traditional evaluations rely on expensive, domain-specific ground-truth labels . obtaining labeled data is expensive, time-consuming, and often requires domain expertise . |
| Approach: | They propose a ground-truth-free evaluation framework focused on reasoning consistency and instruction following. |
| Outcome: | The proposed framework outperforms existing label-free methods, including majority voting, triplet ranking, and peer-review approaches. |
A Unified Agentic Framework for Evaluating Conditional Image Generation (2025.acl-long)
Copied to clipboard
Jifang Wang, Yangxue Yangxue, Longyue Wang, Zhenran Xu, Yiyu Wang, Yaowei Wang, Weihua Luo, Kaifu Zhang, Baotian Hu, Min Zhang
| Challenge: | Conditional image generation is a popular and personalization-oriented task, but there are challenges in developing task-agnostic, reliable, and explainable evaluation metrics. |
| Approach: | They propose a unified agentic framework for comprehensive evaluation of conditional image generation tasks. |
| Outcome: | The proposed framework achieves a high correlation with human assessments on seven prominent image generation tasks. |
Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection have attracted more attention from the community. |
| Approach: | They propose to model the distributional distance between the regular conditional output and the unconditional output, which is generated without a given input text. |
| Outcome: | The proposed model achieves state-of-the-art on the hallucination benchmarks HADES and other datasets. |
Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework (2026.acl-long)
Copied to clipboard
Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu, Min Zhang
| Challenge: | Existing methods for cross-lingual chain-of-thought (XCoT) with self-consistency are costly due to extensive sampling of full trajectories across languages. |
| Approach: | They propose a cross-lingual chain-of-thought framework that minimizes redundancy in token usage and latency. |
| Outcome: | Experiments on polymath show that UL-XCoT reduces decoding token costs and latency by 50% . UL XCot also aggregates remaining high-quality reasoning paths via voting . |
PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models have demonstrated considerable capabilities across various tasks . however, they often fall short of the performance achieved by domain-specific state-of-the-art models . |
| Approach: | They propose a tuning-free method to augment domain-specific abilities of Large language models . they leverage insights from the response preference of expert models to augment LLMs . |
| Outcome: | The proposed method outperforms the expert model on 4 ScienceWorld tasks. |
Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show superior cross-model transferability . Prompt injection attacks are among the most critical threats . |
| Approach: | They propose an activations-guided prompt injection attack framework to address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box approaches. |
| Outcome: | The proposed framework achieves 49.6% success rate and 34.6% improvement over human-crafted prompts on five mainstream LLMs. |
KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions (2026.acl-long)
Copied to clipboard
Tingyu Wu, Zhisheng Chen, Ziyan Weng, Shuhe Wang, Shuo Zhang, Sen Hu, Silin Wu, Qizhen Lan, Huacan Wang, Ronghao Chen
| Challenge: | Existing long-horizon memory benchmarks use multi-turn dialogues or synthetic user histories . despite rapid progress on long-term memory evaluation, there are gaps in existing benchmarks . |
| Approach: | They propose a long-form autobiographical narrative benchmark that reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions. |
| Outcome: | The proposed benchmarks build from long-form autobiographical narratives . they show that retrieval-augmented systems improve factual accuracy while errors persist on temporally grounded explanations and higher-level inferences. |
CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA (2026.findings-acl)
Copied to clipboard
Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang, Zhang Ke-di
| Challenge: | Text-to-SQL models struggle with complex analytical tasks such as generating simple SQL queries. |
| Approach: | They propose a text-to-sql model that leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning. |
| Outcome: | The proposed model outperforms baseline models on six text-to-SQL benchmarks by 6.44% on average while maintaining good capability on three tableQA benchmarks. |
SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models (2024.acl-long)
Copied to clipboard
Weixiang Zhao, Shilong Wang, Yulin Hu, Yanyan Zhao, Bing Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che
| Challenge: | Existing methods to address catastrophic forgetting and knowledge transfer in large language models (LLMs) ignore potential of aligning the two modules to effectively address catastrophic forgetting and knowledge transfers simultaneously. |
| Approach: | They propose a Shared Attentive Learning & Selection module to align the PET learning and selection modules to address catastrophic forgetting and knowledge transfer simultaneously. |
| Outcome: | Experiments on two CL benchmarks show that the proposed framework is superior when scaled to different model sizes, different model architectures and unseen tasks. |
P2 Law: Scaling Law for Post-Training After Model Pruning (2025.acl-long)
Copied to clipboard
| Challenge: | Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs). |
| Approach: | They propose to use model pruning techniques to maintain high performance while reducing hardware requirements for large language models (LLMs). |
| Outcome: | The proposed model pruning law can be generalized to larger dataset sizes, larger model sizes, and higher pruning rates, offering valuable insights for resource allocation in pruned LLMs. |
Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin
| Challenge: | supervised fine-tuning (SFT) is crucial for multimodal large language models, yet a comprehensive scaling law is lacking . et al.: scaling laws focus on model size, pre-training tokens, and MLLM SFT data volumes . |
| Approach: | They propose two scaling laws to guide optimal model-data configuration . they propose one applicable when training data volumes are well defined by researchers . |
| Outcome: | The proposed scaling laws provide valuable recommendations for optimal resource allocation . they show that the proposed laws are more accurate than existing models . |
DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing code benchmarks for large language models remain static, resulting in data contamination and unreliable evaluation results. |
| Approach: | They propose a dynamic, complexity-aware benchmark that overcomes the limitations of static datasets and provides a memorization-advantaged benchmark. |
| Outcome: | DynaCode generates 189 million unique nested code problems across 4 units of code complexity and 16 types of call graphs. |
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)
Copied to clipboard
Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen
| Challenge: | Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance. |
| Approach: | They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents. |
| Outcome: | The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain. |
A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text (2023.acl-long)
Copied to clipboard
| Challenge: | Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text, but their performance drops drastically when confronted with linguistically complex texts. |
| Approach: | They propose an end-to-end Neural Divide-and-Conquer Reasoning framework for linguistically complex texts that they struggle to comprehend. |
| Outcome: | The proposed framework significantly improves performance in complex image-text reasoning problem. |
AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods treat three modal features equally, without distinguishing the importance of different modalities. Existing models split the video into frames, leading to missing the global acoustic information. |
| Approach: | They propose a global Acoustic feature enhanced Modal-Order-Aware network to address these problems. |
| Outcome: | The proposed model outperforms state-of-the-art models on two public datasets. |
TOREE: Evaluating Topic Relevance of Student Essays for Chinese Primary and Middle School Education (2024.findings-acl)
Copied to clipboard
Xinlin Zhuang, Hongyi Wu, Xinshu Shen, Peimin Yu, Gaowei Yi, Xinhao Chen, Tu Hu, Yang Chen, Yupei Ren, Yadong Zhang, Youqi Song, Binxuan Liu, Man Lan
| Challenge: | Existing research on Automatic Essay Scoring (AES) for Chinese essays has overlooked topic relevance and lacks detailed feedback. |
| Approach: | They propose to use TOREE to assess topic relevance in Chinese primary and middle school students’ essays to improve automatic and human evaluations. |
| Outcome: | The proposed method significantly improves both automatic and human evaluations across four diverse LLMs. |
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios (2026.acl-long)
Copied to clipboard
Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo
| Challenge: | Existing benchmarks fail to capture scenarios in which vulnerabilities are introduced by humans . we evaluate 5 popular code agents supported by 5 LLMs on SecureVibeBench . |
| Approach: | They propose a benchmarking tool that compares 105 C/C++ secure coding tasks . they use real-world open-source vulnerabilities and a comprehensive evaluation tool . |
| Outcome: | The proposed benchmarks show that code agents struggle to produce correct and secure code . the best performing agent produces merely 23.8% correct and secured solutions . |
Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing retrieval-augmented strategies for large language models fail to capture dynamic reasoning required to resolve execution failures. |
| Approach: | They propose a framework that implements Experience Replay to transform transient rectification steps into persistent knowledge. |
| Outcome: | The proposed framework improves model accuracy by 8.45% on complex tasks while reducing token consumption by 28.65% and interaction turns by 25.82%. |
Explaining Length Bias in LLM-Based Preference Evaluations (2025.findings-emnlp)
Copied to clipboard
Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong
| Challenge: | a preference evaluation metric is often biased towards longer responses, revealing a reliability problem . a decomposition of the preference evaluation into two components is needed to understand this bias. |
| Approach: | They propose to decompose the preference evaluation metric into two key components . the first component is length-dependent and related to trustworthiness . |
| Outcome: | The proposed evaluation metric is based on two components: desirability and information mass. |
ChildEval:WHEN LARGE LANGUAGE MODELS MEET CHILDREN’S PERSONALITIES (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved remarkable success in effectively understanding and generating human language, leading to a revolutionary era in LLMs. |
| Approach: | They propose a benchmark to evaluate LLMs' ability to infer and follow child-centered preferences in long-context conversations. |
| Outcome: | The proposed benchmark spans five top-level and fourteen sub-level categories covering children’s daily lives and development. |
Adaptive Learning of Local Semantic and Global Structure Representations for Text Classification (C18-1)
Copied to clipboard
Jianyu Zhao, Zhiqiang Zhan, Qichuan Yang, Yang Zhang, Changjian Hu, Zhensheng Li, Liuxin Zhang, Zhiqiang He
| Challenge: | Existing representation models for text classification learn little structure information or rely on pre-defined structures. |
| Approach: | They propose a sandwich neural network to learn local semantic and global structure representations without relying on parsers. |
| Outcome: | The proposed approach achieves competitive performance on several text classification tasks. |
CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating high-quality, multi-step reasoning are limited . we present a new framework for synthesising rigorous, cognitively diverse problems . |
| Approach: | They propose a cognitive atom-based framework for synthesizing mathematically rigorous problems. |
| Outcome: | The proposed framework outperforms existing methods in accuracy, reasoning depth and diversity while exceeding the difficulty of AIME. |
What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects (2026.findings-eacl)
Copied to clipboard
Naihao Deng, Sheng Zhang, Henghui Zhu, Shuaichen Chang, Jiani Zhang, Alexander Hanbo Li, Chung-Wei Hang, Hideo Kobayashi, Yiqun Hu, Patrick Ng
| Challenge: | a series of paradigm shifts have come with distinct characteristics and challenges associated with table modeling. |
| Approach: | They propose to replicate four table LLMs by instruction-tuning three foundation models on four existing datasets. |
| Outcome: | The results show that base model choice plays a more dominant role than training data itself. |
ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)
Copied to clipboard
Chenyang Song, Xu Han, Zhengyan Zhang, Shengding Hu, Xiyu Shi, Kuai Li, Chen Chen, Zhiyuan Liu, Guangli Li, Tao Yang, Maosong Sun
| Challenge: | Activation sparsity is a promising paradigm for accelerating model inference . few large language models achieve high activation spar and comparable performance . |
| Approach: | They propose a method to achieve activation sparsity and acceleration in large language models . they introduce ReLU activation and adopt progressive sparse regularization . |
| Outcome: | The proposed method achieves high activation sparsity and comparable model performance. |
Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou
| Challenge: | Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging . |
| Approach: | They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning. |
| Outcome: | The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets. |
Efficient Table Retrieval and Understanding with Multimodal Large Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Tabular data is often captured in image form across a wide range of real-world scenarios. |
| Approach: | They propose a framework that enables MLLMs to answer queries over large tables. |
| Outcome: | The proposed framework outperforms existing methods by 7.0% in retrieval recall and 6.1% in answer accuracy on a newly constructed dataset with 48,504 unique tables. |
IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit (2025.findings-acl)
Copied to clipboard
| Challenge: | Visual Question Answering (VQA) is a key task in vehicular systems. |
| Approach: | They propose a benchmark that encompasses diverse automotive scenarios . they use images from front, side, and rear cameras, various road types, weather conditions, and interior views . |
| Outcome: | The proposed benchmark includes images from front, side, and rear cameras, various road types, weather conditions, and interior views. |
Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarity (2025.findings-emnlp)
Copied to clipboard
Ping Chen, Xiang Liu, Zhaoxiang Liu, Zezhou Chen, Xingpeng Zhang, Huan Hu, Zipeng Wang, Kai Wang, Shuming Shi, Shiguo Lian
| Challenge: | ambiguity, polysemy, or uncertainty remain significant challenges in natural language processing. |
| Approach: | They introduce a framework that integrates LLM semantic priors with continuous fuzzy membership degrees to create an explicit interaction between probability-based reasoning and fuzzy membership reasoning. |
| Outcome: | The proposed framework integrates semantic priors with continuous fuzzy membership degrees . it allows ambiguous inputs to be gradually transformed into clear and interpretable decisions . |