Papers by Zhao Yang
NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multi-agent problem solving rely on hand-crafted protocols or automatically designed topologies. |
| Approach: | They propose a state-driven framework that formulates multi-agent problem solving as a finite-state execution process. |
| Outcome: | The proposed framework outperforms baselines on diverse benchmarks by 6.74%–19.39% while reducing token consumption. |
Consistent Representation Learning for Continual Relation Extraction (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to train relation extraction models overfit memory samples and perform poorly on imbalanced datasets. |
| Approach: | They propose a method which uses contrastive learning and knowledge distillation to train a model on data with new relations while avoiding forgetting old ones. |
| Outcome: | The proposed method significantly outperforms state-of-the-art baselines and yields strong robustness on the imbalanced datasets. |
HSDreport: Heart Sound Diagnosis with Echocardiography Reports (2024.findings-emnlp)
Copied to clipboard
Zihan Zhao, Pingjie Wang, Liudan Zhao, Yuchen Yang, Ya Zhang, Kun Sun, Xin Sun, Xin Zhou, Yu Wang, Yanfeng Wang
| Challenge: | Existing methods for heart sound diagnosis are limited to a few fixed categories and do not utilize echocardiography reports, the gold standard in the diagnosis of related diseases. |
| Approach: | They propose a benchmark that mandates the direct utilization of heart sounds obtained from auscultation to predict echocardiography reports. |
| Outcome: | The proposed method outperforms existing methods and existing multimodal LLMs in detecting key abnormalities in heart sounds. |
Neural Topic Modeling with Large Language Models in the Loop (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated promising capabilities in topic discovery, but their direct application to topic modeling suffers from issues such as incomplete topic coverage, misalignment of topics, and inefficiency. |
| Approach: | They propose a novel LLM-in-the-loop framework that integrates Large Language Models with Neural Topic Models (NTMs) global topics and document representations are learned through the NTM, while an LLM refines these topics using an Optimal Transport (OT)-based alignment objective. |
| Outcome: | The proposed framework improves topic interpretability while preserving the efficiency of existing NTMs. |
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation (2025.emnlp-main)
Copied to clipboard
Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Baobao Chang
| Challenge: | Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid ‘5Ws’ questions. |
| Approach: | They propose a data organization paradigm where large language models transform documents into more structured and loosely interconnected LUs. |
| Outcome: | Experiments in open-domain and industrial settings show that the proposed paradigm outperforms existing paradigms and shows high adaptability across diverse document formats. |
VoxpopuliTTS: a large-scale multilingual TTS corpus for zero-shot speech generation (2025.coling-main)
Copied to clipboard
Wenrui Liu, Jionghao Bai, Xize Cheng, Jialong Zuo, Ziyue Jiang, Shengpeng Ji, Minghui Fang, Xiaoda Yang, Qian Yang, Zhou Zhao
| Challenge: | Existing multilingual TTS datasets are limited in speech generation fields due to lack of quality data. |
| Approach: | They propose to use 30,000 hours of high-quality speech data across 3 languages . they filter out low-quality text-text pairs and concatenate short transcripts . |
| Outcome: | The proposed dataset comprises 30,000 hours of high-quality speech data, across 3 languages with multiple speakers and styles, suitable for various speech tasks such as TTS and ASR. |
Head-wise Shareable Attention for Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. |
| Approach: | They propose two methods that share parameters across attention heads to reduce memory usage and reduce performance drop by using coarse-grained weight sharing rules. |
| Outcome: | The proposed methods reuse pre-trained weights without retraining and then share, denoted as PostShare. |
CART: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling (2025.acl-long)
Copied to clipboard
Minghui Fang, Shengpeng Ji, Jialong Zuo, Hai Huang, Yan Xia, Jieming Zhu, Xize Cheng, Xiaoda Yang, Wenrui Liu, Gang Wang, Zhenhua Dong, Zhou Zhao
| Challenge: | Cross-modal retrieval tasks are used to retrieve data from one modality or another based on a query from another modality. |
| Approach: | They propose a generative cross-modal retrieval framework based on coarse-to-fine semantic modeling . they propose combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation. |
| Outcome: | The proposed framework achieves excellent performance and efficiency in multimodal retrieval tasks. |
DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)
Copied to clipboard
Zhenyang Cai, Jiaming Zhang, Junjie Zhao, Ziyi Zeng, Yanchao Li, Liang Jingyi, Junying Chen, Yunjin Yang, Jiajun You, Shuzhi Deng, null Xieruiqiii, Yuanting Chen, Xiangyi Feng, Jianquan Li, Liangyi Chen, Junwen Wang, Shan Jiang, Benyou Wang
| Challenge: | Current multimodal large language models (MLLMs) show limited understanding of dental images. |
| Approach: | They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning. |
| Outcome: | The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks. |
Scaling Laws for Code: Every Programming Language Matters (2026.findings-acl)
Copied to clipboard
Jian Yang, Shuyue Guo, Linzheng Chai, Wei Zhang, Aishan Liu, Chuan Hao, Zhoujun Li, Xin Zhao, Xianglong Liu, Weifeng Lv, Bryan Dai
| Challenge: | Existing studies focus on language-agnostic settings, neglecting the inherently multilingual nature of modern software development. |
| Approach: | They propose a proportion-dependent scaling law that prioritizes high-utility languages . they propose PLs to have varying effects during pre-training that affect model performance . |
| Outcome: | The proposed scaling law is based on 1000+ experiments across multiple languages and models. |
LLM-based Translation Inference with Iterative Bilingual Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies show that the ability of large language models to generate contextual understanding of the sentence can degrade translation quality. |
| Approach: | They propose a method that generates contextual understanding for both source and target languages separately. |
| Outcome: | The proposed method outperforms strong comparison methods in multiple domains. |
Unified Thinker: A General Reasoning Core for Image Generation (2026.acl-long)
Copied to clipboard
Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao
| Challenge: | generative models struggle with logic-intensive instruction following, exposing a persistent reasoning–execution gap. |
| Approach: | They propose a task-agnostic reasoning architecture for general image generation . they propose pixel-level feedback to ground the Thinker's policy in pixel feedback . |
| Outcome: | The proposed system significantly improves image reasoning and generation quality. |
GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs (2026.acl-long)
Copied to clipboard
Weidong Tang, Jierui Li, Yueling Hou, Zihan Mei, Can Zhang, Xinyan Wan, Zhiyuan Liang, Pengfei Zhou, Yang You, Wangbo Zhao
| Challenge: | Existing models for general intelligence fail to model how mental states interact and crystallize into group-level outcomes. |
| Approach: | They propose a multimodal benchmark for group-level Theory of Mind (ToM) to probe nonlinear collective behavior. |
| Outcome: | The proposed model performs significantly below human levels, exposing blind spots in modeling social structures and nonlinear collective behavior. |
Reinforced Efficient Reasoning via Semantically Diverse Exploration (2026.acl-long)
Copied to clipboard
Ziqi Zhao, Zhaochun Ren, Jiahong Zou, Liu Yang, Zhiwei Xu, Xuri Ge, Zhumin Chen, Xinyu Ma, Daiting Shi, Shuaiqiang Wang, Dawei Yin, Xin Xin
| Challenge: | Existing methods for reinforcement learning with verifiable rewards suffer from limited exploration diversity and inefficient reasoning. |
| Approach: | They propose a method that rewards concise and correct reasoning while penalizing unnecessarily long reasoning chains. |
| Outcome: | Extensive experiments on Qwen and Llama models validate the effectiveness and efficiency of ROSE. |
Generalizable Cross-Lingual Cognitive Distortion Detection with Standardized Annotations and Multi-Task Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on cognitive distortion have limited generalizability and performance of models in large-scale and cross-linguistic contexts. |
| Approach: | They propose a multi-task learning model based on teacher student architecture solution which improves generalization performance. |
| Outcome: | The proposed model improves generalizability and interpretability of the proposed model. |
LLMEmbed: Rethinking Lightweight LLM’s Genuine Function in Text Classification (2024.acl-long)
Copied to clipboard
| Challenge: | Recent attempts to improve text classification performance are based on heuristic Chain-of-Thought (CoT) LLMEmbed is a simple and effective transfer learning strategy that can be used to improve the performance of large language models. |
| Approach: | They propose a simple transfer learning strategy to improve text classification using heuristic Chain-of-Thought. |
| Outcome: | The proposed method achieves strong performance on publicly available datasets while using low training overhead. |
A Simple Yet Effective Hybrid Pre-trained Language Model for Unsupervised Sentence Acceptability Prediction (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing unsupervised prediction approaches rely on language models to estimate sentence acceptability . low-frequency words would have a significant negative impact on sentence likelihood . |
| Approach: | They propose a method that substitutes Part-of-Speech (POS) tags for low-frequency words in sentences . their method improves both a sentence acceptability benchmark and a cross-domain sentence evaluation corpus . |
| Outcome: | The proposed method improves on a sentence acceptability benchmark and a cross-domain sentence evaluation corpus. |
Addressing Troublesome Words in Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has weaknesses in handling lowfrequency and ambiguous words, which we refer to as troublesome words. |
| Approach: | They propose to use contextual memory to memorize which target words should be produced in which situations to translate troublesome words. |
| Outcome: | The proposed method outperforms baseline models on Chinese-to-English and English-to German translation tasks. |
RippleCOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | et al., 2022: ripple effect challenges knowledge editing for large language models. |
| Approach: | They propose a method to improve the accuracy of large language models by integrating Chain-of-Thought reasoning into the ICL editing approach. |
| Outcome: | RIPPLE-COT outperforms the state-of-the-art on the ripple effect, with gains ranging from 7.8% to 87.1%. |
MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills (2026.eacl-long)
Copied to clipboard
Zonghai Yao, Zihao Zhang, Chaolong Tang, Xingyu Bian, Youxia Zhao, Zhichao Yang, Junda Wang, Huixue Zhou, Won Seok Jang, Feiyun Ouyang, Hong Yu
| Challenge: | Current clinical LLM benchmarks fail to evaluate advanced clinical skills in AI and large language models (LLMs). |
| Approach: | They propose a framework to evaluate large language models (LLMs) using two instruction-following tasks designed to reflect real clinical scenarios. |
| Outcome: | The proposed framework evaluates LLMs through two instruction-following tasks designed to reflect real clinical scenarios. |
Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions (2025.naacl-industry)
Copied to clipboard
Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra
| Challenge: | Streaming automatic speech recognition models use high power consumption to improve usability and accuracy. |
| Approach: | They propose to optimize on-device speech recognition models by adjusting component energy sensitivities based on their specific energy sensitities to reduce power consumption. |
| Outcome: | The proposed approach achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods. |
Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information (2023.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods for open-domain dialogues are difficult due to the one-to-many issue of the open- domain dialogues. |
| Approach: | They propose a learning-based automatic evaluation metric which can robustly evaluate open-domain dialogues by augmenting CVAEs with a Next Sentence Prediction objective and employing Mutual Information to model the semantic similarity of text in the latent space. |
| Outcome: | The proposed method can evaluate open-domain dialogues on two open- domain dialogue datasets. |
Multi-modal Stance Detection: New Datasets and Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for stance detection for pure texts have limited results to multi-modal content. |
| Approach: | They propose a multi-modal stance detection framework that leverages target information to learn multi-modal stance features from textual and visual modalities. |
| Outcome: | The proposed framework achieves state-of-the-art in multi-modal stance detection on five datasets based on Twitter . |
FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner (2026.acl-long)
Copied to clipboard
Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming, Xiao Luo, Wenbin Zhang, Jiahong Zhao, Yi Guo, Jie Yang
| Challenge: | Existing approaches to mathematical reasoning rely on static heuristics or pre-determined reasoning strategies. |
| Approach: | They propose an adaptive framework that integrates fuzzy theory into LLM-based mathematical reasoning. |
| Outcome: | The proposed framework outperforms state-of-the-art models while offering effective and interpretable diagnostics of intermediate problem-solving states. |
Robust Machine Reading Comprehension by Learning Soft labels (2020.coling-main)
Copied to clipboard
| Challenge: | Neural models have achieved great success on the task of machine reading comprehension, which are typically trained on hard labels. |
| Approach: | They propose a robust training method for machine reading comprehension models to address label sparseness problem by using three strategies to train models on soft labels. |
| Outcome: | The proposed method improves the baseline model performance and achieves state-of-the-art performance on NewsQA and QUOREF. |
CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)
Copied to clipboard
Feiteng Fang, Liang Zhu, Xi Feng, Jinchang Hou, Qixuan Zhao, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang
| Challenge: | Large language models (LLMs) have attracted considerable attention from academic and industrial communities due to their outstanding performance in various natural language processing tasks. |
| Approach: | They propose a Contrastive Learning Framework for Human Alignment to evaluate the noise within the data and dynamically adjust the training process. |
| Outcome: | The proposed framework surpasses other algorithms in terms of reward model scores, automatic evaluations, and human assessments on the widely used dataset "Helpful and Harmless" |
TableVista: Benchmarking Multimodal Table Reasoning under Visual and Structural Complexity (2026.findings-acl)
Copied to clipboard
Zheyuan Yang, Liqiang Shang, Junjie Chen, Xun Yang, Chenglong Xu, Bo Yuan, Chenyuan Jiao, Yaoru Sun, Yilun Zhao
| Challenge: | TableVista evaluates multimodal table reasoning under visual and structural complexity . current models struggle to maintain reasoning consistency when structural complexity combined with visually integrated presentations. |
| Approach: | They propose a benchmark for evaluating multimodal table reasoning under visual and structural complexity. |
| Outcome: | The proposed model performs poorly on visual and structural complexity. |
From Charts to Code: A Hierarchical Benchmark for Multimodal Models (2026.acl-long)
Copied to clipboard
Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang
| Challenge: | Chart2Code is a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models. |
| Approach: | They introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models. |
| Outcome: | The proposed benchmark is the first to scale task complexity while capturing diverse scenarios. |
DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Video-guided Machine Translation (VMT) uses short video clips to enhance translation quality, but many samples are text-sufficient. |
| Approach: | They propose a framework that integrates multimodal large language models’ multimodal reasoning into video-guided machine translation by using a pipeline for constructing training data based on multimodal relevance to translation. |
| Outcome: | The proposed framework improves multimodal information utilization in video-guided machine translation, yielding gains in translation quality and computational efficiency. |
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing (2020.acl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing frameworks rely on nontrivial human labor to generate canonical utterances. |
| Approach: | They propose a framework that uses an unsupervised paraphrase model to parse canonical utterances. |
| Outcome: | The proposed framework is effective and compatible with supervised training. |
Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sparse Mixture-of-Experts (SMoE) architectures require loading all expert parameters . previous work focused on expert pruning and merging but focused on neuron-level structure . |
| Approach: | They propose a task-agnostic framework for expert pruning and reconstruction . it prunes redundant experts using router statistics, then decomposes them into neuron-level expert segments . |
| Outcome: | The proposed framework reduces the number of experts and memory usage, making it easier to deploy. |
Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on identifying event factuality at sentence level, which leads to conflicts between different mentions of the same event. |
| Approach: | They propose a document-level event factuality identification model that uses local uncertainty and global structure to model event factuality. |
| Outcome: | The proposed method outperforms existing models on two widely used datasets. |
SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Video-guided machine translation (VMT) aims to improve translation quality by integrating contextual information from paired short video clips. |
| Approach: | They propose a plug-and-play framework for video-guided machine translation with multimodal large language models. |
| Outcome: | The proposed framework improves performance of MLLMs while reducing computational cost. |
Rethinking Sentiment Style Transfer (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation methods for text style transfer are unsatisfactory. |
| Approach: | They propose to use a graph-based method to extract attribute content from sentences . they propose an efficient regularization to leverage attribute-dependent content as guiding signals. |
| Outcome: | The proposed method is based on a YELP and IMDB dataset and it is able to detect errors in the human evaluation. |
SLARD: A Chinese Superior Legal Article Retrieval Dataset (2025.coling-main)
Copied to clipboard
| Challenge: | Existing retrieval methods struggle to achieve ideal results, a study finds . existing large language models lack prior knowledge of the content of superior legal articles . |
| Approach: | They propose to use a Chinese superior legal article retrieval dataset to find relevant articles with higher legal effectiveness. |
| Outcome: | The proposed dataset shows that existing retrieval methods struggle to achieve ideal results. |
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)
Copied to clipboard
Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo
| Challenge: | Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored. |
| Approach: | They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs. |
| Outcome: | The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs. |
Relation-Aware Question Answering for Heterogeneous Knowledge Graphs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing retrieval-based approaches to solve multihop Knowledge Base Question Answering (KBQA) fail to utilize information from head-tail entities and the semantic connection between relations to enhance the information capturing of relations in KGs. |
| Approach: | They propose to use a dual relation graph to find the answer entity in a knowledge graph . they use primal entity graph reasoning, dual relation grafitment and interaction . |
| Outcome: | The proposed approach achieves significant performance gain over the prior state-of-the-art on two public datasets, WebQSP and CWQ. |
Incorporating Syntax and Lexical Knowledge to Multilingual Sentiment Classification on Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | generative approach to multilingual sentiment classification is based on syntactic and lexical knowledge and requires retraining and tuning. |
| Approach: | They propose to use a sentiment extractor supported by syntactic and lexical resources to enhance multilingual sentiment classification without retraining LLMs. |
| Outcome: | The proposed approach reduces the multilingual sentiment classification error by 33 points and performs well even for nongenerative tasks such as topic classification and sentiment polarity judgment. |
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have been proposed and applied to many NLP tasks, yielding state-of-the-art performance, but high storage and computational costs obstruct them to be effectively deployed on resource-constrained devices and real-time applications. |
| Approach: | They propose a BERT distillation method which allows each intermediate student layer to learn from any intermediate teacher layers. |
| Outcome: | The proposed method can learn from different teacher layers adaptively for different NLP tasks. |
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)
Copied to clipboard
Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang
| Challenge: | Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs). |
| Approach: | They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories. |
| Outcome: | The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks. |
Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation (2025.acl-long)
Copied to clipboard
Andong Chen, Yuchen Song, Kehai Chen, Xuefeng Bai, Muyun Yang, Liqiang Nie, Jie Liu, Tiejun Zhao, Min Zhang
| Challenge: | Experimental results show that our model significantly outperforms existing multimodal MT and text-only MT. |
| Approach: | They propose a stable diffusion-based imagination network into a multimodal large language model to generate an image for each source sentence. |
| Outcome: | The proposed model outperforms existing multimodal and text-only MT and achieves an average improvement of 14 BLEU points on Multi30K and MSCOCO multimodal MT benchmarks. |
A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to address Grammatical Error Correction (GEC) tasks are based on large scale labeled data, which leads to extremely high data annotation costs. |
| Approach: | They propose a Chain-of-Task framework to reduce over-correction in large language models . they propose supervised fine-tuning strategy and an algorithm for automatic dataset annotation . |
| Outcome: | The proposed framework achieves state-of-the-art on both FCGEC (in-domain) and NaCGEC (out-of domain) test sets. |
TriFine: A Large-Scale Dataset of Vision-Audio-Subtitle for Tri-Modal Machine Translation and Benchmark with Fine-Grained Annotated Tags (2025.coling-main)
Copied to clipboard
| Challenge: | Existing video-guided machine translation approaches use coarse-grained visual information, resulting in information redundancy and high computational overhead. |
| Approach: | They propose a fine-grained approach to video-guided machine translation using visual information . they use a large-scale dataset with annotated multimodal fine-grain tags . |
| Outcome: | The proposed approach achieves superior performance with lower computational overhead compared to coarse-grained methods and text-only models. |
TexSmart: A System for Enhanced Natural Language Understanding (2021.acl-demo)
Copied to clipboard
Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, ZhanHui Kang, Shuming Shi
| Challenge: | TexSmart supports fine-grained named entity recognition (NER) Large-scale fine-granular entity types are expected to provide richer semantic information for downstream NLP applications. |
| Approach: | They introduce TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. |
| Outcome: | The proposed system supports fine-grained named entity recognition (NER) and enhanced semantic analysis functions. |
Effective Distillation of Table-based Reasoning Ability from LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing work on table-based reasoning distillation has focused on smaller models with limited performance. |
| Approach: | They propose a table-based reasoning distillation approach to distill LLMs into smaller models . their results show that a 220 million parameter model fine-tuned using distilled data improves performance . |
| Outcome: | The proposed model improves on a scientific table-to-text generation dataset and surpasses specific LLMs. |
Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation (2025.findings-emnlp)
Copied to clipboard
Xing Zhang, Jiaheng Wen, Fangkai Yang, Yu Kang, Pu Zhao, Junhao Wang, Maoquan Wang, Yufan Huang, Shengyu Fu, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing code translation benchmarks focus on individual functions, overlooking repository-level challenges like intermodule coherence and dependency management. |
| Approach: | They propose a framework for benchmarking Java-to-C# translation at the repository level . it uses a translation framework guided by skeletons and fine-grained quality evaluation . |
| Outcome: | The proposed framework improves Java-to-C# translation quality at the repository level. |
A Two-Agent Game for Zero-shot Relation Triplet Extraction (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for relation triplet extraction rely on labeled data and are limited in their applicability. |
| Approach: | They propose a two-agent game approach to deliberate and debate unseen relations by two agents, a generator and an extractor. |
| Outcome: | The proposed method outperforms baseline methods by 6%-16% in F1 scores. |
CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus. |
| Approach: | They propose a power-law relationship between loss, mixture ratio, and training tokens scale and formalize the trade-off between general and domain-specific capabilities. |
| Outcome: | The proposed model achieves the desired domain transfer while maintaining general ability and highest utilization of available resources. |
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding (P19-1)
Copied to clipboard
| Challenge: | Existing methods for review generation lack topical and syntactic characteristics of natural languages. |
| Approach: | They propose a review generation model that uses aspect semantics, syntactic sketch, and context information to generate a sentence and corresponding words. |
| Outcome: | The proposed model can generate long and informative review text for users given a product and her/his rating on it. |
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)
Copied to clipboard
Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Jinchuan Tian, Zhenhui Ye, Luping Liu, Zehan Wang, Ziyue Jiang, Xuankai Chang, Jiatong Shi, Chao Weng, Zhou Zhao, Dong Yu
| Challenge: | Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages. |
| Approach: | They propose to use large language models as a general-purpose interface across multiple tasks and languages. |
| Outcome: | The proposed model performs better on 200K hours of 6-language data for voice generation applications. |
Treasures Outside Contexts: Improving Event Detection via Global Statistics (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing neural-based ED models are confused by changeable contexts during testing . we propose a system that extracts statistical event features from word-event cooccurrence frequencies . |
| Approach: | They propose to integrate a set of statistical event features from word-event co-occurrence frequencies into the training set to cooperate with contextual features. |
| Outcome: | The proposed model outperforms ten strong baselines on ACE2005 and KBP2015 datasets. |
Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization (2026.findings-acl)
Copied to clipboard
Rongjie Huang, Dongchao Yang, Wenxiang Guo, Huadai Liu, Xize Cheng, Zehan Wang, Zhou Zhao, Xixin Wu, Helen M. Meng
| Challenge: | Experimental results show that Flow-matching generative models can scale training by increasing data, computational resources, and model size. |
| Approach: | They propose a flow-matching transformer with masked generative modeling for scaling text-to-audio inference-time prediction. |
| Outcome: | The proposed model scales inference-time computations by masking generation and re-predicting them through iterative decoding. |
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) show exceptional problem-solving capabilities but struggle with complex reasoning tasks. |
| Approach: | They propose a novel RAG approach that integrates retrieved information to guide tree-based reasoning process based on LLMs. |
| Outcome: | The proposed approach outperforms existing methods in large language models . iteratively plans intermediate sub-queries and answers based on the LLM itself . |
ATFormer: A Learned Performance Model with Transfer Learning Across Devices for Deep Learning Tensor Programs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Compilation-based methods with performance models have poor measurement accuracy and transferability between platforms. |
| Approach: | They propose a compiler that automatically generates tensors and automatically tunes them for different hardware platforms. |
| Outcome: | The proposed model reduces inference time and costs on modern DNN benchmarks. |
Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for aspect category sentiment analysis do not necessarily occur in a sentence. |
| Approach: | They propose a Beta Distribution-guided aspect-aware graph construction based on external knowledge . they use aspect-related words as the pivots to derive aspect-relevant weights . |
| Outcome: | The proposed approach outperforms the state-of-the-art methods on 6 benchmark datasets. |
An Auxiliary Task Boosted Multi-task Learning Method for Service Account Retrieval with Limited Human Annotation (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to service account retrieval have limited human annotation, resulting in labor-intensive and time-consuming tasks. |
| Approach: | They propose an Auxiliary task Boosted Multi-Task Learning method which introduces multiple auxiliary tasks and enhances the performance of the main task, service account retrieval. |
| Outcome: | The proposed method improves the performance of the main task, service account retrieval. |
EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to enhance performance of Large language models are limited due to the cost of training data and privacy concerns. |
| Approach: | They propose a method that enhances a finetuned model with its inferior version and adopts contrastive decoding to reduce predicted errors. |
| Outcome: | The proposed method outperforms existing methods in data-scarcity scenarios across three domains and shows that it is more robust and robust. |
Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training (2025.naacl-long)
Copied to clipboard
| Challenge: | Current PP methods face severe bottlenecks, including pipeline bubbles and memory footprint. |
| Approach: | They propose a sequence-level one-forward-one-backward (1F1B) PP method for training LLMs on long sequences with high throughput and memory efficiency. |
| Outcome: | The proposed method achieves 1.14X training throughput with half memory footprint compared to baseline methods . it trains an LLM with 30B parameters on sequences up to 64k tokens using 64X NVIDIA A100 GPUs . |
PiCSAR: Probabilistic Confidence Selection and Ranking for Reasoning Chains (2026.findings-acl)
Copied to clipboard
Joshua Ong Jun Leang, Zheng Zhao, Aryo Pradipta Gema, Sohee Yang, Wai-Chung Kwan, Xuanli He, Wenda Li, Pasquale Minervini, Eleonora Giunchiglia, Shay B Cohen
| Challenge: | Recent studies show that large reasoning models (LLMs) achieve strong performance on complex reasoning tasks. |
| Approach: | They propose a method that scores each candidate generation using the joint log-likelihood of the reasoning and final answer. |
| Outcome: | The proposed method outperforms baselines with 2x fewer samples in 20 out of 25 comparisons. |
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. |
An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4 (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have fine-tuned judge models based on open-source LLMs to evaluate the quality of other LLM. |
| Approach: | They propose to use open-source LLMs to evaluate Large Language Models (LLMs) their empirical results show that the models underperform GPT-4 in several dimensions . |
| Outcome: | The proposed models outperform GPT-4 on several dimensions including generalizability, fairness and adaptability. |
RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems (2026.acl-long)
Copied to clipboard
| Challenge: | LR-bench is a high-fidelity, up-to-date benchmark curated from 2024–2025 AI/NLP manuscripts with five-level self-assessed familiarity ratings collected via a large-scale email survey . |
| Approach: | They propose a reviewer-centric ranking framework that distills each reviewer’s recent publications into compact keyword-based profiles and fine-tunes an embedding model with weak preference supervision constructed from heuristic retrieval signals. |
| Outcome: | The proposed framework outperforms existing benchmarks and the CMU gold-standard dataset in the evaluation of AI/NLP manuscripts. |
Keyphrase Generation via Soft and Hard Semantic Corrections (2022.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments show that CorrKG is capable of generating high-quality keyphrases. |
| Approach: | They propose a correction model CorrKG on top of the MLE pipeline to correct the biases . the adaptive adaptive mass learning scheme is designed to better fit OT and FreqFS . |
| Outcome: | The proposed model overcomes the semantic biases in keyphrase generation using OT and FreqFS techniques. |
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation (2026.acl-long)
Copied to clipboard
Sunzhu Li, Jiale Zhao, Huimin Ren, Zhenlin Wei, Yang Zhou, Jingwen Yang, Shunyu Liu, Kaike Zhang, Chen Wei
| Challenge: | Existing methods for generating open-ended rubrics suffer from scalability bottlenecks and coarse criteria resulting in a supervision ceiling effect. |
| Approach: | They propose a framework for automated Coarse-to-Fine Rubric Generation . their framework uses principle-guided synthesis, multi-model aggregation, difficulty evolution . |
| Outcome: | The proposed framework produces comprehensive and highly discriminative criteria capable of capturing the subtle nuances. |
Debiasing the Fine-Grained Classification Task in LLMs with Bias-Aware PEFT (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to mitigate label biases such as retraining, post-hoc adjustment, and parameter-efficient fine-tuning fail to address prediction propensity and discriminative ability biase. |
| Approach: | They propose a bias-aware optimization framework that incorporates two distinct label balance constraints with a PEFT strategy targeting an intermediate layer to mitigate this issue. |
| Outcome: | The proposed approach outperforms or matches the performance of full-parameter fine-tuning and LoRA, achieving superior results with lower perplexity. |
ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis (2023.findings-acl)
Copied to clipboard
Yakun Yu, Mingjun Zhao, Shi-ang Qi, Feiran Sun, Baoxun Wang, Weidong Guo, Xiaoli Wang, Lei Yang, Di Niu
| Challenge: | Existing methods for multimodal sentiment analysis focus on general knowledge, which is inadequate to identify specific sentiments across modalities. |
| Approach: | They propose a method where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture. |
| Outcome: | The proposed method outperforms all prior methods on three popular benchmarks on multimodal sentiment analysis metrics. |
Latent Inter-User Difference Modeling for LLM Personalization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly integrated into users’ daily lives, leading to a growing demand for personalized outputs. |
| Approach: | They propose a framework that models inter-user differences in the latent space instead of relying on language-based prompts. |
| Outcome: | The proposed framework outperforms baseline methods on personalized review generation. |
Analyzing Chain-of-thought Prompting in Black-Box Large Language Models via Estimated V-information (2024.lrec-main)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) prompting and large language models (LLMs) have shown great potential in improving performance on challenging reasoning tasks. |
| Approach: | They propose a new metric which extends the concept of pointwise V-information to black-box models and quantifies label-relevant new information introduced by CoT prompting. |
| Outcome: | The proposed metric extends the concept of pointwise V-information to black-box models, quantifying label-relevant new information introduced by CoT prompting beyond pre-existing label information. |
CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges (2026.findings-acl)
Copied to clipboard
| Challenge: | Increasing saturation of web data limits further scaling of model intelligence. |
| Approach: | They propose a benchmark to evaluate machine creativity in code generation that combines combinatorial and exploratory creativity through reverse engineering and self-play. |
| Outcome: | The proposed benchmark targets combinatorial and exploratory creativity through reverse engineering and self-play. |
RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained speech Transformers in speech translation systems have facilitated state-of-the-art (SotA) results, but their computational cost is high. |
| Approach: | They propose a Reducer Adaptor block that could be seamlessly integrated within any Transformer-based speech encoding architecture. |
| Outcome: | The proposed Reducer Adaptor block outperforms the existing SotA architecture by an average of 0.68 BLEU score on 8 language pairs from Must-C. |
CB-Whisper: Contextual Biasing Whisper Using Open-Vocabulary Keyword-Spotting (2024.lrec-main)
Copied to clipboard
Yuang Li, Yinglu Li, Min Zhang, Chang Su, Jiawei Yu, Mengyao Piao, Xiaosong Qiao, Miaomiao Ma, Yanqing Zhao, Hao Yang
| Challenge: | End-to-end automatic speech recognition systems struggle to recognize rare name entities such as personal names, organizations and terminologies that are not frequently encountered in the training data. |
| Approach: | They propose a convolutional neural network-based ASR system that performs open-vocabulary keyword-spotting before the decoder to match the features between the entities and the utterances. |
| Outcome: | The proposed system significantly improves mixed-error-rate (MER) and entity recall compared to the original Whisper model on three internal datasets and two publicly available datasets. |
Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA (2024.acl-long)
Copied to clipboard
Yue Fan, Jing Gu, Kaiwen Zhou, Qianqi Yan, Shan Jiang, Ching-Chen Kuo, Yang Zhao, Xinze Guan, Xin Wang
| Challenge: | Multipanel images are a common form of visual representations, and humans can achieve approximately 99% accuracy on these questions. |
| Approach: | They propose a benchmark that tests multipanel visual reasoning models with 6,600 triplets of questions, answers, and multipanel images. |
| Outcome: | The proposed benchmark features 6,600 triplets of questions, answers, and multipanel images that challenge state-of-the-art Multimodal Large Language Models (MLLMs) human users can attain approximately 99% accuracy on these questions, compared with previous benchmarks. |
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)
Copied to clipboard
Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing
| Challenge: | Texar is an open-source text generation toolkit that supports a broad set of text generation tasks. |
| Approach: | They introduce Texar, an open-source text generation toolkit that supports text generation tasks. |
| Outcome: | Texar supports machine translation, summarization, dialog, content manipulation, and more. |
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) face memory challenges due to the high cost of backpropagation. |
| Approach: | They propose a zeroth-order (ZO) optimization that matches memory usage to inference . they propose scalable and memory-efficient zeroth order (ZE) optimizer that integrates annealed A-GNB gradients with diagonal Hessian estimation and layer-wise clipping as a second-order pre-conditioner. |
| Outcome: | The proposed algorithm outperforms state-of-the-art methods with an average speedup of 20 over MeZO on RoBERTa-large and OPT-1.3B. |
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)
Copied to clipboard
Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs. |
| Approach: | They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge. |
| Outcome: | Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 . |
Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation metrics struggle to evaluate adversarial negative examples . existing metrics struggle in handling adversarials, resulting in low correlations with human judgments. |
| Approach: | They propose a framework that integrates AMR and domain-specific language models for automatic open-domain dialogue evaluation. |
| Outcome: | The proposed evaluation framework achieves strong correlations with human judgments across multiple datasets. |
Rethinking Multi-Modal Alignment in Multi-Choice VideoQA from Feature and Sample Perspectives (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to VideoQA focus on utilizing frame- or object-level visual representations, but they neglect visual-language interactions. |
| Approach: | They propose to break down video into trajectories and first leverage trajectory feature in VideoQA to enhance alignment between two modalities. |
| Outcome: | The proposed method outperforms all the state-of-the-art models on the NExT-QA benchmark. |
Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion (2025.findings-emnlp)
Copied to clipboard
Yujian Liu, Jiabao Ji, Tong Yu, Ryan A. Rossi, Sungchul Kim, Handong Zhao, Ritwik Sinha, Yang Zhang, Shiyu Chang
| Challenge: | Existing methods to integrate external information into a given table neglect the structured nature of the table. |
| Approach: | They propose a simple yet effective method to integrate external information into a given table by first building an augmenting table and then generating a SQL query over the two tables to answer the question. |
| Outcome: | The proposed method outperforms strong baselines on three table QA benchmarks. |
MccSTN: Multi-Scale Contrast and Fine-Grained Feature Fusion Networks for Subject-driven Style Transfer (2024.lrec-main)
Copied to clipboard
| Challenge: | Stylistic style transfer is an important part of the image processing field . due to the low semantic similarity between the original image and the style image, many fine-grained style features are discarded. |
| Approach: | They propose a new style representation and transfer framework that can be adapted to existing image style transfers. |
| Outcome: | The proposed framework can be adapted to existing image style transfers. |
Sentence-Level Agreement for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Empirical results show that a sentence-level agreement module can significantly improve the performance of neural machine translation (NMT) |
| Approach: | They propose a sentence-level agreement module to minimize the difference between the representation of source and target sentences. |
| Outcome: | Empirical results show the proposed agreement module significantly improves translation performance. |
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)
Copied to clipboard
Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu
| Challenge: | Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects. |
| Approach: | They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt. |
| Outcome: | The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks. |
Dynamic Stashing Quantization for Efficient Transformer Training (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks. |
| Approach: | They propose a dynamic quantization strategy that reduces the amount of memory operations and reduces arithmetic cost by 20.95 on two translation tasks and three classification tasks. |
| Outcome: | The proposed model reduces the amount of arithmetic operations by 20.95 and the number of DRAM operations by 2.55 on two translation tasks and three classification tasks. |
Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models (2026.findings-acl)
Copied to clipboard
Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong
| Challenge: | Vision-Language Models (VLMs) have advanced multimodal learning, driving progress in cross-modal reasoning. |
| Approach: | They propose to examine moral robustness of vision-language models by analyzing their moral stances under multimodal perturbations. |
| Outcome: | The proposed model-agnostic multimodal perturbations expose VLMs to a variety of moral vulnerabilities, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion. |
Large Language Models are In-context Teachers for Knowledge Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | In-context teaching is a method of providing in-concept example rationales to a student to reason over unseen cases. |
| Approach: | They propose to use an LLM's self-elicited explanations as in-context demonstrations to prompt a student to reason over unseen cases. |
| Outcome: | The proposed model outperforms human-crafted demonstrations on medical question answering and human-created models outperfect human-made demonstrations. |
SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)
Copied to clipboard
Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke
| Challenge: | Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis. |
| Approach: | They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis. |
| Outcome: | SciAssess evaluates 11 LLMs on multiple tasks across scientific fields. |
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection (2025.acl-long)
Copied to clipboard
Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu
| Challenge: | Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer. |
| Approach: | They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions. |
| Outcome: | The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios. |
Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to generalize deep neural networks are datahungry and generalize poorly from small datasets. |
| Approach: | They propose an agreement score to evaluate routing processes at instance-level and an adaptive optimizer to enhance routing. |
| Outcome: | The proposed approach improves on two NLP tasks and in low-resource settings with few training instances. |
CR-GIS: Improving Conversational Recommendation via Goal-aware Interest Sequence Modeling (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to determine a goal item by sequentially tracking users’ interests ignore the rich goal-aware implicit interest sequence patterns in a dialog. |
| Approach: | They propose to model goal-aware implicit user interest sequence patterns in a dialog and a hierarchical Star Transformer to guide multi-turn utterances generation. |
| Outcome: | The proposed framework achieves more accurate recommendations with more fluent and coherent dialog utterances. |
An Iterative Emotion Interaction Network for Emotion Recognition in Conversations (2020.coling-main)
Copied to clipboard
| Challenge: | Emotion recognition in conversations (ERC) is a task that aims to recognize the emotion of each utterance in conversations. |
| Approach: | They propose an iterative emotion interaction network which uses iterativly predicted emotion labels instead of gold emotion labels to explicitly model the emotion interaction. |
| Outcome: | The proposed method retains state-of-the-art performance on two datasets and achieves high accuracy. |
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work shows that probabilistic context-free grammars with neural parameterization can be effective in unsupervised constituency parsing. |
| Approach: | They propose a parameterization form of PCFGs based on tensor decomposition which has at most quadratic computational complexity in the symbol number. |
| Outcome: | The proposed model improves unsupervised constituency parsing performance across ten languages. |
ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)
Copied to clipboard
Jiaming Zhou, Shiyao Wang, Shiwan Zhao, Jiabei He, Haoqin Sun, Hui Wang, Cheng Liu, Aobo Kong, Yujie Guo, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin
| Challenge: | Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0. |
| Approach: | They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes. |
| Outcome: | The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation. |
Dependency-aware Prototype Learning for Few-shot Relation Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for few-shot relation classification fail to distinguish multiple relations that co-exist in one sentence. |
| Approach: | They propose a dependency-aware prototype learning method for few-shot relation classification . they utilize dependency trees and shortest dependency paths as structural information . |
| Outcome: | The proposed method achieves better performance than baselines on the FewRel dataset. |
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models (2025.emnlp-main)
Copied to clipboard
Jiajun Zhou, Yifan Yang, Kai Zhen, Ziyue Liu, Yequan Zhao, Ershad Banijamali, Athanasios Mouchtaris, Ngai Wong, Zheng Zhang
| Challenge: | Large Language Models (LLMs) are quantized to lower precision to reduce memory cost and latency in inference. |
| Approach: | They propose a quantized zeroth-order framework for fine-tuning Large Language Models (LLMs) using low-precision forward passes. |
| Outcome: | The proposed method achieves comparable results to first-order methods in FP8 and superior accuracy in INT8 and INT4 training. |
Improving Alignment in LVLMs with Debiased Self-Judgment (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for aligning LVLMs rely on external datasets, human annotations or complex post-processing. |
| Approach: | They propose a method that generates a debiased self-judgment score for LVLMs . this self-evaluation metric is created internally by the model without external resources . |
| Outcome: | The proposed approach outperforms existing methods in reducing hallucinations and safety concerns. |
Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs (2026.acl-long)
Copied to clipboard
Jinhui Chen, Shizhu He, Xingchang Yang, Huanxuan Liao, Yequan Wang, Xiangwen Liao, Wenhao Teng, Kang Liu, Jun Zhao
| Challenge: | Existing continual learning paradigms prioritize instant performance through dense updates, leading to catastrophic forgetting and rapid exhaustion of model capacity. |
| Approach: | They propose a method that preserves previously acquired knowledge and acquires new task-specific skills while preserving sufficient parameter capacity for subsequent adaptation. |
| Outcome: | The proposed method is based on the brain's functional partitioning and can be used to map tasks between specialized and generalist neurons. |
Composite Backdoor Attacks Against Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated superior performance on various tasks, but untrustworthy third-party LLMs may covertly introduce vulnerabilities for downstream tasks. |
| Approach: | They propose a composite backdoor attack that scatters multiple trigger keys in different prompt components. |
| Outcome: | The proposed attack achieves 100% Attack Success Rate (ASR) with a False Triggered Rate (FTR) below 2.06% and negligible model accuracy degradation. |
Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for prompt tuning for Large Language Models find backdoor attacks to be significant in data-rich scenarios. |
| Approach: | They propose a backdoor attacks through contrastive-enhanced machine unlearning in data-limited scenarios . they use a machine un learning method to capture precise backdoor patterns . |
| Outcome: | The proposed method captures precise backdoor patterns without association between triggers and backdoors, reducing side effects. |
New Intent Discovery with Attracting and Dispersing Prototype (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for detecting new intents with labeled data are not cluster-friendly . a robust prototypical attracting learning (RPAL) method is designed to compel instances to gravitate toward their corresponding prototype . |
| Approach: | They propose a robust and adaptive prototypical learning framework for globally distinct decision boundaries for both known and new intent categories. |
| Outcome: | The proposed method improves on CLINC, BANKING, and StackOverflow benchmarks on three challenging benchmarks. |
Q-learning with Language Model for Edit-based Unsupervised Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Unsupervised text summarization methods are promising, but their performance is still behind that of state-of-the-art supervised methods. |
| Approach: | They propose a method based on Q-learning with an edit-based summarization that uses an Editorial Agent and Language Model converter to predict edit actions. |
| Outcome: | The proposed method delivers competitive performance even with zero paired data, while requiring no validation set. |
ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show ToM outperforms existing divide-and-conquer frameworks . RAG relies on similarity-based rankings to retrieve and reason over chunks based on logical coherence . |
| Approach: | They propose a Tree-oriented MapReduce framework for long-context reasoning . it leverages the hierarchical structure of long documents by constructing a DocTree . |
| Outcome: | Experimental results show that ToM outperforms existing divide-and-conquer frameworks and RAGs . the proposed framework improves logical coherence and long-context reasoning on 70B+ LLMs compared to existing approaches . |
Nested Named Entity Recognition as Corpus Aware Holistic Structure Parsing (2022.coling-1)
Copied to clipboard
| Challenge: | Named entity recognition is a natural language processing task . nested NER is based on a linear structure, but there is no research on applying corpus-level information to NER. |
| Approach: | They propose a holistic structure parsing algorithm to reveal the entire NEs in a sentence . they introduce points-wise mutual information and other frequency features from corpus-aware statistics . |
| Outcome: | The proposed model outperforms existing models on widely-used benchmarks and achieves state-of-the-art. |
KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to design the interaction strategy between large language models and knowledge graphs (KGs) are not effective for large language model (LLM)s to solve complex tasks due to the large volume and structured format of KG data. |
| Approach: | They propose an LLM-based agent framework that enables small LLMs to actively make decisions over knowledge graphs. |
| Outcome: | The proposed framework outperforms existing methods on in-domain and out-domain datasets using 10K samples. |
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)
Copied to clipboard
Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui
| Challenge: | coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored . |
| Approach: | They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding. |
| Outcome: | The proposed benchmark aims to accelerate the development of more scaffold-aware agents. |
PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM agents generate verbose and inefficient natural language plans to guide reasoning, which restricts agents’ ability to generalize across similar tasks. |
| Approach: | They propose a pseudocode-style planning guide optimization method that captures the structural logic of reasoning and uses two planning-oriented rewards to enhance agent learning. |
| Outcome: | The proposed method outperforms existing LLM agents on representative agent benchmarks and outperformed the current leading baselines. |
PITA: Prompting Task Interaction for Argumentation Mining (2024.acl-long)
Copied to clipboard
| Challenge: | Argumentation mining (AM) aims to detect arguments and their inherent relations from textual compositions. |
| Approach: | They propose a method to model the inter-relationships among three subtasks within a generative framework. |
| Outcome: | The proposed method achieves state-of-the-art performance on two AM benchmarks. |
Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
Qibin Wang, Pu Zhao, Shaohan Huang, Fangkai Yang, Lu Wang, Furu Wei, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing approaches to test-time scaling are limited due to the quality of candidate responses. |
| Approach: | They propose a new metric to quantify the relative improvement of self-refinement beyond majority voting. |
| Outcome: | The proposed method achieves state-of-the-art performance across five benchmarks over other methods. |
EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation (2026.acl-long)
Copied to clipboard
Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao
| Challenge: | Existing methods for story evaluation lack reasoning capabilities for open-source models . evolvR framework provides high-fidelity evaluators for story generation tasks . |
| Approach: | They propose a framework that self-synthesizes chain-of-thought data via a multi-persona strategy . they propose evolvR to provide a reward model for story generation . |
| Outcome: | The proposed framework achieves state-of-the-art performance on three evaluation benchmarks . it also enhances the quality of generated stories, validating the superiority of the framework . |
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 . |
SmartSpanNER: Making SpanNER Robust in Low Resource Scenarios (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is one of the most fundamental tasks in natural language processing. |
| Approach: | They propose a method which introduces a Named Entity Head (NEH) prediction task to SpanNER and performs multi-task learning together with task of span classification. |
| Outcome: | The proposed method improves the robustness of SpanNER in low resource scenarios on the CoNLL03, Few-NERD, GENIA and ACE05 benchmark datasets. |
ParaCook: On Time-Efficient Planning for Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang
| Challenge: | Existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. |
| Approach: | They propose a framework for large language models that allows agents to plan long-horizon tasks in a scalable way. |
| Outcome: | The proposed framework is based on the Overcooked game and can be used to evaluate time efficiency-aware multi-agent planning. |
A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation (D19-1)
Copied to clipboard
| Challenge: | Existing methods favor uninformative and non replier-specific responses due to lack of relevant information guidance. |
| Approach: | They propose to use a semi-supervised variable network to generate replier-specific responses . they use vMF as latent space to obtain stable KL performance . |
| Outcome: | The proposed model outperforms baseline models on two large conversation datasets and generates diverse and replier-specific responses. |
Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning Tasks (2025.acl-long)
Copied to clipboard
| Challenge: | Existing models excel in arithmetic reasoning but their generalization capabilities are incompletely understood. |
| Approach: | They propose a theoretical framework for understanding the generalization behaviors of transformers in arithmetic tasks, focusing on length generalization. |
| Outcome: | The proposed framework can predict generalization behaviors in transformers with a high translation invariance and base mismatch in modular operations. |
MathSight: A Benchmark Exploring Have Vision-Language Models Really Seen in University-Level Mathematical Reasoning? (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks rarely isolate how much visual information contributes to reasoning . a growing collection of benchmarks has catalyzed rapid progress in multimodal reasoning - but how much it contributes remains unclear . |
| Approach: | They propose a university-level multimodal mathematical reasoning benchmark to quantify the effect of visual input. |
| Outcome: | The proposed benchmark disentangles and quantifies the effect of visual input on multimodal reasoning models. |
LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods struggle to capture the visual layout in complex document images. |
| Approach: | They propose to integrate layout knowledge into document image translation by using a layout-aware encoder and a multi-step conductive decoder to achieve the translation step by step. |
| Outcome: | The proposed model outperforms state-of-the-art methods with better parameter efficiency. |
CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent Layers (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve inference efficiency target to reduce per-layer latency, but ignore cumulative latency due to number of layers. |
| Approach: | They propose to identify quasi-independent layers that can be concurrently computed to significantly decrease inference latency. |
| Outcome: | Empirical results show that the proposed method reduces latency by 48.3% on LLaMA-33B while maintaining close level of performance. |
LaCo: Large Language Model Pruning via Layer Collapse (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for model quantization, knowledge distillation, and model pruning are limited by hardware support limitations and the need for extensive training. |
| Approach: | They propose a layer-wise structured pruner that collapses rear model layers into a prior layer and enables a rapid reduction in model size while preserving the model structure. |
| Outcome: | The proposed pruner outperforms state-of-the-art pruning methods at pruning ratios of 25-30% and maintains an average task performance of over 80% at different pruning ratio. |
LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection (2025.acl-industry)
Copied to clipboard
| Challenge: | e-commerce payment fraud detection is a new area for reinforcement learning (RL) and Large Language Models (LLMs). |
| Approach: | They propose to integrate reinforcement learning (RL) with Large Language Models (LLMs) by framing transaction risk as a multi-step Markov Decision Process (MDP), RL optimizes risk detection across multiple payment stages. |
| Outcome: | The proposed approach improves fraud detection accuracy and demonstrates zero-shot capability. |
Document-Level Relation Extraction via Pair-Aware and Entity-Enhanced Representation Learning (2022.coling-1)
Copied to clipboard
| Challenge: | Existing document-level relation extraction methods are sparse in relational entity pairs and the representation of entity pairs is insufficient. |
| Approach: | They propose a Pair-Aware and Entity-Enhanced(PAEE) model to solve two challenges . they propose predicting potential relational entity pairs and assembling directional entity pairs . |
| Outcome: | The proposed model can obtain state-of-the-art performance on four benchmark datasets . it can predict potential relational entity pairs and assemble directional entity pairs . |
Rumor Detection on Social Media with Crowd Intelligence and ChatGPT-Assisted Networks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing research on rumor detection challenges the expressive power of text encoding sequences, and insufficient mining of semantic structural information. |
| Approach: | They propose a Crowd Intelligence-based semantic feature learning module to capture textual content’s sequential and hierarchical features and a knowledge-based structural mining module that leverages ChatGPT for knowledge enhancement. |
| Outcome: | The proposed system achieves performance improvement in rumor detection tasks validating the effectiveness and rationality of using large language models as auxiliary tools. |
Efficient Prior-Guided Reasoning for Robust Retrieval-Augmented Generation under Conflicts (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) has become a standard paradigm for grounding Large Language Models (LLMs) however, performance degrades substantially when faced with noisy, outdated, or conflicting retrieved information. |
| Approach: | They propose a framework that explicitly elicits the model’s parametric knowledge as prior information to guide reasoning on retrieved documents. |
| Outcome: | The proposed framework achieves robust performance across varying degrees of external inconsistency and noise. |
A Survey of RAG-Reasoning Systems in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, Philip S. Yu
| Challenge: | a survey of RAG-based reasoning-based approaches shows that it is not effective for multi-step inferences. |
| Approach: | They map how advanced reasoning optimizes each stage of RAG . they show how retrieved knowledge supply missing premises and expand context for complex inference . |
| Outcome: | The proposed frameworks achieve state-of-the-art across knowledge-intensive benchmarks. |
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation (2026.acl-long)
Copied to clipboard
Jin Cui, Jiaqi Guo, Jiepeng Zhou, Ruixuan Yang, Jiayi Lu, Jiajun Xu, Jiangcheng Song, Boran Zhao, Pengju Ren
| Challenge: | Existing approaches restrict students to following a single golden rationale and treat different reasoning paths independently, causing suboptimal performance. |
| Approach: | They propose a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction and employ a feedback-driven inertia calibration mechanism to align supervision with the student’s current adaptability. |
| Outcome: | Experiments show that the proposed framework achieves state-of-the-art performance on both in-distribution and out-of distribution benchmarks. |
MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)
Copied to clipboard
Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, Guanghui Fu
| Challenge: | Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability. |
| Approach: | They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions. |
| Outcome: | The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications. |
RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026.acl-long)
Copied to clipboard
Zhiyuan Peng, Xin Yin, Pu Zhao, Fangkai Yang, Lu Wang, Ran Jia, Xu Chen, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing benchmarks focus on isolated function/class-level generation, neglecting complete microservice repository generation. |
| Approach: | They propose a multilingual benchmark for repository-level end-to-end web microservice generation that reflects real-world development workflows. |
| Outcome: | The benchmark compared 106 repositories across 18 domains and 11 frameworks and 1,258 API endpoints and 2,335 test cases. |
Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM-based agents lack inherent spatial awareness, relying on web search or text matching while hallucinating spatial relationships. |
| Approach: | They propose a spatial-based agent that can perform real-world geospatial computations . they use natural-language questions to parse into executable workflows based on geoFlow Graphs - directed acyclic graphs with nodes corresponding to spatial concepts and edges representing transformations. |
| Outcome: | The proposed agent outperforms existing baselines on MapEval-API and MapQA benchmarks while producing interpretable and executable geospatial workflows. |
RTADev: Intention Aligned Multi-Agent Framework for Software Development (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are efficient assistants to humans in software development tasks, but they can cause errors during the development process. |
| Approach: | They propose an intention aligned multi-agent framework that ensures that all agents work based on a consensus. |
| Outcome: | The proposed framework reduces errors and improves the quality of generated software code. |
VQA-Augmented Machine Translation with Cross-Modal Contrastive Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multimodal machine translation methods often extract visual features using pre-trained models while learning text features from scratch, leading to representation imbalance. |
| Approach: | They propose a cross-modal VQA-augmented multimodal machine translation method . it aligns image-source text pairs and image-question text pairs through dual-text contrastive learning . |
| Outcome: | The proposed method outperforms state-of-the-art methods on multiple evaluation metrics. |
Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to ACE event detection treat multiple events in one sentence as independent ones and recognize them separately. |
| Approach: | They propose a hierarchical and bias tagging network framework to detect multiple events in one sentence collectively and a gated multi-level attention mechanism to automatically extract and fuse the sentence-level and document-level information. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on a 2005 ACE dataset. |
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation (2023.acl-long)
Copied to clipboard
| Challenge: | MMDialog is a dataset of 1.08 million real-world dialogues with 1.53 million unique images across 4,184 topics. |
| Approach: | They propose to use a curated set of 1.08 million dialogues with 1.53 million unique images to generalize the open domain. |
| Outcome: | The proposed system can predict responses to multi-modal content with state-of-the-art techniques and measure their performance. |
On Safety Risks in Experience-Driven Self-Evolving Agents (2026.findings-acl)
Copied to clipboard
Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, Hao He, Wanxiang Che, Bing Qin, Ting Liu
| Challenge: | Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. |
| Approach: | They investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments. |
| Outcome: | The findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation. |
Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, introducing words from irrelevant utterances. |
| Approach: | They propose a framework to capture the multi-granularity of semantic information and fetch the relevant utterance. |
| Outcome: | The proposed framework outperforms state-of-the-art models on two benchmark datasets . it can capture the source of important words and fetch the relevant utterance . |
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. |
Duplicate-Aware Controlled Code Generation: Enhancing Copyright Protection with Targeted Reordering Beam Search in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Experimental results demonstrate that TRBS effectively reduces verbatim repetition while maintaining functional adequacy. |
| Approach: | They propose a plug-and-play decoding method that dynamically reorders beam candidates to reduce direct copying. |
| Outcome: | The proposed method reduces verbatim repetition while maintaining functional adequacy on a multi-language code generation benchmark. |
Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation frameworks often rely on single-frame assessments, which can lead to outcome-hacking. |
| Approach: | They propose a process-aware evaluation paradigm that uses a hierarchical rubric to evaluate the validity of the intermediate steps and the final result. |
| Outcome: | The proposed model achieves POC@1.0 only about 20% and exhibits significant outcome-hacking. |
Table-R1: Inference-Time Scaling for Table Reasoning Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | In this study, we explore inference-time scaling on table reasoning tasks. |
| Approach: | They propose a large-scale dataset of reasoning traces and a reinforcement learning with verifiable rewards approach to enable inference-time scaling on table reasoning tasks. |
| Outcome: | The proposed model matches or exceeds GPT-4.1 and DeepSeek-R1 models on diverse table reasoning tasks. |
LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation (2025.coling-main)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) is currently the most commonly used PEFT method for fine-tuning models with billions of parameters. |
| Approach: | They propose to use low-rank Adaptation to evaluate LoRA parameter features and then retain LoRA for important layers and the other layers share the same LoRA. |
| Outcome: | The proposed method achieves comparable performance to full fine-tuning and LoRA while retaining 50% of the LoRA parameters on average. |
STAD: Self-Training with Ambiguous Data for Low-Resource Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches for low-resource relation extraction use only confident instances and uncertain instances. |
| Approach: | They propose a self-training approach for low-resource relation extraction using auto-annotated instances. |
| Outcome: | The proposed method improves on two widely used datasets with low-resource settings. |
LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild (2024.findings-acl)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) is an effective yet efficient solution for fine-tuning large language models. |
| Approach: | They propose a low-rank Adaptation framework that retrieves and composes multiple LoRAs according to input prompts. |
| Outcome: | Experimental results show that LoraRetriever outperforms baselines in terms of performance and versatility. |
PlotGen-Bench: Evaluating VLMs on Generating Visualization Code from Diverse Plots across Multiple Libraries (2026.findings-acl)
Copied to clipboard
| Challenge: | PlotGen-Bench evaluates vision-language models' ability to generate executable visualization code from plots under realistic and complex visualization requirements. |
| Approach: | They propose a benchmark to evaluate plot-to-code generation in vision-language models . they use Matplot, Matplos, Mat3D, Mat4D, and Mat4E to evaluate their performance . |
| Outcome: | The proposed benchmark covers 9 major categories, 30 subcategories, and 3 core tasks . it covers 2D, 3D and animated plots across 5 widely used visualization libraries. |
Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to integrate knowledge graph (KG) with neural machine translation (NMT) have two problems: knowledge under-utilization and granularity mismatch. |
| Approach: | They propose a multi-task learning method on sub-entity granularity to combine machine translation and knowledge reasoning tasks. |
| Outcome: | The proposed method significantly outperforms baseline models on translation tasks and handling the entities. |
LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)
Copied to clipboard
Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang
| Challenge: | LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases . |
| Approach: | They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website . |
| Outcome: | The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks. |
Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing (2025.naacl-long)
Copied to clipboard
| Challenge: | Current approaches for detoxification or preventing jailbreaking involve fine-tuning billions of parameters through gradient descent with substantial computational cost. |
| Approach: | They propose to use supervised fine-tuning and Reinforcement Learning from human feedback to modify LLMs' behavior by directly editing a small subset of parameters. |
| Outcome: | Experiments show that editing a small subset of parameters can modulate specific behaviors of LLMs, such as detoxification and resistance to jailbreak, with only inference-level computational resources. |
DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data (P18-4)
Copied to clipboard
| Challenge: | Existing methods to extract events from documents are limited due to the high cost of labeling . Experimental results demonstrate the effectiveness of a document-level Chinese financial event extraction system. |
| Approach: | They propose a document-level Chinese financial event extraction framework which detects event mentions and extracts events from financial news. |
| Outcome: | The proposed system detects event mentions and extracts events from financial news . it can generate large scale labeled data and extract events from entire document . |
I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)
Copied to clipboard
Huilin Deng, Hongchen Luo, Yue Zhu, Long Li, Zhuoyue Chen, Xinghao Zhao, Ming LI, Chuyang Zhao, Jihai Zhang, MengChang Wang, Yang Cao, Yu Kang
| Challenge: | Existing methods for large language model reasoning suffer from exploration collapse due to the semantic homogeneity of random rollouts. |
| Approach: | They propose to use latent policy optimization via iterative information bottleneck to optimize reasoning trajectories by diversifying reasoning . |
| Outcome: | Empirical results show that the proposed method achieves state-of-the-art performance with margins of up to 5.3% in accuracy and 7.4% in diversity metrics. |
FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in latent diffusion models (LDMs) have markedly enhanced text-to-audio generation, yet their iterative sampling processes impose substantial computational demands, limiting practical deployment. |
| Approach: | They propose to learn straight flow for fast simulation by using flashAudio with rectified flows and immiscible flow to minimize the total distance of data-noise pairs in a batch vias assignment. |
| Outcome: | The proposed method can learn straight flow for fast simulations and reduce noise distribution. |
GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to perform large-scale query-passage retrieval are term-based, but they lose interaction between query-pastage pairs. |
| Approach: | They propose to fuse query (passage) information into query representations via graph neural networks that are constructed by queries and their top retrieved passages. |
| Outcome: | The proposed model outperforms existing models on MSMARCO, Natural Questions and TriviaQA datasets and achieves the new state-of-the-art on these datasets. |
Self-contradictory reasoning evaluation and detection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown impressive reasoning ability, but many downstream reasoning tasks focus on performance-wise evaluation. |
| Approach: | They define and assess the Self-Contra rate across three datasets and delve into finer-grained categories of Self-contra reasoning. |
| Outcome: | The proposed model can detect self-contra reasoning with a 52.2% F1 score, much lower than for humans. |
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 . |
Agri-CM3: A Chinese Massive Multi-modal, Multi-level Benchmark for Agricultural Understanding and Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks lack comprehensive evaluations, particularly in multi-level reasoning, making it difficult to identify model limitations. |
| Approach: | They propose to use Agri-CM3 to assess multi-level reasoning in agricultural management by integrating multiple data modalities. |
| Outcome: | The Agri-CM3 benchmark includes 3,939 images and 15,901 multi-level multiple-choice questions with detailed explanations. |
Scaling Parameter-Constrained Language Models with Quality Data (2024.emnlp-industry)
Copied to clipboard
Ernie Chang, Matteo Paltenghi, Yang Li, Pin-Jie Lin, Changsheng Zhao, Patrick Huber, Zechun Liu, Rastislav Rabatin, Yangyang Shi, Vikas Chandra
| Challenge: | Scaling laws in language modeling quantify training loss as a function of dataset size and model parameters, but neglect the critical role of data quality in model generalization. |
| Approach: | They propose to use effective training tokens as a combination of text diversity and syntheticity as measured by a teacher model to calculate scaling laws. |
| Outcome: | The proposed term effective training tokens is a combination of two readily-computed indicators of text diversity and syntheticity as measured by a teacher model. |
Multi-Domain Neural Machine Translation with Word-Level Domain Context Discrimination (D18-1)
Copied to clipboard
| Challenge: | Experimental results on Chinese-English and English-French multi-domain translation tasks demonstrate the effectiveness of the proposed model. |
| Approach: | They propose to use mixed-domain parallel sentences to construct a unified model that allows translation to switch between different domains. |
| Outcome: | The proposed model distinguishes and exploits word-level domain contexts on Chinese-English and English-French translation tasks. |
PresentAgent: Multimodal Agent for Presentation Video Generation (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing methods for generating static slides or text summaries are limited to producing narrated presentations. |
| Approach: | They propose a multimodal agent that transforms long-form documents into narrated presentations. |
| Outcome: | The present agent produces fully synchronized visual and spoken content that closely mimics human-style presentations. |
Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains (2025.acl-long)
Copied to clipboard
| Challenge: | Knowledge graphs are a useful tool for organizing complex data in knowledge-intensive domains. |
| Approach: | They propose an expandable framework that combines structured domain texts with advanced semantic techniques to create a tree-like graph from textbooks. |
| Outcome: | The proposed framework surpasses competing methods in the text-Annotated dataset with high scores on the Text-Annalytated data. |
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing reward models assume a global reward function, limiting personalization and pluralistic alignment. |
| Approach: | They propose a framework that leverages binary preference datasets to enhance personalized preference learning. |
| Outcome: | The proposed framework captures diverse human preferences without fine-grained annotations and significantly improves personalized preference learning on downstream tasks. |
Hebbian-Guided Bi-Directional Rank Adaptation for Parameter-Efficient Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) is a widely used method to fine-tune large language models . but its fixed-rank design cannot capture the varying importance across different layers . |
| Approach: | They propose a framework that bi-directionally reallocates low-rank capacity using Hebbian-inspired importance estimation. |
| Outcome: | Experiments show that HeBiRA improves performance over baselines. |
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models (2025.acl-long)
Copied to clipboard
Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | Recent code large language models have demonstrated impressive performance on code-related tasks. |
| Approach: | They propose a paradigm that learns from expert battles to address these limitations . they create an arena where leading LLMs challenge each other with evaluations . |
| Outcome: | The proposed model improves on existing models by leveraging expert battles . it achieves state-of-the-art performance even without relying on proprietary models . |
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)
Copied to clipboard
Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei
| Challenge: | Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning. |
| Approach: | They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios. |
| Outcome: | The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics. |
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. |
Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)
Copied to clipboard
Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li
| Challenge: | Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization . |
| Approach: | They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume. |
| Outcome: | Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency. |
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. |
Enhancing Neural Topic Model with Multi-Level Supervisions from Seed Words (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing topic seed words are difficult to incorporate into topic models due to the semantic diversity of natural language. |
| Approach: | They propose a neural topic model enhanced with supervisions from seed words on word and document levels. |
| Outcome: | The proposed model outperforms the state-of-the-art seeded topic models in terms of topic quality and classification accuracy. |
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition (2025.coling-main)
Copied to clipboard
Yuming Yang, Wantong Zhao, Caishuang Huang, Junjie Ye, Xiao Wang, Huiyuan Zheng, Yang Nan, Yuran Wang, Xueying Xu, Kaixin Huang, Yunke Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current Large Language Models struggle with complex entity taxonomies in open domains and lack NER capabilities. |
| Approach: | They propose a dataset to guide LLMs' generalization in Open NER under a universal entity taxonomy. |
| Outcome: | The proposed model outperforms GPT-4 in 3 out-of-domain benchmarks across 15 datasets and 6 languages. |
SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflage (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made safety issues of LLMs more prominent and critical. |
| Approach: | They propose a framework which attacks LLMs through semantic camouflage and replaces unsafe content with semantic features to conceal malicious intent . |
| Outcome: | The proposed framework outperforms existing models in over 80% of cases and is highly effective against various defenses. |
Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence (2024.findings-acl)
Copied to clipboard
| Challenge: | Emotional Intelligence (EI) is a key concept in the field of human intelligence. |
| Approach: | They propose a method to enhance EI of large language models by naive fine-tuning on EI-related tasks. |
| Outcome: | The proposed method improves EI of two LLM-based assistants without compromising GI. |
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing models for multimodal sentiment analysis are limited in their capacity to be deployed in the real world. |
| Approach: | They propose a model that can dynamically refine erroneous sentiment words by leveraging multimodal sentiment clues. |
| Outcome: | The proposed model surpasses the state-of-the-art models on three datasets. |
ReLearn: Unlearning via Learning for Large Language Models (2025.acl-long)
Copied to clipboard
Haoming Xu, Ningyuan Zhao, Liming Yang, Sendong Zhao, Shumin Deng, Mengru Wang, Bryan Hooi, Nay Oo, Huajun Chen, Ningyu Zhang
| Challenge: | Existing methods for unlearning large language models often rely on reverse optimization to reduce target token probabilities. |
| Approach: | They propose a data augmentation and fine-tuning pipeline for effective unlearning . they propose augmentation, evaluation frameworks to measure contextual forgetting . |
| Outcome: | The proposed framework achieves targeted forgetting while preserving high-quality outputs. |
Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Knowledge-based visual reasoning (KB-VR) is a challenging task, as it requires machines not only to understand concepts and relationships of visual scenes, but also to associate them with external world knowledge to perform chain of reasoning on open-world questions. |
| Approach: | They propose a visual knowledge card (VKC) that integrates internal visual knowledge and external world knowledge produced by a knowledge generator into an image. |
| Outcome: | The proposed model achieves new state-of-the-art results compared to previous top-performing models on three popular KB-VR benchmarks. |
Knowledge Boundary of Large Language Models: A Survey (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) store vast amount of knowledge in their parameters, but they still have limitations in the memorization and utilization of certain knowledge. |
| Approach: | They propose a comprehensive definition of the LLM knowledge boundary and introduce a formalized taxonomy categorizing knowledge into four distinct types. |
| Outcome: | The proposed definition of the LLM knowledge boundary and taxonomy categorizes knowledge into four distinct types . aims to offer a comprehensive overview, facilitate access to key issues, and inspire further advancements in LLM research. |
RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)
Copied to clipboard
Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang
| Challenge: | Existing benchmarks for large language models focus on simple, flat table structures. |
| Approach: | They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG. |
| Outcome: | The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG. |
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)
Copied to clipboard
Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths. |
| Approach: | They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO. |
| Outcome: | The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages. |
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to evaluate open domain dialogues have a one-to-many problem . existing approaches lack commonsense reasoning biases and perform poorly in domain-specific scenarios. |
| Approach: | They propose a framework that leverages both a small, specialised model and LLMs for the evaluation of open-domain dialogues. |
| Outcome: | The proposed framework achieves state-of-the-art performance in both classification and evaluation tasks and exhibits better correlation with human judgements. |
PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor (2026.findings-acl)
Copied to clipboard
Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, JingYuan Zhao, Qin Chen, Ningning Zhou, Kai Chen, Liang He
| Challenge: | Existing models focus on a single therapy, but complex cases require flexible strategies among various therapies. |
| Approach: | They propose a multi-session, multi-therapy, and highly realistic benchmark . it is designed to address three key challenges: 1) can we train a highly realistic AI counselor? 2) How to systematically evaluate an AI counselor?" |
| Outcome: | The proposed benchmark is annotated with extensive professional skills and includes over 677 meta-skills and 4577 atomic skills. |
Visual Prompt Tuning for Few-Shot Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work on pretraining models for text classification uses image encoders instead of visual prompts. |
| Approach: | They propose a method to deploy large-scale pre-trained models in the prompt-tuning paradigm in few-shot learning. |
| Outcome: | The proposed method outperforms the most recent prompt-tuning methods on five public text classification datasets. |
TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph (2022.coling-1)
Copied to clipboard
| Challenge: | Existing target-oriented dialogs take a local and greedy strategy for response generation, where global planning is absent. |
| Approach: | They propose a global planning method for target-oriented dialog on a commonsense knowledge graph to adjust local response generation towards the global target. |
| Outcome: | The proposed method can reach the target with a higher success rate, fewer turns, and more coherent responses. |
Guess Me if You Can: Acronym Disambiguation for Enterprises (P18-1)
Copied to clipboard
| Challenge: | Acronyms are abbreviations formed from the initial components of words or phrases . acronyms can be difficult to understand for people who are not familiar with the subject matter . |
| Approach: | They propose a framework to automatically resolve the true meanings of acronyms in a given context . they use the enterprise corpus as input and a high-quality acronym disambiguation system as output . |
| Outcome: | The proposed framework can be deployed to any enterprise to support acronym disambiguation. |
Adversarial Knowledge Stimulated Contrastive Prompting for Few-shot Language Learners (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompt-based fine-tuning has boosted performance of Pre-trained language models on few-shot Natural Language Understanding (NLU) tasks by employing task-specific prompts. |
| Approach: | They propose a Cloze-driven prompt framework for prompt tuning that implicitly stimulates knowledge from pre-trained language models. |
| Outcome: | The proposed framework outperforms state-of-the-art for prompt-based fine-tuning on few-shot NLU tasks. |
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy (2026.acl-industry)
Copied to clipboard
| Challenge: | Reasoning LLMs often spend tokens on long intermediate reasoning traces when solving new problems. |
| Approach: | They propose to store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration and retrieve these skills at inference time to guide future reasoning. |
| Outcome: | The proposed approach reduces reasoning tokens while improving overall performance on coding and mathematical reasoning tasks. |
Structure-Discourse Hierarchical Graph for Conditional Question Answering on Long Documents (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to conditional question answering on long documents ignore document structure and discourse relations between sentences in document sections. |
| Approach: | They construct a Structure-Discourse Hierarchical Graph and conduct bottom-up information propagation to address this issue. |
| Outcome: | The proposed approach outperforms the existing methods on the conditional question answering on long documents by 3.0 EM score and 2.4 F1 score on answer measuring, and 2.2 EM and 1.9 F1 scores on jointly answer and condition measuring. |
CMMLU: Measuring massive multitask language understanding in Chinese (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models struggle to achieve an accuracy of even 60%, which is the pass mark for Chinese exams. |
| Approach: | They propose to use CMMLU to evaluate Chinese multilingual and Chinese LLMs in a comprehensive benchmark that covers various subjects and settings. |
| Outcome: | The proposed benchmark covers natural sciences, social sciences, engineering, and the humanities and aims to improve on existing models. |
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay (2024.emnlp-main)
Copied to clipboard
Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang
| Challenge: | Existing studies on LLM agents' social behaviors are lacking . previous studies focused on positive social behaviors, leaving research on negative social behaviors relatively scarce. |
| Approach: | They propose a framework that features a multi-agent system facilitating efficient communication and interaction with LLM agents. |
| Outcome: | The proposed framework is based on Avalon and evaluates on game success and analyzes agents’ social behaviors. |
Rethinking Token Reduction for State Space Models (2024.emnlp-main)
Copied to clipboard
Zheng Zhan, Yushu Wu, Zhenglun Kong, Changdi Yang, Yifan Gong, Xuan Shen, Xue Lin, Pu Zhao, Yanzhi Wang
| Challenge: | Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% . |
| Approach: | They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging. |
| Outcome: | The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements. |
Improving Low-resource Question Answering by Augmenting Question Information (2023.findings-emnlp)
Copied to clipboard
Andong Chen, Yuan Sun, Xiaobing Zhao, Rosella Galindo Esparza, Kehai Chen, Yang Xiang, Tiejun Zhao, Min Zhang
| Challenge: | Low-resource questions pose a significant challenge within the field of Question-Answering (QA) tasks. |
| Approach: | They propose a method that leverages large models' internal knowledge to enhance the quality of augmented data by Prompt Answer, Question Generation, and Question Filter. |
| Outcome: | The proposed method outperforms existing augmentation strategies on high-resource QA tasks like SQUAD1.1 and TriviaQA. |
Table-R1: Region-based Reinforcement Learning for Table Understanding (2026.findings-acl)
Copied to clipboard
Zhenhe Wu, Jian Yang, Zhongjiang He, Changzai Pan, Jiaheng Liu, Xianjie Wu, Yu Zhao, Shuangyong Song, Yongxiang Li, Zhoujun Li, Xuelong Li
| Challenge: | Tables are a widely used data format that poses unique challenges for language models due to their structured row-column interactions. |
| Approach: | They propose a region-based reinforcement learning approach that integrates region evidence into reasoning steps. |
| Outcome: | The proposed method outperforms baseline models on three benchmark datasets and significantly reduces the reasoning token consumption by 67.5%. |
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2026.findings-acl)
Copied to clipboard
Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu
| Challenge: | Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning from large language models (LLMs). |
| Approach: | They propose a data distribution lens to understand when and why CoT reasoning fails . they propose 'data-based' training that trains LLMs from scratch . |
| Outcome: | The proposed model enables models to generate reasoning trajectories that approximate those observed during training. |
GCPG: A General Framework for Controllable Paraphrase Generation (2022.findings-acl)
Copied to clipboard
Kexin Yang, Dayiheng Liu, Wenqiang Lei, Baosong Yang, Haibo Zhang, Xue Zhao, Wenqing Yao, Boxing Chen
| Challenge: | Existing studies highlight a special condition under two indispensable aspects of controllable paraphrase generation (CPG) individually, lacking a unified circumstance to explore and analyze their effectiveness. |
| Approach: | They propose a general controllable paraphrase generation framework that integrates lexical and syntactical conditions into a text sequence and uniformly processes them in an encoder-decoder paradigm. |
| Outcome: | The proposed framework can combine lexical and syntactical conditions and improve paraphrase generation. |
AD-LLM: Benchmarking Large Language Models for Anomaly Detection (2025.findings-acl)
Copied to clipboard
Tiankai Yang, Yi Nian, Li Li, Ruiyao Xu, Yuangang Li, Jiaqi Li, Zhuo Xiao, Xiyang Hu, Ryan A. Rossi, Kaize Ding, Xia Hu, Yue Zhao
| Challenge: | Anomaly detection (AD) is an important machine learning task with many real-world uses, including fraud detection, medical diagnosis, and industrial monitoring. |
| Approach: | They propose a benchmark that evaluates how large language models (LLMs) can help with NLP anomaly detection. |
| Outcome: | The proposed model can perform zero-shot detection without tasks-specific training, data augmentation and model selection, and it can suggest unsupervised AD models. |
Learning to Rewrite: Generalized LLM-Generated Text Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Existing detectors for Large Language Models (LLMs) struggle to generalize in open-world settings. |
| Approach: | They propose a framework to detect LLM-generated text with exceptional generalization to unseen domains by reinforcing LLMs’ inherent rewriting tendencies. |
| Outcome: | The proposed framework outperforms state-of-the-art detection methods by 23.04% in AUROC, 35.10% for out-of distribution tests, and 48.66% under adversarial attacks. |
Data Diversity Matters for Robust Instruction Tuning (2024.findings-emnlp)
Copied to clipboard
Alexander Bukharin, Shiyang Li, Zhengyang Wang, Jingfeng Yang, Bing Yin, Xian Li, Chao Zhang, Tuo Zhao, Haoming Jiang
| Challenge: | Recent studies have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities. |
| Approach: | They propose an algorithm to control diversity and quality of instruction tuning datasets and validate it. |
| Outcome: | The proposed algorithm significantly improves worst and average case performance on large scale instruction tuning datasets. |
Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)
Copied to clipboard
Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao
| Challenge: | Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications. |
| Approach: | They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions. |
| Outcome: | The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions. |
PAPERMIND: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs (2026.findings-acl)
Copied to clipboard
Yanjun Zhao, Tianxin Wei, Jiaru Zou, Xuying Ning, Yuanchen Bei, Lingjie Chen, Simmi Rana, Wendy H. Yang, Hanghang Tong, Jingrui He
| Challenge: | Existing benchmarks assess integrated and agent-oriented scientific reasoning in isolation . Existing systems assess integrated reasoning in isolated tasks . |
| Approach: | They propose a benchmark to evaluate integrated and agent-oriented scientific reasoning over research papers. |
| Outcome: | The proposed benchmark evaluates integrated and agent-oriented scientific reasoning over scientific papers. |
Bloom-Eval: A Hierarchical Evaluation Benchmark for Automatic Survey Generation Based on Bloom’s Taxonomy (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods suffer from cognitive dimensional simplification and methodological unreliability due to the ”LLM-as-a-Judge” approach. |
| Approach: | They propose a six-tiered benchmark that evaluates ASG systems by prioritizing deterministic algorithms and introducing a GRADE approach for abstract abilities. |
| Outcome: | The proposed method provides the ASG field with a systematic, reproducible, and theoretically grounded benchmark to guide future research. |
MuG: A Multimodal Classification Benchmark on Game Data with Tabular, Textual, and Visual Fields (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multimodal classification systems use tabular, textual, and visual data to provide efficient and scalable services. |
| Approach: | They propose a multimodal classification benchmark MuG with eight datasets . they analyze label balance ratios, percentages of missing features, distributions of data within each modality . |
| Outcome: | The proposed benchmark is available on https://github.com/lujiaying/MUG-Bench . it includes eight datasets that allow researchers to evaluate and improve their models . |
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging (2024.emnlp-main)
Copied to clipboard
Deyuan Liu, Zhanyue Qin, Hairu Wang, Zhao Yang, Zecheng Wang, Fangying Rong, Qingbin Liu, Yanchao Hao, Bo Li, Xi Chen, Cunhang Fan, Zhao Lv, Dianhui Chu, Zhiying Tu, Dianbo Sui
| Challenge: | Existing methods for parameter pruning fail to utilize the knowledge from pruned parameters. |
| Approach: | They propose a method that uses manifold learning and the Information Bottleneck measure to merge similar layers to preserve model performance. |
| Outcome: | The proposed method outperforms pruning methods on multiple datasets and LLMs with quantization and achieves substantial compression ratios. |
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)
Copied to clipboard
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
| Challenge: | Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood. |
| Approach: | They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction . |
| Outcome: | The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones . |
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for complex instruction-following with elaborate constraints rely on a weaker model, especially GPT-4, limiting their application. |
| Approach: | They propose a Multi-granularity Self-Contrastive Training framework to improve instruction alignment without relying on a stronger model. |
| Outcome: | The proposed framework improves instruction-following with elaborate constraints without external supervision on coarse and fine granularity. |
Does Visual Grounding Enhance the Understanding of Embodied Knowledge in Large Language Models? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Despite significant progress in multimodal language models, it remains unclear whether visual grounding enhances their understanding of embodied knowledge compared to text-only models. |
| Approach: | They propose to assess vision-language models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions. |
| Outcome: | The proposed benchmark assesses the models’ perceptual abilities across different sensory modalities through vector comparison and question-answering tasks with over 1,700 questions. |
Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | State-of-the-art vision-language models require massive scaling that limits practical deployment. |
| Approach: | They propose to use supervised fine-tuning to train small-scale vision-language models but face out-of-domain collapse when trained with traditional supervised learning (SFT). |
| Outcome: | Experiments show that curr-reFT achieves state-of-the-art performance across visual tasks in both in- and out-of domain settings and benchmarks. |
Improving Zero-shot LLM Re-Ranker with Risk Minimization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are effective Query Likelihood Models, but their estimation is biased and the model's accuracy is poor. |
| Approach: | They propose a framework which leverages Bayesian decision theory to quantify and mitigate this bias. |
| Outcome: | The proposed framework improves re-ranking, especially in improving the Top-1 accuracy. |
Imagination and Contemplation: A Balanced Framework for Semantic-Augmented Multimodal Machine Translation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal Machine Translation (MMT) is effective in resolving linguistic ambiguities, but visual information often introduces redundancy or noise, potentially impairing translation quality. |
| Approach: | They propose a semantic-augmented framework that integrates "Imagination" and "Contemplation" they first generate synthetic images from source text and align them with authentic images via an optimal transport loss . |
| Outcome: | The proposed framework outperforms baselines on translation datasets with visually ambiguous or weakly correlated content. |
Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media (2025.emnlp-main)
Copied to clipboard
| Challenge: | Digital media platforms often contribute to cognitive-behavioral fixation, a phenomenon in which users exhibit sustained and repetitive engagement with narrow content domains. |
| Approach: | They propose a multimodal topic extraction module and a cognitive-behavioral fixation quantification module that collaboratively enable adaptive, hierarchical, and interpretable assessment of user behavior. |
| Outcome: | The proposed framework lays the groundwork for scalable computational analysis of cognitive fixation. |
Tailored Primitive Initialization is the Secret Key to Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) has emerged as a powerful paradigm for improving the reasoning capabilities of large language models. |
| Approach: | They propose a pipeline that automatically discovers thinking token patterns with reasoning primitives and curates SFT datasets to prepare LLMs for RL. |
| Outcome: | The proposed pipeline outperforms baseline methods on mathematical and logical reasoning benchmarks on RL tasks. |
Iterative Nearest Neighbour Machine Translation for Unsupervised Domain Adaptation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for supervised domain adaptation of machine translation focus on fine-tuning, which is non-extensible. |
| Approach: | They propose to perform unsupervised domain adaptation in a non-parametric manner by using in-domain monolingual data and performing nearest neighbour inference on both forward and backward directions. |
| Outcome: | The proposed method significantly improves the in-domain translation performance and achieves state-of-the-art results among non-parametric methods. |
Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to solve non-deterministic reasoning problems in large language models are limited by their complexity and lack of a clear understanding of the problem. |
| Approach: | They propose a method to diagnose and correct non-deterministic reasoning behaviors in large language models. |
| Outcome: | The proposed method outperforms baselines and WebQSP benchmarks on the widely used WebQ SP and CWQ benchmarks. |
LLM-Driven Multi-Perspective Location Completion for Next Location Prediction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods assume that check-in data is complete, overlooking the subjective nature of user behavior, leading to inaccurate capture of user preferences. |
| Approach: | They propose a framework that uses spatial coordinates to augment location completion by transforming geographic coordinates into text. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on three real-world datasets. |
Attack Named Entity Recognition by Entity Boundary Interference (2024.lrec-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a cornerstone natural language processing task . despite its robustness, studies on its robustity are lacking. |
| Approach: | They propose a one-word modification NER attack that strategically inserts a new boundary into the sentence and triggers the model to make a wrong recognition. |
| Outcome: | The proposed method is effective on English and Chinese models with 70%-90% success rate. |
A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing training paradigms for dialogue policy learning with brute-force random sampling are expensive and lack reliable evaluation of difficulty scores. |
| Approach: | They propose a flexible adaptive curriculum learning framework that integrates curriculum learning with a generic global curriculum. |
| Outcome: | The proposed framework improves learning performance and efficiency on three public dialogue datasets. |
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks. however, their extensive memory requirements present significant challenges for deployment in resource-constrained environments. |
| Approach: | They propose a training-free framework that achieves ultra-low equivalent bit-width KV cache quantization. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on TruthfulQA and LongBench. |
Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained language models overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions. |
| Approach: | They propose a low-parameters Prompt Tuning method which leverages prompt decomposition and compressed outer product to facilitate multiple interactions among prompt tokens. |
| Outcome: | Experiments on six architectures and eight datasets show that the proposed method outperforms state-of-the-art methods in performance and efficiency. |
CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) offer promising avenues for automated cognitive restructuring in mental health settings, but current approaches lack the adaptability to balance conflicting therapeutic dimensions, such as empathy and rationality. |
| Approach: | They propose a decoupled optimization framework that implements a dimension-guided Monte Carlo tree search to train expert policies specialized for distinct therapeutic attributes rather than relying on a monolithic alignment strategy. |
| Outcome: | The proposed framework achieves consistent improvements over baselines across multiple evaluation dimensions, including diagnostic accuracy, contextual appropriateness, task effectiveness, and overall helpfulness, while enabling controllable cognitive restructuring generation. |
Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer Enhancement (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to enhance the context-faithfulness of Large Language Models (LLMs) ignore the fundamental mechanism of how contextual information is processed within LLMs’ internal states. |
| Approach: | They propose a method that enhances the utilization of contextual knowledge within LLMs’ internal representations by employing V-usable information analysis. |
| Outcome: | The proposed method improves context-faithfulness generation in Question-Answering tasks, particularly in scenarios involving unknown or conflicting contextual knowledge. |
Exploiting Pre-Ordering for Neural Machine Translation (L18-1)
Copied to clipboard
| Challenge: | Existing studies have shown that Neural Machine Translation suffers from the problems that some source words are mistakenly translated for multiple times . |
| Approach: | They propose a pre-ordering approach to solve the under-translation problem by pre-ordnanced source sentences and position embedding to enhance monotone translation. |
| Outcome: | The proposed method significantly improves translation quality by 2.43 BLEU points on Chinese-to-English translation. |
Rethinking Data Mixing from the Perspective of Large Language Models (2026.acl-short)
Copied to clipboard
Yuanjian Xu, Tianze Sun, Changwei Xu, XinLong Zhao, Jianing Hao, Ran Chen, Yang Liu, Ruijie Xu, Stephen Chen, Guang Zhang
| Challenge: | Existing methods to mix data with LLMs have relied on domain definitions derived from intuition. |
| Approach: | They propose a reweighting framework that restructures data scheduling as a graph-constrained optimization problem. |
| Outcome: | The proposed framework achieves competitive performance on GPT-2 models. |
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences. |
| Approach: | They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles. |
| Outcome: | The proposed method improves performance across reward objectives and targets. |
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. |
Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator (D19-1)
Copied to clipboard
| Challenge: | Modern pointer generators only capture exact word matches, ignoring possible inflections or abstractions, which restricts its power of capturing richer latent alignment. |
| Approach: | They propose a pointer generator architecture that allows the model to "edit" pointed tokens instead of always copying them. |
| Outcome: | The proposed model captures more latent alignment relations than exact word matches and generates higher-quality summaries validated by both qualitative and quantitative evaluations. |
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation (2025.findings-acl)
Copied to clipboard
Xinglin Lyu, Wei Tang, Yuang Li, Xiaofeng Zhao, Ming Zhu, Junhui Li, Yunfei Lu, Min Zhang, Daimeng Wei, Hao Yang, Min Zhang
| Challenge: | Document-level context is crucial for speech translation due to noise from ASR . incorporating document-level contextual information into ST remains a challenge . |
| Approach: | They develop an online framework that integrates document-level context into machine translation . they use document-based modules to integrate document- level context into ST . |
| Outcome: | The proposed framework outperforms baselines in sentence and discourse metrics . it can correct ASR transcription errors and improve translation performance . |
ConReader: Exploring Implicit Relations in Contracts for Contract Clause Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing CCE methods treat contracts as plain text, creating a barrier to understanding complex contracts. |
| Approach: | They propose a framework to model implicit relations in legal contracts to improve contract understanding . they propose Term-Definition Relation captures the relation between important terms and their definitions . |
| Outcome: | The proposed framework improves on two CCE tasks in conventional and zero-shot settings. |
Face-Sensitive Image-to-Emotional-Text Cross-modal Translation for Multimodal Aspect-based Sentiment Analysis (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models focus on utilizing semantic information in the image but ignore using visual emotional cues. |
| Approach: | They propose a face-sensitive image-to-emotional-text translation method that captures visual emotional cues through facial expressions and selectively matches and fuses with the textual content. |
| Outcome: | The proposed method achieves state-of-the-art results on the Twitter-2015 and Twitter-2017 datasets. |
Improve Neural Entity Recognition via Multi-Task Data Selection and Constrained Decoding (N18-2)
Copied to clipboard
| Challenge: | Entity recognition is a widely benchmarked task in natural language processing . a neural architecture called BiLSTM-CRF is used to model the language sequences . |
| Approach: | They propose a neural architecture called BiLSTM-CRF to model the language sequences. |
| Outcome: | The proposed system achieves state-of-the-art on English entity recognition task and also in other languages. |
Triviality Corrected Endogenous Reward (2026.acl-long)
Copied to clipboard
Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao
| Challenge: | Recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards focuses on open-ended text generation, requiring either annotated data or powerful closed-source models. |
| Approach: | They propose a method that rewards the relative information gain between a specialist and a generalist reference policy, modulated by a probability-dependent correction mechanism. |
| Outcome: | The proposed model improves on multiple writing benchmarks and model architectures without external supervision and validates generality across different generation tasks. |
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. |
Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models acquire general knowledge from pretraining but pretraining data contain undesirable social biases which can be perpetuated or even amplified by LLMs. |
| Approach: | They propose an efficient yet effective annotation pipeline to investigate social biases in pretraining data. |
| Outcome: | The proposed pipeline investigates social biases in the pretraining corpus using protected attribute detection and regard classification. |
YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)
Copied to clipboard
Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen
| Challenge: | prevailing pre-training approaches for large language models involve several complexities. |
| Approach: | They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data . |
| Outcome: | The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data . |
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing evaluation methods for document summarization require human annotations and annotations. |
| Approach: | They propose a method which measures the quality of a summary by measuring its semantic similarity with a pseudo reference summary, using contextualized embeddings and soft token alignment techniques. |
| Outcome: | The proposed method correlates better with human ratings by 18- 39% compared to the state-of-the-art evaluation metrics. |
ICL-Bandit: Relevance Labeling in Advertisement Recommendation Systems via LLM (2025.findings-emnlp)
Copied to clipboard
Lu Wang, Chiming Duan, Pu Zhao, Fangkai Yang, Yong Shi, Xuefeng Luo, Bingjing Xu, Weiwei Deng, Qingwei Lin, Dongmei Zhang
| Challenge: | In-context learning (ICL) is a common practice to enhance LLM performance on domain-specific tasks. |
| Approach: | They propose a method that leverages large language models to enhance query-ad relevance labeling . they identify and provide superior demonstrations for ICL, thereby improving labeling performance . |
| Outcome: | The proposed method improves query-ad relevance labeling performance by providing demonstrations. |
ProMediate: A Simulation Testbed for Evaluating Proactive Mediation in Multi-Party Negotiation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly integrated into agentic frameworks to assist individual users in completing diverse tasks. |
| Approach: | They propose a simulation environment with a plug-and-play proactive AI mediator . they use a socio-cognitive evaluation framework to measure consensus changes, intervention latency, mediator effectiveness and intelligence. |
| Outcome: | The proposed model outperforms a generic baseline in multi-party negotiation scenarios while being 77% faster in response. |
Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)
Copied to clipboard
Bohan Li, Jiannan Guan, Longxu Dou, Yunlong Feng, Dingzirui Wang, Yang Xu, Enbo Wang, Qiguang Chen, Bichen Wang, Xiao Xu, Yimeng Zhang, Libo Qin, Yanyan Zhao, Qingfu Zhu, Wanxiang Che
| Challenge: | Existing data on MBTI personality detection are based on self-reported labels and fail to capture the full range of population personality traits. |
| Approach: | They construct a manually annotated MBTI personality detection dataset with soft labels under the guidance of psychologists and use them to identify the task. |
| Outcome: | The MBTIBench is the first manually annotated MBti personality detection dataset with soft labels under the guidance of psychologists. |
Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems (2020.coling-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics are not designed to cope with this flexibility. |
| Approach: | They propose to group the qualities into three groups to obtain a single metric called USL-H. |
| Outcome: | The proposed metric achieves good correlations with human judgment and maintains its configurability towards different aspects and metrics. |
Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Aligned Large Language Models exhibit remarkable versatility, capable of handling diverse real-world tasks. |
| Approach: | They propose a coarse to fine framework to fine-tune aligned Large Language Models to achieve a balance between speciality and versatility. |
| Outcome: | The proposed framework outperforms baseline methods across diverse tasks and model scales. |
FaiMA: Feature-aware In-context Learning for Multi-domain Aspect-based Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for aspect-based sentiment analysis are limited and integrating with existing techniques is difficult. |
| Approach: | They propose a framework that utilizes in-context learning as a feature-aware mechanism that facilitates adaptive learning in multi-domain ABSA tasks. |
| Outcome: | The proposed framework achieves significant performance improvements in multiple domains compared to baselines, increasing F1 by 2.07% on average. |
CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting code capture the overall semantics of the code rather than its intrinsic vulnerability-specific semantics. |
| Approach: | They propose an approach that leverages contrastive learning to generate precise vulnerability code representations under the supervision of vulnerability descriptions. |
| Outcome: | The proposed approach outperforms state-of-the-art methods in vulnerability detection tasks by 11.85% and 13.61%. |
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluation of dialog systems are expensive and not scalable . a framework for estimating human evaluation scores is proposed to bridge this gap . |
| Approach: | They propose a framework for estimating human evaluation scores based on off-policy evaluation . they use language quality metrics for single-turn response generation given a fixed context . |
| Outcome: | The proposed framework outperforms existing methods in terms of correlation with human evaluation scores. |
REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Empathy relies on the cognitive capacity to relate to similar past experiences. Existing methods prioritize semantic similarity over emotion characteristics, leading to unempathetic responses. |
| Approach: | They propose a framework that integrates four Emotion Attributes into the retrieval process to ensure explicit emotional alignment. |
| Outcome: | Empirical results show that REG significantly outperforms baselines, offering a robust solution for empathetic generation. |
VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery (2026.findings-eacl)
Copied to clipboard
Jinchao Ge, Tengfei Cheng, Biao Wu, Zeyu Zhang, Shiya Huang, Judith Bishop, Gillian Shepherd, Meng Fang, Ling Chen, Yang Zhao
| Challenge: | MLLMs that use domain-specific data are limited in understanding cultural heritage artifacts such as ancient Greek pottery . supervised fine-tuning improves adaptation to domain knowledge, but it struggles with deeper reasoning tasks. |
| Approach: | They propose a visual question-answer tool that augments SFT with reinforcement learning using verifiable rewards. |
| Outcome: | The proposed model outperforms baseline models on reasoning-intensive questions on ancient Greek pottery. |
A Text-Centered Shared-Private Framework via Cross-Modal Prediction for Multimodal Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies treat all three modal features equally and implicitly explore the interactions between different modalities. |
| Approach: | They propose a text-centered shared-private framework for multimodal fusion . they propose modalities that can provide shared and private semantics . |
| Outcome: | The proposed framework outperforms baselines on the MOSEI and MOSI datasets. |
Demystifying Data Organization for Enhanced LLM Training (2026.acl-long)
Copied to clipboard
Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang, Xin Zhang, Wenshan Wu, Qihao Zhao, Hao Li, Yuanyuan Gao, Kim-Hui Yap, Scarlett Li
| Challenge: | Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. |
| Approach: | They propose to reuse pre-computed sample-level scores originally generated for data efficiency and introduce two new data ordering methods to improve LLM training. |
| Outcome: | The proposed methods improve the stability and performance of LLM training. |
Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have demonstrated remarkable performance on few-shot Named Entity Recognition tasks due to the high cost of obtaining high-quality labeled data. |
| Approach: | They propose to decompose the task into entity span detection and entity type classification using a type-independent entity span detector and then classify the detected spans based on their types. |
| Outcome: | The proposed method consistently yields improvements over two baseline approaches. |
Investigating Capsule Networks with Dynamic Routing for Text Classification (D18-1)
Copied to clipboard
| Challenge: | Earlier efforts in text modeling have achieved limited success on word meanings . convolutional neural networks (CNNs) are used to model higher level concepts and facts in texts . |
| Approach: | They propose three strategies to stabilize dynamic routing process to alleviate disturbance of noise capsules. |
| Outcome: | The proposed methods achieve state-of-the-art on 4 out of 6 datasets . they show that capsule networks exhibit significant improvement over baseline methods . |
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Traditional Video Quality Assessment (VQA) focuses on aesthetic fidelity and technical distortions. |
| Approach: | They propose a new task that evaluates whether a UGC item has positive community resonance based on multimodal attributes rather than visual quality alone. |
| Outcome: | The proposed task outperforms state-of-the-art baselines on CASTER-Bench . it provides interpretable and empathetic reasoning paths that align with real community feedback. |
Web Sitemap Knowledge Can Enhance Autonomous Browsing (2026.findings-acl)
Copied to clipboard
Yuyao Zhang, Hongyu Lu, Jiajie Jin, Hongjin Qian, Shiyu Li, Zhao Yang, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou
| Challenge: | Existing web agents suffer from limited robustness, efficiency and task success due to lack of structural understanding of websites and lack of browsing priors in pre-trained models. |
| Approach: | They propose an agent-oriented sitemap protocol that integrates structured website knowledge into web agents. |
| Outcome: | The proposed agent-oriented sitemap improves robustness, efficiency and effectiveness without extra training. |
Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization (2025.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization. |
| Approach: | They propose a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization. |
| Outcome: | The proposed approach extracts inter-user differences to enhance LLM personalization. |
Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference (P18-1)
Copied to clipboard
| Challenge: | Existing approaches to natural language inference focus on interaction architectures of sentences . but, we propose to transfer knowledge from discourse markers to augment the model . |
| Approach: | They propose to transfer knowledge from discourse markers to augment the quality of the NLI model. |
| Outcome: | The proposed method achieves state-of-the-art performance on large-scale datasets. |
HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)
Copied to clipboard
An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu
| Challenge: | Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization. |
| Approach: | They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts . |
| Outcome: | The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters. |
Diversity Helps Jailbreak Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for jailbreaking large language models rely on laborious human engineering and whitebox access to model internals. |
| Approach: | They propose a method that instructs large language models to deviate from prior context and generate harmful outputs by instructing them to deviat from previous attacks. |
| Outcome: | The proposed method achieves a 62.83% higher success rate in compromising ten leading chatbots, while using only 12.9% of the queries. |
A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for document image translation rely on the vanilla encoder-decoder paradigm . a novel dynamic aggregation mechanism is designed to enhance the text semantics in query features toward translation. |
| Approach: | They propose a Query-Response DIT framework that reformulates the DIT task into a parallel response/translation process of multiple queries. |
| Outcome: | The proposed framework improves translation quality on four translation directions on three benchmarks. |
Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extraction (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing ASTE datasets are limited in their ability to represent real-world scenarios, hindering progress in this area. |
| Approach: | They propose a new ASTE dataset that is manually annotated to better fit real-world scenarios by providing more diverse and realistic reviews. |
| Outcome: | The proposed dataset is manually annotated to better fit real-world scenarios. |
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)
Copied to clipboard
Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun
| Challenge: | Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks. |
| Approach: | They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies. |
| Outcome: | The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%. |
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. |
Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for hierarchical text classification are lacking in the field of natural language processing. |
| Approach: | They propose a hierarchy-aware T5 model with path-adaptive attention mechanism to exploit hierarchical dependency across different levels. |
| Outcome: | The proposed model outperforms state-of-the-art models especially in Macro-F1 and low Macro. |
Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching (2025.acl-long)
Copied to clipboard
Jialong Zuo, Shengpeng Ji, Minghui Fang, Mingze Li, Ziyue Jiang, Xize Cheng, Xiaoda Yang, Chen Feiyang, Xinyu Duan, Zhou Zhao
| Challenge: | Existing methods focus on disentangling speakers and content, while others focus on preserving the source's prosody. |
| Approach: | They propose a rhythm-controllable and efficient zero-shot voice conversion model that transforms the source speaker’s timbre into an unseen one while retaining speech content. |
| Outcome: | The proposed model adapts the linguistic content duration to the desired speaking style, facilitating the transfer of the target speaker’s rhythm. |
Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks (2021.emnlp-main)
Copied to clipboard
Qingbin Liu, Pengfei Cao, Cao Liu, Jiansong Chen, Xunliang Cai, Fan Yang, Shizhu He, Kang Liu, Jun Zhao
| Challenge: | Existing offline DST models require a fixed dataset to train . Existing domain-lifelong learning methods are impractical in real-world applications . |
| Approach: | They propose a domain-lifelong learning method to continuously train a DST model on new data to learn incessantly emerging new domains while avoiding catastrophically forgetting old learned domains. |
| Outcome: | The proposed method outperforms state-of-the-art lifelong learning methods by 4.25% and 8.27% on the MultiWOZ and the SGD benchmarks. |
Part Represents Whole: Improving the Evaluation of Machine Translation System Using Entropy Enhanced Metrics (2022.findings-aacl)
Copied to clipboard
| Challenge: | Existing machine translation metrics have poor correlations with human assessments . entropy-based evaluations are often limited to a limited number of samples . |
| Approach: | They propose a fast and unsupervised approach to enhance machine translation metrics using entropy by introducing sentence-level difficulty. |
| Outcome: | The proposed method outperforms existing metrics on five sub-tracks in the WMT19 Metrics shared tasks. |
GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)
Copied to clipboard
Yiyang Zhou, Linjie Li, Shi Qiu, Zhengyuan Yang, Yuyang Zhao, Siwei Han, Yangfan He, Kangqi Li, Haonian Ji, Zihao Zhao, Haibo Tong, Lijuan Wang, Huaxiu Yao
| Challenge: | Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning. |
| Approach: | They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis. |
| Outcome: | The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection. |
ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs’ Capability via Chart Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of multimodal large language models rely on limited case studies . however, they lack the ability to generate accurate edits according to the instructions . |
| Approach: | They propose a benchmark for chart editing that includes 1,405 edit instructions applied to 233 real-world charts. |
| Outcome: | The proposed benchmark includes 1,405 diverse editing instructions applied to 233 real-world charts. |
Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)
Copied to clipboard
Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni
| Challenge: | MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture. |
| Approach: | They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content. |
| Outcome: | The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context. |
Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models (LLMs) have achieved some success, but their knowledge understanding and memory capacity significantly degrades after extensive editing. |
| Approach: | They propose a method that stores the basis vectors of the representation space of past edits in a knowledge cache and projects the gradient of the current edit onto a space orthogonal to previous knowledge for updating. |
| Outcome: | The proposed method improves question-answering ability and hallucination mitigation by 14% and 61% for large language models after 3,000 edits. |
Sign2Vis: Automated Data Visualization from Sign Language (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to translate natural language descriptions into visualization queries focus on spoken languages, not sign languages. |
| Approach: | They propose a sign language interface that enables the DHH community to engage more fully with data analysis. |
| Outcome: | The proposed interface can be used by the deaf and hard-of-hearing community. |
Extremely Small BERT Models from Mixed-Vocabulary Training (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation methods cannot be directly applied to train student models with reduced vocabulary and embedding dimensions. |
| Approach: | They propose a method to align teacher and student embeddings via mixed-vocabulary training. |
| Outcome: | The proposed method compresses BERT-LARGE to a task-agnostic model with smaller vocabulary and hidden dimensions, which is an order of magnitude smaller than other distilled models. |
Representation-Guided Parameter-Efficient LLM Unlearning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to unlearning large language models often memorize sensitive or harmful information, but they struggle with the forget-retain trade-off due to the polysemantic nature of LLMs parameters. |
| Approach: | They propose a representation-guided low-rank unlearning approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning. |
| Outcome: | The proposed approach outperforms state-of-the-art models on TOFU and WMDP benchmarks while maintaining higher model utility. |
Dynamic Planning for LLM-based Graphical User Interface Automation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to planning for GUI tasks are limited due to long historical dialogues. |
| Approach: | They propose a novel approach to dynamic planning based on environmental feedback and execution history to guide action prediction in GUI tasks. |
| Outcome: | The proposed approach surpasses the strong GPT-4V baseline by +12.7% in accuracy. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Document Image Machine Translation (DIMT) faces generalization challenges due to limited training data and the complex interplay between visual and textual information. |
| Approach: | They propose a single-to-mix Modality alignment framework leveraging Multimodal Large Language Models (MLLMs) this framework aligns an imageonly encoder with multimodal representations of an MLLM pre-trained on large-scale document image datasets. |
| Outcome: | The proposed framework improves translation quality in cross-domain generalization and challenging document image scenarios. |
Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving (2025.findings-acl)
Copied to clipboard
| Challenge: | a benchmark for university-level physics problem solving contains 1,297 expert-annotated problems . a proprietary model, o3-mini, achieves only 59.9% accuracy, highlighting fundamental weaknesses in scientific reasoning, conceptual understanding, and mathematical precision. |
| Approach: | They introduce Physics, a benchmark for university-level physics problem solving. |
| Outcome: | The proposed model achieves only 59.9% accuracy on the most advanced model, o3-mini . the proposed model is a powerful tool for evaluating models on advanced problems . |
A Simple-Yet-Efficient Instruction Augmentation Method for Zero-Shot Sentiment Classification (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have used labeled sentiment instances to instruction tune LLMs, improving zero-shot sentiment classification performance. |
| Approach: | They propose a simple-yet-efficient method which does not rely on actual labeled sentiment instances. |
| Outcome: | The proposed method outperforms LLMs tuned with more complex instruction tuning methods by 5.1 points and increases scores by 30 points. |
DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms (2024.acl-short)
Copied to clipboard
| Challenge: | Existing self-reflection methods lack effective feedback information, limiting the translation performance of large language models (LLMs). |
| Approach: | They propose a framework that leverages the dual learning of translation tasks to provide effective feedback, thereby enhancing the models’ self-reflective abilities and improving translation performance. |
| Outcome: | The proposed framework improves the models’ self-reflective abilities and improves translation accuracy and eliminating ambiguities across translation tasks. |
Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing unified optimization strategies overlook the statistical conflict between these distinct gradient signals. |
| Approach: | They propose a framework to reduce bias-variance trade-offs in Large Language Models . they propose DYPO, which leverages intrinsic group dynamics to significantly reduce RL gradient variance . |
| Outcome: | The proposed framework outperforms traditional pipelines on reasoning benchmarks and out-of-distribution tasks. |
ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) are powerful but still suffer from inefficient and off-target reasoning. |
| Approach: | They propose a training-free framework that automatically optimizes Large Reasoning Models' reasoning by generating think-prefixes that evolve driven by a taxonomy of reasoning behaviors. |
| Outcome: | The proposed framework significantly improves accuracy-length trade-off for efficient reasoning, drastically improves safety and improves instruction following. |
UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods such as LoRA and VeRA use a low-rank approximation method that reduces the number of trainable parameters without compromising performance. |
| Approach: | They propose a parameter-efficient fine-tuning approach that leverages a low-rank approximation method that reduces the number of trainable parameters without compromising performance. |
| Outcome: | The proposed approach outperforms existing methods on GLUE and E2E benchmarks and is effective in instruction-tuning large language models and image classification models. |
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension (2024.acl-long)
Copied to clipboard
Qian Yang, Jin Xu, Wenrui Liu, Yunfei Chu, Ziyue Jiang, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Zhou Zhao, Chang Zhou, Jingren Zhou
| Challenge: | Existing benchmarks for audio-centric interaction have impeded advancements in this field . AIR-Bench evaluates LALMs' ability to understand audio signals and interact with humans . |
| Approach: | They propose a benchmark to evaluate the ability of large audio-language models to understand audio signals . they use 19 tasks with approximately 19k single-choice questions to examine single-task ability . |
| Outcome: | The proposed framework evaluates the ability of large audio-language models to understand audio signals and interact with humans in the textual format. |
QAEval: Mixture of Evaluators for Question-Answering Task Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing QA evaluation methods struggle with open-ended and unstructured responses. |
| Approach: | They propose a hybrid framework that combines rule-based reliability with LLM-based adaptability to overcome these challenges. |
| Outcome: | The proposed framework outperforms existing models like GPT-4o and Claude-3 in accuracy and cost. |
DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to domain adaptation only use reliable pseudo instances, i.e., pseudo instances with high prediction confidence, to retrain the model. |
| Approach: | They propose a domain adversarial learning enhanced self-training framework that uses meta-learning to estimate the importance of each pseudo instance and a meta constructor to construct the meta-validation set. |
| Outcome: | The proposed framework reduces label noise and preserves hard examples while maintaining accuracy. |
Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders (D19-1)
Copied to clipboard
| Challenge: | Existing work on variableal autoencoders and waterstein autoencoding models has shown significant progress in open-domain response generation. |
| Approach: | They propose to embed user-level and utterance-level information into two multimodal distributions and combine them into a mixed distribution. |
| Outcome: | The proposed model outperforms state-of-the-art models on a large-scale real-world dataset. |
Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing TIMT tasks focus on text-line-level images. |
| Approach: | They propose to extend the existing TIMT task and introduce a new framework to translate a source document image to markdown-formatted target translation. |
| Outcome: | The proposed task aims to translate a source document image with long context and complex layout structure to markdown-formatted target translation. |
Reconstructing Event Regions for Event Extraction via Graph Attention Networks (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing approaches for event extraction focus on sentence-level event extraction, but they lack a broader view of the document context. |
| Approach: | They build graphs with candidate event filler extractions enriched by sentential embeddings as nodes and use graph attention networks to identify event regions in a document and aggregate event information. |
| Outcome: | The proposed method performs well on two languages and shows that it is faster than previous methods. |
Streaming Hallucination Detection in Long Chain-of-Thought Reasoning (2026.findings-acl)
Copied to clipboard
Haolang Lu, Minghui Pan, Ripeng LI, Guoshun Nan, Jialin Zhuang, Zijie Zhao, Zhongxiang Sun, Kun Wang, Yang Liu
| Challenge: | Long chain-of-thought reasoning improves performance of large language models, yet hallucinations in such settings often emerge subtly and propagate across reasoning steps. |
| Approach: | They propose to treat step-level hallucination judgments as local observations and introduce a cumulative prefix-level signal that tracks the global evolution of the reasoning state over the entire trajectory. |
| Outcome: | The proposed method enables streaming hallucination detection in long CoT reasoning, providing real-time, interpretable evidence. |
Faster MoE LLM Inference for Extremely Large Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing inference optimizations for coarse-grained Mixture-of-Experts models implicitly assume a fixed activation budget, which is poorly understood. |
| Approach: | They propose a training-free policy that adapts token-level activation using router confidence and entropy while remaining within the model’s original budget. |
| Outcome: | The proposed skipping policy can provide substantial throughput gains, but optimal static schedules vary significantly across models and routing mechanisms. |
EmoRes: Toward Adaptive Psychological Support via User-Agnostic Benchmark and Topic-Mining Agent (2026.findings-acl)
Copied to clipboard
Zhengwei Zou, Xuanming Jiang, Baoyi An, Dingyu Nie, Zhengxing Fang, Qingyu Liu, Xueming Qian, Guoshuai Zhao, Zhongyu Yang
| Challenge: | Large language models generate fragmented and emotionally inconsistent dialogues lacking the therapeutic structure necessary for reliable assessment. |
| Approach: | They propose a framework that boosts psychological reasoning via a Topic-Mining Emotional Agent and a multi-perspective Self-Reflection Agent. |
| Outcome: | The proposed framework improves topic continuity, emotional coherence, and clinical interpretability over baselines and validated by ablation studies and human evaluations. |
Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)
Copied to clipboard
Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu
| Challenge: | Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs. |
| Approach: | They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn. |
| Outcome: | The proposed framework improves strategy selection preferences at each dialogue turn. |
ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025.emnlp-main)
Copied to clipboard
Zhao Xinjie, Fan Gao, Xingyu Song, Yingjian Chen, Rui Yang, Yanran Fu, Yuyang Wang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
| Challenge: | Multi-hop question answering (QA) is a central challenge in natural language processing . early mistakes can cause errors and undermine the final result, authors say . |
| Approach: | They propose a reversible multi-agent reasoning framework that backtracks to earlier valid states when conflicts arise. |
| Outcome: | Empirical evaluation shows that the framework improves on forward-only benchmarks by 6% . the approach enables agents to backtrack to valid states when conflicts arise . |
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment (2026.acl-long)
Copied to clipboard
Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou, Qipeng Guo, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model’s current behavior but overlooking more informative ones. |
| Approach: | They propose a Rank–Surprisal Ratio metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory. |
| Outcome: | The proposed metric captures both alignment and informativeness to assess the suitability of a reasoning trajectory. |
DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators (2024.emnlp-main)
Copied to clipboard
| Challenge: | Concatenating large language models are adapted to context-aware neural machine translation in a concatenated way . a recent paradigm shift has been witnessed in discourse-related challenges such as zero pronoun translation . |
| Approach: | They propose an alternative adaptation approach to make large language models discriminately model and utilize inter- and intra-sentence contexts. |
| Outcome: | The proposed approach outperforms concatenation mode and improves performance in discourse modeling. |
Target-Aware Language Modeling via Granular Data Sampling (2024.emnlp-main)
Copied to clipboard
Ernie Chang, Pin-Jie Lin, Yang Li, Changsheng Zhao, Daeil Kim, Rastislav Rabatin, Zechun Liu, Yangyang Shi, Vikas Chandra
| Challenge: | Language model pretraining is the cornerstone of universal language models (LMs), creating generalpurpose representations to excel across a variety of downstream tasks. |
| Approach: | They propose to use multi-granular tokens to sample large-scale language models for domain-specific use cases. |
| Outcome: | The proposed model outperforms random sampled samples on eight benchmarks with 1% of the data and performs on par with the full RefinedWeb data. |
Think before Go: Hierarchical Reasoning for Image-goal Navigation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for image-goal navigation fail to extract informative visual cues, leading agents to wander around. |
| Approach: | They propose a framework that decomposes image-goal navigation into high-level planning and low-level execution. |
| Outcome: | The proposed method is superior to existing methods in both simulation and real-world environments. |
Position Really Matters: Towards a Holistic Approach for Prompt Tuning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Prompt tuning is effective in extracting knowledge from foundation models, but its effectiveness is uncertain. |
| Approach: | They propose a parametric prompt tuning strategy that dynamically determines different factors of prompts based on specific tasks or instances. |
| Outcome: | The proposed approach improves performance across a wide range of tasks including NLP, vision recognition, and vision-language tasks. |
Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification System (2022.naacl-industry)
Copied to clipboard
Tao Zhu, Zhe Zhao, Weijie Liu, Jiachi Liu, Yiren Chen, Weiquan Mao, Haoyan Liu, Kunbo Ding, Yudong Li, Xuefeng Yang
| Challenge: | Existing continual learning methods use data replay, parameter isolation and regularization to mitigate catastrophic forgetting. |
| Approach: | They propose a parameter-efficient continual learning framework that updates parameters offline and then trains using an online regularization method. |
| Outcome: | The proposed framework reduces catastrophic forgetting and saves the model with the changed parameters instead of all parameters. |
Improving Translation Quality Estimation with Bias Mitigation (2023.acl-long)
Copied to clipboard
| Challenge: | State-of-the-art translation Quality Estimation models are biased, relying on monolingual features while ignoring the bilingual semantic alignment. |
| Approach: | They propose a method to mitigate the bias of translation quality estimation models by contrastive learning between clean and noisy sentence pairs. |
| Outcome: | The proposed method improves the estimation performance while mitigating the bias. |
ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation (2025.emnlp-main)
Copied to clipboard
Minghua He, Yue Chen, Fangkai Yang, Pu Zhao, Wenjie Yin, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing code translation models only learn the contextual semantics of code during pre-training, neglecting executability information closely related to the execution state of the code. |
| Approach: | They propose an LLM specifically designed for code translation called ExeCoder . it uses executability representations such as functional semantics and syntax structures to enhance LLMs' capabilities. |
| Outcome: | The proposed model outperforms existing open-source code translation models on two metrics. |
Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been used in Knowledge Distillation (KD) to compress large models. |
| Approach: | They propose a Kullback-Leiber divergence method which adaptively allocates weights to combine RKL and FKL to reduce the size of Large Language Models (LLMs). |
| Outcome: | The proposed method outperforms baselines and improves diversity and quality of generated responses. |
Aspect and Sentiment Aware Abstractive Review Summarization (C18-1)
Copied to clipboard
| Challenge: | Abstractive summarization is a task that generates short and concise summaries of user generated reviews. |
| Approach: | They propose an interactive attention mechanism to learn the representations of context and aspect words within reviews, acted as an encoder. |
| Outcome: | The proposed model achieves impressive results compared to other strong competitors on a real-life dataset. |
Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for GUI understanding ignore a key GUI-referring task: screen reading based on user-indicated points. |
| Approach: | They propose a Tree-of-Lens agent that constructs a Hierarchical Layout Tree based on user input points and a GUI screenshot. |
| Outcome: | The proposed agent can interpret the Screen Point-and-Read task on mobile, web, and operating systems. |
SELF-GUARD: Empower the LLM to Safeguard Itself (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have investigated methods to improve the safety of large language models (LLMs) safety training involves fine-tuning the LLM with adversarial samples, which activate the LRM’s capabilities against jailbreak. |
| Approach: | They propose a safety training approach that integrates safety training and safeguards to train the LLM to perform harmfulness detection on its own outputs. |
| Outcome: | The proposed method reduces harmful output and adds a [harmful] or [harmless] tag to the end of the LLM's response. |
Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding (2024.findings-emnlp)
Copied to clipboard
Liang Zhao, Xiachong Feng, Xiaocheng Feng, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin, Ting Liu
| Challenge: | Existing methods to enhance length extrapolation of large language models have been developed, but a systematic survey is lacking. |
| Approach: | They propose to examine the effects of positional encoding on length extrapolation. |
| Outcome: | The proposed methods improve the extrapolation of large language models, but they are still lacking a systematic survey. |
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach (2025.findings-acl)
Copied to clipboard
Yurong Wu, Fangwen Mu, Qiuhong Zhang, Jinjing Zhao, Xinrun Xu, Lingrui Mei, Yang Wu, Lin Shi, Junjie Wang, Zhiming Ding, Yiwei Wang
| Challenge: | Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images. |
| Approach: | They propose a prompt-stealing benchmark consisting of 50 templates and 450 images organized into Easy and Hard difficulty levels. |
| Outcome: | The proposed method outperforms baseline methods with an average improvement of over 10%. |
Large Dual Encoders Are Generalizable Retrievers (2022.emnlp-main)
Copied to clipboard
Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernandez Abrego, Ji Ma, Vincent Zhao, Yi Luan, Keith Hall, Ming-Wei Chang, Yinfei Yang
| Challenge: | Experimental results show that dual encoders outperform sparse and dense retrievers on the BEIR dataset significantly. |
| Approach: | They challenge belief that bottleneck layer is too limited for out-of-domain generalization . they scale up the model while keeping bottleneck as a single dot-product with a fixed size . |
| Outcome: | The proposed model outperforms sparse and dense retrievers on the BEIR dataset significantly. |
ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL (2026.acl-long)
Copied to clipboard
Yaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang, Ziyi Liu, Haiqin Yang, Yiying Yang, Yuhang Zhao, Pingfu Chao, Wenhao Jiang
| Challenge: | Current Text-to-SQL reasoning models lack integrated execution feedback during generation. |
| Approach: | They propose a text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback. |
| Outcome: | The proposed framework achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale. |
A Language Model based Evaluator for Sentence Compression (P18-2)
Copied to clipboard
| Challenge: | Existing methods to produce readable sentence compression are based on machine learning or syntactic tree-based approaches. |
| Approach: | They propose a language-model-based evaluator for deletion-based sentence compression . they propose deleting operations on source sentences to obtain best target compression based on the proposed model . |
| Outcome: | The proposed model generates more readable compression comparable to strong baselines. |
Look Beyond Feeling: Unveiling Latent Needs from Implicit Expressions for Proactive Emotional Support (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are gaining popularity as scalable tools for mental health support . however, nearly half of individuals do not receive timely support due to limited selfawareness or reluctance to seek help. |
| Approach: | They propose a proactive emotional support framework that leverages principles of active listening to uncover implicit user needs. |
| Outcome: | The proposed model elicits implicit emotional needs and delivers empathetic support compared to baselines . |
Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)
Copied to clipboard
Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong
| Challenge: | Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited. |
| Approach: | They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning . |
| Outcome: | The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster. |
Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing decoding methods for large language models (LLMs) are specialized in resolving knowledge conflicts and could inadvertently deteriorate performance in absence of conflicts. |
| Approach: | They propose an adaptive decoding method to discern whether knowledge conflicts occur and resolve them by a contextual information-entropy constraint decoding technique. |
| Outcome: | The proposed method improves the model’s faithfulness to conflicting context and maintains high performance among non-conflicting contexts. |
Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge (2024.emnlp-main)
Copied to clipboard
| Challenge: | despite advances in multimodal large language models, the challenge of interpreting long-form videos remains a challenge . despite advancements in video-language benchmarks, the inefficiency in temporal grounding and limited pre-trained context window size remains . |
| Approach: | They propose a framework that bootstraps MLLMs with advanced temporal grounding capabilities and broadens their contextual scope. |
| Outcome: | The proposed framework significantly enhances the temporal capabilities of existing MLLMs. |
SPHERE: An Evaluation Card for Human-AI Systems (2025.findings-acl)
Copied to clipboard
Dora Zhao, Qianou Ma, Xinran Zhao, Chenglei Si, Chenyang Yang, Ryan Louie, Ehud Reiter, Diyi Yang, Tongshuang Wu
| Challenge: | Existing evaluation methods and standards for human-AI systems are unclear, especially for large language models. |
| Approach: | They propose an evaluation card SPHERE which provides a template for evaluation protocols . they outline current evaluation practices and areas for improvement . |
| Outcome: | The evaluation card provides a template for designing evaluation protocols . it outlines current evaluation practices and areas for improvement . |
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies treat named entity recognition as a sequential labeling problem. |
| Approach: | They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted . |
| Outcome: | The proposed framework outperforms competing models on four benchmark datasets. |
FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for speech editing still suffer from over-smoothing problem and lack of robustness due to stutter. |
| Approach: | They propose a stutter-oriented automatic speech editing model that incorporates sutter information into the hidden sequence. |
| Outcome: | The proposed model achieves state-of-the-art performance on a speech recording dataset . it can improve fluency of stuttering speech in terms of objective and subjective metrics. |
Alignment Rationale for Natural Language Inference (2021.acl-long)
Copied to clipboard
| Challenge: | Existing explanation methods pick prominent features, but alignments between words or phrases are more enlightening clues to explain the model. |
| Approach: | They propose a method to generate alignment rationale explanations for co-attention based models in NLI by feature selection. |
| Outcome: | The proposed method is more faithful and human-readable compared with existing methods. |
The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks to evaluate LLMs' capabilities are inadequate for assessing their musical capabilities. |
| Approach: | They propose to use a large-scale music benchmark specifically designed to evaluate the music-related capabilities of large language models (LLMs). |
| Outcome: | The proposed framework evaluates 16 large language models in the domain of music. |
Table-based Fact Verification with Self-labeled Keypoint Alignment (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for fact verification rely on graph feature or data augmentation but fail to investigate evidence correlation between statement and table effectively. |
| Approach: | They propose a self-labeled keypoint alignment model to explore correlation between statement and table . they propose integrating a mixture-of experts block to integrate interacted information . |
| Outcome: | The proposed model outperforms the state-of-the-art models and captures interpretable evidence words on three widely-studied datasets. |
Unsupervised Rewriter for Multi-Sentence Compression (P19-1)
Copied to clipboard
| Challenge: | Multi-sentence compression aims to generate a grammatical but reduced compression from multiple input sentences while retaining key information. |
| Approach: | They propose a neural rewriter for multi-sentence compression that does not need any parallel corpus. |
| Outcome: | Empirical studies show that the proposed approach achieves comparable results upon automatic evaluation and improves the grammaticality of compression based on human evaluation. |
EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026.findings-acl)
Copied to clipboard
Haoqin Sun, Jinghua Zhao, Xuechen Wang, Shiwan Zhao, Jiaming Zhou, Hui Wang, Xi Yang, Yequan Wang, Yonghua Lin
| Challenge: | Existing datasets face issues such as low quality, limited scale, and incomplete modalities, hindering model performance. |
| Approach: | They propose to use Chinese multimodal datasets to capture authentic emotional interplay from 19 professional actors. |
| Outcome: | The EmotionTalk dataset spans 23.6 hours of dyadic conversations across diverse scenarios. |
SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space. |
| Approach: | They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations. |
| Outcome: | The proposed framework outperforms baselines while maintaining reasonable time and computational costs. |
Rejection-to-Acceptance Transition: Model Editing-Based Jailbreak Backdoor Injection Not Limited to Few Output Tokens (2026.findings-acl)
Copied to clipboard
Shiji Yang, Min Cai, Hao Xiong, Congyao Mei, Haodong Zou, Shicheng Tan, Jie Chen, Fulan Qian, Shu Zhao
| Challenge: | Existing methods for jailbreaking LLMs are implemented by binding backdoors to predefined phrases as first few output tokens, inducing the LLM’s next-token prediction to produce continuous responses. |
| Approach: | They propose a model editing-based jailbreak backdoor attack that hijacks LLM representations into a acceptance domain rather than binding to a few output tokens. |
| Outcome: | The proposed model editing method outperforms existing methods, showing stronger jailbreak capabilities across LLMs and datasets. |
Document-level Event Extraction via Parallel Prediction Networks (2021.acl-long)
Copied to clipboard
| Challenge: | Document-level event extraction (DEE) is indispensable when events are described throughout a document. |
| Approach: | They propose a document-level event extraction model that can extract structured events from a text in parallel. |
| Outcome: | The proposed model outperforms current state-of-the-art methods on a document-level event extraction task. |
DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Current Event Extraction methods focus on high-resource scenarios, which requires large amount of annotated data. |
| Approach: | They propose a demonstration-based learning paradigm for EE to fully use annotated data . they propose EE as a natural language generation task guided by schema-based prompts . |
| Outcome: | The proposed model outperforms current methods in low-resource scenarios. |
Token-level Proximal Policy Optimization for Query Generation (2025.emnlp-main)
Copied to clipboard
Yichen Ouyang, Lu Wang, Fangkai Yang, Pu Zhao, Chenghua Huang, Jianfeng Liu, Bochen Pang, Yaming Yang, Yuefeng Zhan, Hao Sun, Qingwei Lin, Saravan Rajmohan, Weiwei Deng, Dongmei Zhang, Feng Sun
| Challenge: | Large Language Models (LLMs) have improved search engines and recommendation systems through their text understanding capabilities. |
| Approach: | They propose a token-level proximal policy optimization approach to empower LLMs to perform better in query generation through fine-tuning. |
| Outcome: | The proposed approach outperforms existing LLMs on an open-source and industrial dataset. |
Aspect-based Sentiment Analysis as Machine Reading Comprehension (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to aspect-based sentiment analysis stack multiple modules and result in severe error propagation. |
| Approach: | They propose a MRC-PrOmpt mOdeL framework where multiple sentiment aspects are elicited by a machine reading comprehension model and their corresponding sentiment polarities are classified in a prompt learning way. |
| Outcome: | The proposed framework significantly outperforms existing state-of-the-art models or achieves comparable performance on widely-used benchmark 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. |
Towards Infinite-Long Prefix in Transformer (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prefix Learning is an empirically efficient and effective method for language models . but the theoretical understandings are limited on the performance of such methods . |
| Approach: | They propose a method that can train an ultra-long prefix in a stylized setting using the Neural Tangent Kernel framework. |
| Outcome: | The proposed method can achieve superior performance on vision, natural language, and math data. |
Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing document-level neural machine translation methods use all context sentences in a fixed scope. |
| Approach: | They propose an approach to select dynamic context so that document-level neural machine translation models can utilize more useful selected context sentences. |
| Outcome: | The proposed approach can select adaptive context sentences for different source sentences and significantly improves translation quality over sentences in a document. |
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. |
MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts (2024.lrec-main)
Copied to clipboard
| Challenge: | Current Chain-of-thought Distillation methods hinder CoT reasoning performance . student models are separately distilled from specific reasoning tasks . parameter update of student models severely harms CoT ability on unseen reasoning tasks. |
| Approach: | They propose a method which distills Chain-of-thought reasoning ability of large language models to much smaller student models. |
| Outcome: | The proposed method improves the reasoning ability of large language models on 14 datasets. |
End-to-End Learnable Psychiatric Scale Guided Risky Post Screening for Depression Detection on Social Media (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to detect depression from social media posting history are limited by frozen screening models and lack of learning. |
| Approach: | They propose to use a frozen screening model to train a risky post detection model with psychiatric scales to enable a learnable end-to-end learning process. |
| Outcome: | The proposed model outperforms several strong baseline methods and qualitative analysis confirms that it better captures users’ mental states than others. |
Multilingual Knowledge Graph Completion with Language-Sensitive Multi-Graph Attention (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multilingual knowledge graph completion have two drawbacks: alignment dependency and training inefficiency. |
| Approach: | They propose a multilingual knowledge graph completion framework with language-sensitive multi-graph attention to predict missing links on all given KGs. |
| Outcome: | The proposed model improves on the DBP-5L and E-PKG datasets. |
BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models have driven major progress in NLP, but memory and compute requirements hinder practical deployment. |
| Approach: | They propose a framework that preserves high accuracy while achieving 1-bit weight quantization . the orthogonal-kronecker transformation learns an orthogonale mapping via EM minimization - a new approach to quantization is proposed . |
| Outcome: | The proposed framework achieves 1-bit weight quantization with low activations with low-bit activations. |
Neural Bi-Lexicalized PCFG Induction (2021.acl-long)
Copied to clipboard
| Challenge: | Neural lexicalized PCFGs make strong independence assumption on the generation of the child word and thus bilexical dependencies are ignored. |
| Approach: | They propose an approach to parameterize L-PCFGs without making implausible independence assumptions. |
| Outcome: | The proposed approach improves both running speed and unsupervised parsing performance on the English WSJ dataset. |
Decoding the Multimodal Mind: Generalizable Brain-to-Text Translation via Multimodal Alignment and Adaptive Routing (2026.findings-acl)
Copied to clipboard
| Challenge: | Current approaches to decoding language from the human brain rely on unimodal representations, neglecting the brain’s inherently multimodal processing. |
| Approach: | They propose a framework that leverages Multimodal Large Language Models to align brain signals with a shared semantic space encompassing text, images, and audio. |
| Outcome: | The proposed framework achieves an 8.48% improvement on the most commonly used benchmark on fMRI datasets with textual, visual, and auditory stimuli. |
A Survey on Detection of LLMs-Generated Content (2024.findings-emnlp)
Copied to clipboard
Xianjun Yang, Liangming Pan, Xuandong Zhao, Haifeng Chen, Linda Petzold, William Yang Wang, Wei Cheng
| Challenge: | Recent advances in large language models have led to an increase in synthetic content generation . the ability to detect LLMs-generated content has become of paramount importance . |
| Approach: | They propose to provide a detailed overview of existing detection strategies and benchmarks, scrutinizing their differences and advocating for more adaptable and robust models to enhance detection accuracy. |
| Outcome: | The proposed model will be able to detect human-written content in real time. |
Little Giants: Synthesizing High-Quality Embedding Data at Scale (2025.naacl-long)
Copied to clipboard
| Challenge: | Synthetic data generation is an increasingly popular way of training models without the need for large, manually labeled datasets. |
| Approach: | They propose a framework that aligns open-source small models to efficiently generate large-scale embedding data. |
| Outcome: | The proposed framework outperforms state-of-the-art embedding models by using only 1/10 of the GPT API calls. |
WatME: Towards Lossless Watermarking Through Lexical Redundancy (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text watermarking rely on arbitrary vocabulary partitioning during decoding, which compromises the availability of suitable tokens and significantly degrades the quality of responses. |
| Approach: | They propose a method that leverages linguistic prior knowledge of lexical redundancies in LLM vocabularies to seamlessly integrate watermarks. |
| Outcome: | The proposed approach preserves the expressive power of large language models while preserving watermark detectability. |
Domain Adaptation for Person-Job Fit with Transferable Deep Global Match Network (D19-1)
Copied to clipboard
| Challenge: | Existing methods to solve person-job fit in single-domain setting are limited by labeled data. |
| Approach: | They propose a deep global match network for capturing the global semantic interactions between two sentences from a job posting and a candidate resume respectively. |
| Outcome: | The proposed model is effective when there is not enough labeled data. |
CCIM: Cross-modal Cross-lingual Interactive Image Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on text image machine translation (TIMT) lacks recognized source language information resulting in a decrease in translation performance. |
| Approach: | They propose a cross-modal cross-lingual interactive model which incorporates source language information by synchronizing source and target language results. |
| Outcome: | The proposed model outperforms end-to-end models and has faster decoding speed with smaller model size than cascade models. |
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation (2020.acl-main)
Copied to clipboard
| Challenge: | a standard evaluation setup for supervised machine learning tasks does not hold for natural language generation tasks. |
| Approach: | They propose to use reference-free machine translation evaluation to compare source texts to system translations to find key limitations. |
| Outcome: | The proposed metrics perform poorly as semantic encoders for reference-free machine translation evaluation. |
Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (2024.findings-acl)
Copied to clipboard
Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang
| Challenge: | Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents. |
| Approach: | They propose a cognitive framework that incorporates first-order and second-order perspective transitions into LLMs to enhance their ability to identify and counteract deceptive information. |
| Outcome: | The proposed framework enhances LLMs’ ability to identify and counteract deceptive information without extra fine-tuning and data. |
Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing safety defenses for large language models fail to explicitly repel harmful patterns . Optimal transport (SOT) allows for safe fine-tuning without sacrificing safety . |
| Approach: | They propose a framework that reframes safe fine-tuning from instance-level filtering challenge to distribution-level alignment task grounded in Optimal Transport. |
| Outcome: | a new framework improves safety of large language models while maintaining competitive performance . the proposed framework reduces the risk of errors and improves model performance compared to baselines . |
A Simple Yet Effective Corpus Construction Method for Chinese Sentence Compression (2022.lrec-1)
Copied to clipboard
| Challenge: | Deletion-based sentence compression has made significant progress in the english language . however, there is a lack of large-scale and high-quality parallel corpus for the Chinese language to train an efficient system. |
| Approach: | They propose to construct a Chinese corpus with 151k pairs of sentences and train extractive and generative neural compression models on the constructed corpus. |
| Outcome: | The proposed method generates high-quality compressed sentences on automatic and human evaluation metrics compared with baselines. |
NLP-ADBench: NLP Anomaly Detection Benchmark (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Anomaly detection (AD) is an important machine learning task, but its effectiveness in detecting harmful content, phishing attempts, and spam reviews is limited. |
| Approach: | They introduce NLP-ADBench, the most comprehensive NLP anomaly detection benchmark to date . it includes eight curated datasets and 19 state-of-the-art algorithms . |
| Outcome: | The NLP-ADBench benchmark includes 19 state-of-the-art methods and 8 curated datasets . no single model dominates across all datasets, indicating need for automated model selection . |
Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal large language models are increasingly deployed in open-ended, real-world environments where inputs are messy, underspecified, and not always trustworthy. |
| Approach: | They evaluate multimodal large language models in real-world environments where inputs are messy, underspecified, and not always trustworthy. |
| Outcome: | The proposed models fail to detect hidden issues even when they possess the necessary perceptual and reasoning skills. |
Fast Adaptation via Prompted Data: An Efficient Cross-Domain Fine-tuning Method for Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been successful in a variety of natural language understanding tasks, but domain discrepancies between the downstream task and the pre-training corpora may have hindered LLMs to excel further in the vertical applications. |
| Approach: | They propose a Fast Adaptation method for LLMs via Prompted Data that integrates downstream text corpora, gold labels and external knowledge sources into a highly controllable prompt. |
| Outcome: | The proposed method bridges the gap between the downstream task and the pre-training corpora and integrates downstream text corpors, gold labels and external knowledge sources into a highly controllable prompt. |
Exploring Fine-Grained Human Motion Video Captioning (2025.coling-main)
Copied to clipboard
Bingchan Zhao, Xinyi Liu, Zhuocheng Yu, Tongchen Yang, Yifan Song, Mingyu Jin, Sujian Li, Yizhou Wang
| Challenge: | Existing video captioning models fail to capture nuanced semantics of videos . existing models generate coarse descriptions of human motions, resulting in poor quality . |
| Approach: | They construct a fine-grained human motion video captioning dataset named BoFiT and a model that generates fine-grain descriptions of human motions via prompting. |
| Outcome: | The proposed model outperforms existing models on comprehensive metrics. |
Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech (D19-3)
Copied to clipboard
| Challenge: | Language model adaptation (LMA) is a promising solution for conversational speech recognition systems. |
| Approach: | They propose to use language model adaptation techniques to adapt language models to conversational speech recognition. |
| Outcome: | The proposed toolkit compares state-of-the-art language model adaptation techniques in conversational speech recognition tasks. |
Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have suggested that the composition of the pretraining corpus exerts a significant impact upon the performance of LLMs. |
| Approach: | They analyze the impact of 48 datasets from 5 major categories of pretraining data of Large Language Models and measure their impacts on LLMs using benchmarks about nine major categories. |
| Outcome: | The proposed analysis provides insights into the organization of data to support more efficient pretraining of Large Language Models. |
Don’t Just Say “I don’t know”! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies investigate ways to refuse to answer unknown questions . Large Language Models (LLMs) display a significant level of overconfidence when answering questions that they are aware of. |
| Approach: | They propose a self-alignment method to utilize Large Language Models to enhance its response-ability to unknown questions. |
| Outcome: | The proposed method is superior to baseline methods on four types of unknown questions. |
Learning Better Masking for Better Language Model Pre-training (2023.acl-long)
Copied to clipboard
| Challenge: | Existing PrLMs adopt a Random-Token Masking strategy with a fixed masking ratio and different contents are masked by an equal probability throughout the training. |
| Approach: | They propose two scheduled masking approaches that adaptively tune masking ratio and masked content in different training stages, which improves pre-training efficiency and effectiveness. |
| Outcome: | The proposed methods improve the pre-training efficiency and effectiveness on the downstream tasks. |
A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning (2026.acl-long)
Copied to clipboard
Tianyu Yang, Sihong Wu, Yilun Zhao, Zhenwen Liang, Lisen Dai, Chen Zhao, Minhao Cheng, Arman Cohan, Xiangliang Zhang
| Challenge: | Multimodal mathematical Reasoning (MMR) has attracted increasing attention for its ability to solve mathematical problems involving both textual and visual modalities. |
| Approach: | They review the theoretical frameworks of multimodal reasoning and examine the challenges they face in visual math tasks. |
| Outcome: | The proposed models can solve problems involving both textual and visual modalities. |
Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been successful in Text-to-SQL tasks, but their deployment in real-world environments is hindered by latent reliability issues. |
| Approach: | They propose a framework to autonomously uncover latent failure patterns in LLM-based Text-to-SQL generation. |
| Outcome: | The proposed framework uncovers a substantial number of failure cases on state-of-the-art open-source LLMs. |
Progressive Self-Training with Discriminator for Aspect Term Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to extract aspect terms from review sentences are limited due to lack of annotated data. |
| Approach: | They propose to refine conventional self-training to progressive self-teaching to reduce noise . they use a discriminator to filter the noisy pseudo-labels. |
| Outcome: | The proposed model outperforms baseline models and achieves state-of-the-art performance on four SemEval datasets. |
Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns (2025.acl-long)
Copied to clipboard
| Challenge: | Currently, LLMs learn in a data-driven schema while the instructions about complex tasks are both scarce and hard to collect or construct. |
| Approach: | They employ a gradient-based method to dissect the process that the Supervised Fine-tuning Process (SFT) adapts LLMs to downstream tasks via the perspective of attention patterns. |
| Outcome: | The proposed method dissects the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns. |
WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling (2026.findings-acl)
Copied to clipboard
Jiacheng Li, Jianchao Tan, Zhidong Yang, Pingwei Sun, Feiye Huo, Jiayu Qin, Xiangyu Zhang, Maoxin He, Guangming Tan, Weile Jia, Xunliang Cai, Tong Zhao
| Challenge: | Recent advances in training optimization for Transformer-based large language models lack systematic optimization of weight patterns during training. |
| Approach: | They propose a Weight Scaling method that rescales weights while preserving model outputs to improve model training efficiency and model quality. |
| Outcome: | The proposed method significantly improves convergence quality and loss reduction in LLMs with Grouped Query Attention architectures and LoRA fine-tuning tasks. |
MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning (2026.findings-acl)
Copied to clipboard
Ruijun Huang, Zhiqiao Kang, Yuxuan Zhu, Junxiong Li, Jiahao Zhao, Minghuan Tan, Feng Jiang, Min Yang
| Challenge: | Large Language Models (LLMs) exhibit severe hallucinations, which undermine reliability of automated scientific document understanding systems. |
| Approach: | They propose a framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization. |
| Outcome: | The proposed framework significantly reduces hallucination rates and improves overall accuracy on the MeasEval benchmark. |
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios (2025.findings-acl)
Copied to clipboard
Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, Daniel Zhang-Li, Jifan Yu, Shu Zhao, Juanzi Li, Jie Tang
| Challenge: | TableLLM is a robust large language model capable of handling tabular data manipulation tasks. |
| Approach: | They propose a distant supervision method for training which includes a reasoning process extension strategy and a cross-way validation strategy. |
| Outcome: | The proposed model has 8 billion parameters and is capable of handling tabular data tasks. |
DGoT: Dynamic Graph of Thoughts for Scientific Abstract Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for generating abstracts involve collecting domain data and training corresponding models to complete the task of text summarization. |
| Approach: | They propose a method to train language models based on domain datasets and a Dynamic Graph of Thought (DGoT) which inherits the advantages of existing GoT prompt approach while reducing model reasoning cost. |
| Outcome: | The proposed method saves the cost of model training and improves reliability due to the hallucination problem of LLMs. |
FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models (2025.coling-main)
Copied to clipboard
Shu Liu, Shangqing Zhao, Chenghao Jia, Xinlin Zhuang, Zhaoguang Long, Jie Zhou, Aimin Zhou, Man Lan, Yang Chong
| Challenge: | Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, but their proficiency and reliability in the specialized domain of financial data analysis remain uncertain. |
| Approach: | FinDABench is a benchmark designed to evaluate the financial data analysis capabilities of Large Language Models (LLMs) it comprises 15,200 training instances and 8,900 test instances, all meticulously crafted by human experts. |
| Outcome: | FinDABench measures the financial data analysis capabilities of large language models (LLMs) across three dimensions: 1) Core Ability; 2) Analytical Ability; 3) Technical Ability. |
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)
Copied to clipboard
Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E
| Challenge: | AEGIS examines whether current models can effectively audit AI-generated images in academic papers. |
| Approach: | They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics. |
| Outcome: | AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis. |
ICA-Proto: Iterative Cross Alignment Prototypical Network for Incremental Few-Shot Relation Classification (2023.findings-eacl)
Copied to clipboard
Wangjie Jiang, Zhihao Ye, Bang Liu, Ruihui Zhao, Jianguang Zheng, Mengyao Li, Zhiyong Li, Yujiu Yang, Yefeng Zheng
| Challenge: | Existing methods for relation classification suffer from the scarcity of manually annotated data. |
| Approach: | They propose a novel relation classification model that incorporates query representation into the encoding of novel prototypes and utilizes iteratively to achieve more interaction. |
| Outcome: | The proposed model outperforms the state-of-the-art model on two benchmark datasets. |
Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing Multimodal Large Language Models (MLLMs) are predominantly trained on consistent visual-textual inputs, leaving open the question of whether they can handle semantic mismatches in layout-rich content. |
| Approach: | They propose to use multimodal inconsistency reasoning to assess MLLMs' ability to reason about semantic mismatches in webpages, presentation slides, and posters. |
| Outcome: | The proposed model outperforms open-source models in detecting inconsistencies in webpages, presentation slides, and posters while remaining vulnerable to inconsistent errors. |
OmniDiagram: Advancing Unified Diagram Code Generation via Visual Interrogation Reward (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on programmable diagram generation focus on a narrow set of tasks and languages. |
| Approach: | They propose a unified framework that integrates diverse diagram code languages and task definitions. |
| Outcome: | The proposed framework can bridge complex visual information with executable code across diverse tasks and languages. |
S2ST-Omni: Hierarchical Language-Aware SpeechLLM Adaptation for Multilingual Speech-to-Speech Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | S2ST-Omni integrates a speech-to-text frontend with a modular, plug-and-play text-tospeech backend. |
| Approach: | They propose a compositional S2ST framework that integrates a speech-to-text frontend with a modular, plug-and-play text-tospeech backend. |
| Outcome: | The proposed framework outperforms existing frameworks in translation and synthesis . it integrates a speech-to-text translation frontend with a plug-and-play text-tospeech backend . |
Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework (2025.findings-emnlp)
Copied to clipboard
Bohao Yang, Dong Liu, Chenghao Xiao, Kun Zhao, Chen Tang, Chao Li, Lin Yuan, Yang Guang, Chenghua Lin
| Challenge: | Large Language Models (LLMs) are capable of generating human-like text, but the potential for freely customisable characters remains underexplored. |
| Approach: | They propose a framework which employs Large Language Models to create freely customisable characters through personalised characteristic feature injection. |
| Outcome: | The proposed framework provides valuable insights for developing more accurate and customisable human simulacra. |
Treble Counterfactual VLMs: A Causal Approach to Hallucination (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies link hallucination to data or representation biases, but their causal origins remain unclear. |
| Approach: | They propose a causal framework to analyze and mitigate hallucination in vision-language models by using counterfactual analysis to estimate the Natural Direct Effect (NDE) of each modality and their interaction. |
| Outcome: | The proposed framework significantly reduces hallucination while preserving task performance while retaining reliability. |
H-LegalKI: A Hierarchical Legal Knowledge Integration Framework for Legal Community Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Legal question answering (LQA) aims to bridge the gap between limited availability of legal professionals and the extensive volume of legal issues. |
| Approach: | They propose a legal knowledge retriever and a hierarchical legal knowledge integration framework to address multiple user-specific circumstances. |
| Outcome: | The proposed framework outperforms baselines on the legal community question-answering dataset. |
Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for language analysis are inadequate for specialized domains like psychology. |
| Approach: | They have enriched a Chinese social media database with psychological lexicons to enhance its applicability to psychological text analysis. |
| Outcome: | The proposed model performed better on six public datasets and provided relevant predictions given the masked sentences. |
AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Large Language Models are increasingly used in Personalized Image Aesthetic Assessment (PIAA) however, their predictions may reflect subtle biases influenced by demographic factors such as gender, age, and education. |
| Approach: | They propose to evaluate MLLMs along two complementary dimensions: (1) stereotype bias and (2) alignment between model outputs and genuine human aesthetic preferences. |
| Outcome: | The proposed benchmark covers three subtasks: aesthetic perception, assessment, empathy and alignment between outputs and genuine human aesthetic preferences. |
Born a BabyNet with Hierarchical Parental Supervision for End-to-End Text Image Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing research on text image machine translation (TIMT) is divided into two types: Cascade methods combine text image recognition and MT models to recognize source language text images. |
| Approach: | They propose a method which is optimized with hierarchical parental supervision to improve translation performance. |
| Outcome: | The proposed method significantly outperforms existing methods on synthetic and real-world tests on both synthetic and realistic images. |
CoAct: Co-Active LLM Preference Learning with Human-AI Synergy (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to learn from preference-based feedback are expensive and scarce. |
| Approach: | They propose a framework that synergistically combines self-rewarding and active learning through human-AI collaboration. |
| Outcome: | The proposed framework outperforms existing methods on three reasoning benchmarks and achieves average improvements of +13.25% on GSM8K, +8.19% on MATH, and +13.16% on WebInstruct. |
Improving MLLM’s Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. |
| Approach: | They propose a novel fine-tuning paradigm that allows the model to generate OCR text before producing translation text, which allows it to leverage its strong monolingual OCR ability while learning to translate text across languages. |
| Outcome: | The proposed model can leverage its strong monolingual OCR ability while learning to translate text across languages. |
Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)
Copied to clipboard
Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge. |
| Approach: | They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy. |
| Outcome: | The proposed model protects private data while enhancing the model's knowledge. |
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)
Copied to clipboard
Zijing Wang, YongKang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schuetze
| Challenge: | Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance. |
| Approach: | They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation. |
| Outcome: | The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs. |
MMSciCode: Real-world Evaluation of Multilingual Multi-Discipline Scientific Research Coding (2026.acl-long)
Copied to clipboard
| Challenge: | MMSciCode is a benchmark for evaluating foundation models in scientific code generation. |
| Approach: | They propose a multilingual, multi-discipline benchmark for evaluating foundation models in scientific code generation that integrates domain-specific knowledge with algorithmic reasoning. |
| Outcome: | The new benchmark is annotated by domain experts and features rigorous quality controls to ensure dataset integrity and authenticity. |
SportQA: A Benchmark for Sports Understanding in Large Language Models (2024.naacl-long)
Copied to clipboard
Haotian Xia, Zhengbang Yang, Yuqing Wang, Rhys Tracy, Yun Zhao, Dongdong Huang, Zezhi Chen, Yan Zhu, Yuan-fang Wang, Weining Shen
| Challenge: | SportQA is a benchmark specifically designed for evaluating Large Language Models (LLMs) sports knowledge is characterized by its fast pace, variety of types, abundance of strategies, and rich player narratives . |
| Approach: | They propose a benchmark specifically designed for evaluating Large Language Models in the context of sports understanding. |
| Outcome: | The proposed benchmark aims to bridge the gap between existing and specialized benchmarks in sports understanding. |
Towards Informative Open-ended Text Generation with Dynamic Knowledge Triples (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained language models (PLMs) have impressive capabilities in open-ended text generation. |
| Approach: | They propose a dynamic knowledge-guided informative open-ended text generation approach that utilizes a knowledge graph to help the model generate more contextually related entities and detailed facts. |
| Outcome: | The proposed approach generates more informative texts than baselines. |
Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph (2020.coling-main)
Copied to clipboard
| Challenge: | Existing studies rely on deep graph neural networks (GNNs) to capture rich structural information, but they lack the structural information needed for QA. |
| Approach: | They propose a framework which captures structural information from KBs and models long-distance node relations from two perspectives. |
| Outcome: | The proposed framework models long-distance node relations from two perspectives . it is based on two widely used multi-hop KBQA datasets . |
T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)
Copied to clipboard
Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li
| Challenge: | Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications. |
| Approach: | They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning. |
| Outcome: | The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation. |
Socratic Style Chain-of-Thoughts Help LLMs to be a Better Reasoner (2025.findings-acl)
Copied to clipboard
| Challenge: | Synthetic data generation is a promising approach to enhance reasoning capabilities of large language models. |
| Approach: | They propose a multi-agent debate framework based on the Socratic questioning strategy . they use socratic questions to deepen the thinking process and broaden it to motivate self-reflection . |
| Outcome: | The proposed framework outperforms existing methods on math and code generation tasks while maintaining affordable costs. |
Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA (2026.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge base question answering methods are limited by syntactic constraints and are prone to structural deviations that render queries unexecutable. |
| Approach: | They propose a framework that reframes semantic parsing as an iterative reasoning process driven by execution feedback. |
| Outcome: | The proposed method achieves significant improvements in query executability and answer accuracy on the WebQSP and CWQ datasets. |
“I Know Who You Are”: Character-Based Features for Conversational Humor Recognition in Chinese (2022.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study has focused on how to recognize punchlines from dialogues, but has neglected character information. |
| Approach: | They propose a character-fusion conversational humor recognition model that uses character information to recognize punchlines from dialogue. |
| Outcome: | The proposed model improves performance on Chinese sitcoms corpus and punchline identification. |
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. |
Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing knowledge enhancement techniques for pre-trained language models (PLMs) introduce noisy entity representations. |
| Approach: | They propose a knowledge enhancement filter that integrates external knowledge bases to enhance PLMs' ability to capture entity knowledge. |
| Outcome: | The proposed method achieves the highest F1-score and accuracy while reducing the computational cost by 1.7-2.5x. |
EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving (2026.findings-acl)
Copied to clipboard
Xiyuan Zhou, Xinlei Wang, Yirui He, Ruixi Zou, Yang Wu, Yuheng Cheng, Yulu Xie, Wenxuan Liu, Huan Zhao, Yan Xu, Jinjin Gu, Junhua Zhao
| Challenge: | Existing benchmarks focus on well-defined or abstract reasoning and fail to capture real-world engineering problems. |
| Approach: | They propose a hierarchical benchmark to evaluate large language models on engineering problems. |
| Outcome: | The proposed model performs well under well-defined conditions and is based on three levels of difficulty and covers diverse engineering subfields. |
UCS-SQL: Uniting Content and Structure for Enhanced Semantic Bridging In Text-to-SQL (2025.findings-acl)
Copied to clipboard
Zhenhe Wu, Zhongqiu Li, JieZhangChinaTele JieZhangChinaTele, Zhongjiang He, Jian Yang, Yu Zhao, Ruiyu Fang, Bing Wang, Hongyan Xie, Shuangyong Song, Zhoujun Li
| Challenge: | Existing methods overlook the challenge of effectively transforming structure information from NL to SQL. |
| Approach: | They propose a text-to-SQL framework that unites content and structure pipes to bridge the gap between NL and SQL. |
| Outcome: | The proposed framework bridges the gap between natural language questions and SQL by combining content and structure pipes. |
Scene-robust Natural Language Video Localization via Learning Domain-invariant Representations (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on improving performance with the assumption of independently identical data distribution while ignoring out-of-distribution data. |
| Approach: | They propose a scene-robust NLVL problem and a generalizable framework to learn a robust model. |
| Outcome: | The proposed model learns generalizable domain-invariant representations by alignment and decomposition. |
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (2024.findings-acl)
Copied to clipboard
Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Dongmei Zhang
| Challenge: | Existing approaches to compress prompts only leverage unidirectional context, causing suboptimal results. |
| Approach: | They propose a task-agnostic prompt compression method that takes tokens from context . they use a Transformer encoder to capture all essential information needed for prompt compression . |
| Outcome: | The proposed method is 3x-6x faster than existing prompt compression methods and faster than baselines. |
Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning (2026.acl-long)
Copied to clipboard
Junpeng Ding, Zichen Tang, Haihong E, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun, Yang Xu, Yichen Liu, Haocheng Gao, Zijie Xi, Ruomeng Jiang, Peizhi Zhao, Rongjin Li, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Jintong Chen, Siying Lin
| Challenge: | Xu and Peng, 2025) . . SPUR is a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. |
| Approach: | They propose to use 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images to evaluate the visual perception of multimodal large language models (MLLMs) . they also propose to utilize cross-panel relation understanding to evaluate MLLM’s ability to decipher intricate cross-panel relations. |
| Outcome: | The proposed model is based on 4,264 question-answering pairs derived from 1,084 expert-curated images. |
Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling (2025.acl-long)
Copied to clipboard
Yang Yuguang, Yu Pan, Jixun Yao, Xiang Zhang, Jianhao Ye, Hongbin Zhou, Lei Xie, Lei Ma, Jianjun Zhao
| Challenge: | Expressive zero-shot voice conversion (VC) aims to modify source timbre to match unseen speaker . existing zero- shot VC systems struggle to reproduce paralinguistic information in highly expressive speech . |
| Approach: | They propose a framework for expressive zero-shot voice conversion that uses hybrid content encoding and memory-augmented context-aware timbre modeling. |
| Outcome: | The proposed framework surpasses state-of-the-art VC systems in speech naturalness, speaker similarity, and speaker similarness. |
DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search (2026.acl-long)
Copied to clipboard
Zhibang Yang, Xinke Jiang, Rihong Qiu, Ruiqing Li, Yihang Zhang, Yue Fang, Yongxin Xu, Hongxin Ding, Xu Chu, Junfeng Zhao, Yasha Wang
| Challenge: | Existing methods for ambiguous queries struggle to retrieve high-quality documents . DFAMS outperforms advanced FR methods by 14.37% in knowledge classification accuracy . |
| Approach: | They propose a framework that leverages dynamic information flow to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources. |
| Outcome: | The proposed framework outperforms existing methods in classification accuracy and retrieval recall tests. |
Self-Evaluation of Large Language Model based on Glass-box Features (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation methods rely on external evaluators, focusing on training and prompting strategies, but model-aware glass-box features are overlooked. |
| Approach: | They propose to use model-aware glass-box features to evaluate an LLM's output. |
| Outcome: | The proposed model-aware features are reliable quality indicators for self-evaluation on public benchmarks. |
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reward models rely on scalar or pairwise judgments that fail to capture multifaceted nature of human preferences. |
| Approach: | They propose a rubric-based reward model that uses a large collection of prompt, rubric pairs to generate a scalar score or preference label for each response. |
| Outcome: | The proposed model surpasses strong size-matched baselines by 8.4% across multiple benchmarks. |
PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan
| Challenge: | Quantization is a viable solution for pre-trained language models, but most existing methods are task-specific and require customized training and quantization with a large number of trainable parameters. |
| Approach: | They propose a "quantize before fine-tuning" framework that allows for quantization with a large number of trainable parameters on each individual task. |
| Outcome: | The proposed framework is compatible with quantization-aware training and post-training quantization and corrects quantization errors. |
GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models generate human-like content, but they also pose a problem with generation diversity, negatively impacting generation diversity and user experience. |
| Approach: | They propose a Logits-Addition watermark and three variants that aim to enhance diversity to overcome generation diversity challenges. |
| Outcome: | The Logits-Addition watermark outperforms the Logits+Trick-based watermark in diversity tests and outperformed other decoding-based methods by 0.1 to 0.3. |
Towards Noise-Tolerant Speech-Referring Video Object Segmentation: Bridging Speech and Text (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in vision-language learning have significantly advanced Human-Computer Interactions (HCI). |
| Approach: | They propose a method to align the semantic spaces between speech and text by incorporating two modules to align semantic spaces. |
| Outcome: | The proposed method outperforms state-of-the-art approaches on AVOS benchmarks. |
3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding (2023.emnlp-main)
Copied to clipboard
| Challenge: | 3D visual grounding aims to localize the desired objects in a 3D point cloud by a free-form language description. |
| Approach: | They propose a relation-aware framework which captures relative spatial relationships between objects and enhances object attributes. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on three benchmarks . it captures relative spatial relationships between objects and enhances object attributes . |
Permutative Preference Alignment from Listwise Ranking of Human Judgments (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to align Large Language Models with human preferences are based on the Bradley-Terry model, but when multiple responses are available, the B-T model fails to guarantee an accurate list ranking of the responses. |
| Approach: | They propose an offline listwise approach that incorporates the Normalized Discounted Cumulative Gain (NDCG) as an alternative training objective for LLM alignment. |
| Outcome: | The proposed approach outperforms existing pairwise and listwise methods on evaluation sets and general benchmarks such as AlpacaEval. |
LESA: Learnable LLM Layer Scaling-Up (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for depth scaling-up rely on empirical heuristic rules for layer duplication, resulting in poor initialization and slower convergence during continual pre-training. |
| Approach: | They propose a method for learning latent parameters between layers by concatenating parameters from each layer and applying Singular Value Decomposition. |
| Outcome: | Experiments show that LESA outperforms baseline models with less than half the cost of existing methods. |
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal embedding models encode multimedia inputs into latent vector representations. |
| Approach: | They propose to synthesize multimodal multilingual data using a multimodal large language model . they identify three criteria for high-quality synthetic multimodal data . |
| Outcome: | The proposed model outperforms existing models on the MMEB Benchmark and the XTD benchmark. |
Neural Document Summarization by Jointly Learning to Score and Select Sentences (P18-1)
Copied to clipboard
| Challenge: | Sentence scoring and sentence selection are two main steps in extractive document summarization systems. |
| Approach: | They propose an end-to-end neural network framework for extractive document summarization by jointly learning to score and select sentences. |
| Outcome: | The proposed framework outperforms the state-of-the-art summarization models on the CNN/Daily Mail dataset. |
Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to train low-latency multilayer perceptrons (MLPs) on graph tasks are based on graph nodes and lack graph structural information. |
| Approach: | They propose to distill graph structural information from Graph Neural Networks (GNNs) to low-latency multilayer perceptrons (MLPs) on graph tasks. |
| Outcome: | The proposed method does not require graph edges (edge-free setting) yet learns structure-aware MLPs. |
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)
Copied to clipboard
Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Zhou Xiao, Yang Yu, Jie Zhou
| Challenge: | Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications. |
| Approach: | They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts. |
| Outcome: | The proposed model outperforms existing models and improves on annotated documents. |
Entity Concept-enhanced Few-shot Relation Extraction (2021.acl-short)
Copied to clipboard
| Challenge: | Existing FSRE methods fail to classify relations based on information of sentences and entity pairs due to limited samples and lack of knowledge. |
| Approach: | They propose a concept-sentence attention module to select the most appropriate concept from multiple concepts of each entity by calculating the semantic similarity between sentences and concepts. |
| Outcome: | The proposed scheme outperforms existing methods on a few-shot relation extraction dataset. |
From Chaotic OCR Words to Coherent Document: A Fine-to-Coarse Zoom-Out Network for Complex-Layout Document Image Translation (2025.coling-main)
Copied to clipboard
| Challenge: | Document Image Translation (DIT) aims to translate documents in images from one language to another. |
| Approach: | They propose a novel end-to-end network called Zoom-out DIT to improve document translation by combining word positioning, sentence recognition and document organization. |
| Outcome: | The proposed network improves word positioning, sentence recognition and document organization, and improves translation quality. |
AdaptFlow: Adaptive Workflow Optimization via Meta-Learning (2025.findings-emnlp)
Copied to clipboard
Runchuan Zhu, Bowen Jiang, Lingrui Mei, Fangkai Yang, Lu Wang, Haoxiang Gao, Fengshuo Bai, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing approaches to large language models rely on static templates or manual workflows. |
| Approach: | AdaptFlow is a language-based meta-learning framework inspired by model-agnostic meta- learning. |
| Outcome: | AdaptFlow outperforms manual and automated workflows on question answering, code generation and mathematical reasoning benchmarks. |
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs (2026.findings-acl)
Copied to clipboard
Ru Peng, Tianyu Zhao, Xijun Gu, Zhiting Fan, Haokai Xu, Jinyang Zhang, Yawen Zeng, Yihong Zhuang, Kexin Yang, Junyang Lin, Dayiheng Liu, Junbo Zhao
| Challenge: | High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. |
| Approach: | They define the first HSS domain system covering 14 mainstream fields and introduce HSS-Synth. |
| Outcome: | the proposed pipeline outperforms 14 leading baselines on 16 benchmarks. |
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. |
MultiAgentESC: A LLM-based Multi-Agent Collaboration Framework for Emotional Support Conversation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on generating responses directly and neglect integration of domain-specific reasoning and expert interaction. |
| Approach: | They propose a training-free multi-agent collaboration framework for ESC to emulate human-like process of providing emotional support through dialogue analysis, strategy deliberation, and response generation. |
| Outcome: | The proposed framework excels at providing emotional support and diversifying support strategy selection. |
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. |
Learning Relation Alignment for Calibrated Cross-modal Retrieval (2021.acl-long)
Copied to clipboard
| Challenge: | despite advances in multimodal pre-training, cross-modal retrieval remains challenging . lack of relation consistency impairs contextualized representation of image-text pairs . |
| Approach: | They propose a new metric to quantify the relation consistency by measuring the semantic distance between linguistic and visual relations. |
| Outcome: | The proposed method boosts the performance of prevailing models on Flickr30k and MS COCO datasets by a considerable margin. |
Large Language Models Are Still Misled by Simple Bias Ensembles (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for large language models are constrained to datasets where each sample is manually injected with only one type of bias. |
| Approach: | They propose a multi-bias benchmark where each sample contains multiple types of biases. |
| Outcome: | The proposed benchmark shows that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating compounded biases. |
A Corpus of Adpositional Supersenses for Mandarin Chinese (2020.lrec-1)
Copied to clipboard
| Challenge: | Adpositions are frequent markers of semantic relations, but they are highly ambiguous and vary significantly from language to language. |
| Approach: | They propose to annotate Chinese adpositions in a corpus with all aforementioned supersenses . they adapt a framework that defined a set of supersens according to ostensibly language-independent criteria . |
| Outcome: | The proposed corpus is the first to be broadly annotated with adposition semantics in Chinese . it shows that the supersense categories are well-suited to Chinese adepositions despite syntactic differences from English . |
Stance Detection on Social Media with Background Knowledge (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies of stance detection focus on learning stance information about specific targets from context, but in real-world scenarios, we usually have a certain understanding of a target when we express our stance on it. |
| Approach: | They propose to take the background knowledge of the target into account for better stance detection by categorizing it into episodic and discourse knowledge categories and a heuristic retrieval algorithm based on the topic to retrieve the Wikipedia documents relevant to the sample. |
| Outcome: | The proposed framework achieves state-of-the-art on four benchmark datasets showing that the proposed framework is able to detect stances in-target and zero-shot scenarios. |
Self-supervised Rewiring of Pre-trained Speech Encoders:
Towards Faster Fine-tuning with Less Labels in Speech Processing (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained speech encoders have facilitated great success across various speech processing tasks, but fine-tuning them for downstream tasks requires large training data to converge or to achieve state-of-the-art. |
| Approach: | They propose to rewire pre-trained speech encoders to improve their representation space without task-specific labels by neutrally synthesising audio inputs and frame masking. |
| Outcome: | The proposed model shows consistent improvement in isotropy in the representation space on 6 speech processing tasks. |
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)
Copied to clipboard
Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao
| Challenge: | Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios. |
| Approach: | They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions. |
| Outcome: | The proposed framework improves generalization and realism of large language models under complex and irregular table conditions. |
Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure (2025.acl-short)
Copied to clipboard
| Challenge: | TestCase-Eval focuses on Fault Coverage and Fault Exposure tasks . authors provide insights into their strengths and limitations in generating effective test cases . correctness and robustness of algorithmic solutions hinge on quality of test suites . |
| Approach: | They introduce TestCase-Eval, a benchmark for systematic evaluation of LLMs in test-case generation. |
| Outcome: | The new benchmark measures the performance of LLMs in test-case generation. |
Weight-Inherited Distillation for Task-Agnostic BERT Compression (2024.findings-naacl)
Copied to clipboard
| Challenge: | Knowledge Distillation (KD) is a predominant approach for BERT compression. |
| Approach: | They propose a weight-inherited distillation method which directly transfers knowledge from the teacher to a compact student model by inheriting the weights. |
| Outcome: | The proposed method outperforms state-of-the-art KD-based methods on GLUE and SQUAD benchmarks. |
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance (D19-1)
Copied to clipboard
| Challenge: | Existing evaluation metrics are not capable of evaluating text quality. |
| Approach: | They propose a metric that compares system output against reference texts based on semantics rather than surface forms. |
| Outcome: | The proposed metric shows a high correlation with human judgment of text quality on a number of text generation tasks. |
Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)
Copied to clipboard
Lei Huang, Xiaocheng Feng, Weitao Ma, Liang Zhao, Yuchun Fan, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin
| Challenge: | Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive. |
| Approach: | They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources. |
| Outcome: | Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources. |
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have sparked concerns about their safety. |
| Approach: | They propose a method to identify safety-related information in the model parameter space . they propose to use a few adversarially chosen examples to fine-tune LLMs . |
| Outcome: | The proposed method can break safety alignment in multilingual LLMs using a few examples . it also shows that the proposed method jailbreaks LLM models adapted to new languages . |
M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)
Copied to clipboard
Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng
| Challenge: | Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities . |
| Approach: | They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models. |
| Outcome: | The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree. |
Watermarking with Low-Entropy POS-Guided Token Partitioning and Z-Score-Driven Dynamic Bias for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing watermarking methods reduce the fidelity of semantics in LLMs . |
| Approach: | They propose a low-entropy token partitioning mechanism and z-score-driven dynamic bias mechanism to enhance semantics. |
| Outcome: | The proposed framework improves semantic fidelity and robustness against bias sparsity attacks. |
Task Compass: Scaling Multi-task Pre-training with Task Prefix (2022.findings-emnlp)
Copied to clipboard
Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng
| Challenge: | Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. |
| Approach: | They propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. |
| Outcome: | The proposed model can be used as a foundation backbone for a wide range of tasks and as augmentation tool for data augmentation with complementary tasks. |
M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge editing methods for MLLMs lack multi-granularity knowledge . existing knowledge editing approaches lack multimodality knowledge and generalize to multimodal data. |
| Approach: | They propose a multimodal knowledge editing method which integrates key knowledge layers within MLLMs and collaboratively edits them. |
| Outcome: | The proposed method improves visual generality performance on knowledge data of different granularities. |
UNIVID: Unified Vision-Language Model for Video Moderation (2026.acl-industry)
Copied to clipboard
Kejuan Yang, Yizhuo Zhang, Mingyuan Du, Yue Zhang, Dixin Zheng, Kaili Zhao, Yang Xiao, Hanzhong Liang, Kenan Xiao
| Challenge: | Existing video moderation systems rely on fragmented black-box classification models that are difficult to maintain and lack transparency. |
| Approach: | They propose a Unified Vision-Language model for Video Moderation that generates policy-aware captions that serve as an interpretable intermediate representation. |
| Outcome: | The proposed model reduces violation leakage and overkill rate by 42.7% while reducing maintenance costs. |
Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for large language models adopt query-driven iterative reasoning from a local perspective, limiting efficiency and accuracy for complex multi-hop tasks. |
| Approach: | They propose a multi-view instructed adaptive reasoning of LLM on Knowledge Graphs that allows LLMs to plan, evaluate, and adapt reasoning paths from a global perspective. |
| Outcome: | The proposed model overcomes the limitations of local exploration by enabling LLMs to plan, evaluate, and adapt reasoning paths from a global perspective. |
Advancing E-commerce Merchants Telemarketing with Synthetic Data-Driven LLMs (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are proving broadly applicable across diverse industries, including e-commerce. |
| Approach: | They propose a hybrid data synthesis framework that unifies the input schema with profile and strategy designed by top sales and extracts them via a Multi-task paradigm. |
| Outcome: | The proposed model reaches the performance level of the top 25% of human sales in terms of the final marketing results. |
Data-Efficiently Learn Large Language Model for Universal 3D Scene Perception (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for 3D scene understanding are limited to specific downstream tasks, hindering their practicality in real-world applications. |
| Approach: | They propose a 3D visual perceptual ability and advanced reasoning capabilities for 3D scenes by aligning 3D representations into the feature space of advanced LLMs. |
| Outcome: | The proposed system achieves a 82.2% relative score compared with state-of-the-art methods with limited data. |
More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored. |
| Approach: | They conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning under a unified pipeline designed to mirror training and deployment scenarios. |
| Outcome: | The proposed pipelines mirror training and deployment scenarios and are suitable for industrial applications. |
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code. |
| Approach: | They propose a structure-aware method that breaks large AST nodes into smaller chunks . this method generates self-contained, semantically coherent units across programming languages . |
| Outcome: | The proposed method boosts Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation. |
EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)
Copied to clipboard
Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Yong Liao
| Challenge: | Existing knowledge evolution benchmarks are static and fail to capture the evolving nature of LLMs and knowledge. |
| Approach: | They propose an evolving dataset that categorizes information into stable, evolved, and uncharted states. |
| Outcome: | The proposed dataset is auto-updatable and enables evaluation of continuously changing knowledge and newly released LLMs. |
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for steering concept vectors suffer from noisy features in diverse datasets that undermine steering robustness. |
| Approach: | They propose a Sparse Autoencoder-Denoised Concept Vector (SDCV) which selectively keeps the most discriminative SAE latents while reconstructing hidden representations. |
| Outcome: | The proposed method improves steering success rates by 4-16% across six challenging concepts while maintaining topic relevance. |
Are LLMs Aware that Some Questions are not Open-ended? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown impressive capability to answer questions in a wide range of scenarios. |
| Approach: | They propose a method that enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features. |
| Outcome: | The proposed method improves the question awareness of LLMs by adaptively adjusting the output distributions based on question features. |
Benchmarking LLMs for Translating Classical Chinese Poetry: Evaluating Adequacy, Fluency, and Elegance (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing large language models fall short of translating culturally significant content . existing models fall behind in achieving such translations, authors say . |
| Approach: | They propose a suitable benchmark for translating classical Chinese poetry into English . they propose RAT, a retrieval-augmented machine translation method that enhances the translation process . |
| Outcome: | The proposed method improves translation quality in terms of adequate, fluent, and elegant translations. |
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback (2026.acl-long)
Copied to clipboard
Taiwei Shi, Zhuoer Wang, Longqi Yang, Ying-Chun Lin, Zexue He, Mengting Wan, Pei Zhou, Sujay Kumar Jauhar, Sihao Chen, Shan Xia, Hongfei Zhang, Jieyu Zhao, Xiaofeng Xu, Xia Song, Jennifer Neville
| Challenge: | Traditional alignment methods rely on human annotations and are subjective and misalignment with real-world user preferences. |
| Approach: | They propose a framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically. |
| Outcome: | The proposed framework identifies and classifies user feedback to LLM responses between conversation turns and creates examples of preferred and dispreferred responses according to user preferences. |
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)
Copied to clipboard
Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang
| Challenge: | Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows . |
| Approach: | They propose a repository-level evaluation benchmark to assess security of AI-generated code. |
| Outcome: | The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation. |
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering (2023.emnlp-industry)
Copied to clipboard
Fangkai Yang, Pu Zhao, Zezhong Wang, Lu Wang, Bo Qiao, Jue Zhang, Mohit Garg, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Large Language Models (LLMs) have gained popularity but lack specific domain knowledge in domain-specific tasks. |
| Approach: | They propose a model interaction paradigm that empowers LLM to achieve better performance on domain-specific tasks where it is not proficient. |
| Outcome: | The proposed approach outperforms the commonly used LLM with retrieval methods in domain-specific tasks. |
CDAˆ2: Counterfactual Diffusion Augmentation for Cross-Domain Adaptation in Low-Resource Sentiment Analysis (2025.coling-main)
Copied to clipboard
| Challenge: | Domain adaptation is widely employed in cross-domain sentiment analysis, but concerns have been raised regarding their robustness and sensitivity to data distribution shift. |
| Approach: | They propose a framework CDA2 for cross-domain adaptation in low-resource sentiment analysis which employs counterfactual diffusion augmentation. |
| Outcome: | The proposed framework generates high-quality counterfactual target samples and achieves state-of-the-art performance on benchmark datasets. |
Logic Traps in Evaluating Attribution Scores (2022.acl-long)
Copied to clipboard
| Challenge: | Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. |
| Approach: | They propose to review existing methods for evaluating attribution scores and summarize the logic traps in these methods. |
| Outcome: | The proposed methods show that they do not contain logic traps and that they are not reliable. |
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)
Copied to clipboard
Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Zhaoxin Fan, Bo Tang, Jihao Zhao, Jiawei Yang, Shichao Song, Mengwei Wang
| Challenge: | Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs . |
| Approach: | They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service . |
| Outcome: | The proposed benchmark evaluates the security of RAG against 14 representative RAG components. |
Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive performance across numerous NLP tasks, but fine-tuning them for Machine Translation (MT) often introduces catastrophic forgetting, compromising the broad general abilities of LLMs and introducing potential security risks. |
| Approach: | They propose a method that harnesses the strong generative capabilities of Large Language Models to create rationales for training data, which are then "replayed" to prevent forgetting. |
| Outcome: | The proposed approach harnesses the strong generative capabilities of LLMs to create rationales for training data, which are then “replayed” to prevent forgetting. |
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL (2025.coling-main)
Copied to clipboard
Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li
| Challenge: | Recent LLM-based Text-to-SQL methods suffer from performance degradation on “huge” databases and complex user questions that require multi-step reasoning. |
| Approach: | They propose a framework that integrates a decomposer agent and auxiliary agents to generate SQL queries from natural language text. |
| Outcome: | The proposed framework achieves comparable execution accuracy on SQL-Llama tasks compared to the baseline model. |
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)
Copied to clipboard
Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong
| Challenge: | Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. |
| Approach: | They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs. |
| Outcome: | The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks. |
RefGPT: Dialogue Generation of GPT, by GPT, and for GPT (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data. |
| Approach: | They propose a method to generate huge truthful and customized dialogues without worrying about factual errors caused by the model hallucination. |
| Outcome: | The proposed method solves the model hallucination in dialogue generation by restricting the LLMs to leverage the given reference instead of reciting their own knowledge to generate dialogues. |
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. |
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Xiaolong Wei, Zerun Zhu, Simin Niu, Xingyu Zhang, Peiying Yu, Changxuan Xiao, Yuchen Li, Jicheng Yang, Zhejun Zhao, Chong Meng, Long Xia, Daiting Shi
| Challenge: | Existing alignment paradigms for creative writing use static reward signals and supervised data. |
| Approach: | They propose a constraint-aware reward model that synthesizes query-specific criteria to provide fine-grained preference judgments. |
| Outcome: | The proposed framework aligns models with human preferences across content quality and structural paradigms without supervised fine-tuning and ground-truth references. |
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation (2026.findings-acl)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood. |
| Approach: | They reversely traced information flow across decoding, projection, and activation phases and found that CoT may serve as a decoding space pruner . |
| Outcome: | The proposed framework can be used to design more efficient and robust prompts. |
ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models (2022.naacl-main)
Copied to clipboard
Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Zhipeng Chen, Jingyuan Wang, Xin Zhao, Ji-Rong Wen
| Challenge: | Recent years have featured a trend towards Transformer based pretrained language models (PLMs) in natural language processing systems. |
| Approach: | They propose to use four evaluation dimensions to evaluate ten widely-used PLMs . they find that pretrained language models are good at different ability tests . |
| Outcome: | The results show that pretrained language models are good at different ability tests and have excellent transferability between tasks. |
Navigating the OverKill in Large Language Models (2024.acl-long)
Copied to clipboard
Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin
| Challenge: | Recent studies have highlighted a tendency among large language models to refuse to answer benign queries. |
| Approach: | They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding. |
| Outcome: | The proposed approach reduces the refusal rate by 20% while having little impact on safety. |
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)
Copied to clipboard
Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen
| Challenge: | Existing open-source multi-modal large language models (MLLMs) focus on enhancing foundational capabilities, leaving a significant gap in human preference alignment. |
| Approach: | They propose a dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs’ alignment with human preferences. |
| Outcome: | The proposed dataset of 200K high-quality training samples improves human preference alignment while maintaining or enhancing performance on standard VQA benchmarks. |
DR-Arena: an Automated Evaluation Framework for Deep Research Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for evaluating deep research capabilities rely on static datasets. |
| Approach: | They propose a fully automated evaluation framework that pushes DR agents to their capability limits through dynamic investigation. |
| Outcome: | DR-Arena achieves a Spearman correlation of 0.94 with the LMSYS Search Arena leaderboard. |
KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)
Copied to clipboard
Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng Li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu
| Challenge: | Recent advances in pre-trained language models have made it possible to generate human-like text. |
| Approach: | They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached. |
| Outcome: | The proposed game lacks incentives and relies on players to explore on their own. |
LDEDE: LRP-Driven Efficient Detection and Editing Framework for LLM Privacy Neurons (2026.findings-acl)
Copied to clipboard
Zhao Zhengyuan, Cao Lifeng, null Sunhaodong, Shi Haotian, Du Xuehui, Liu Aodi, Niu Lanjie, Yang Xiaocheng
| Challenge: | Existing privacy protection methods fail to cover context-dependent sensitive information and are prone to performance degradation. |
| Approach: | They propose a Layer-wise Relevance Propagation-driven framework for efficient privacy neuron detection and editing. |
| Outcome: | The proposed framework achieves 80% higher efficiency than gradient attribution methods while reducing leakage risks of Phone, Email, and medical privacy by 42.7%–73.5% on average and cutting computational time by 60%–90%. |
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. |
SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)
Copied to clipboard
Hui Wang, Jinghua Zhao, Yifan Yang, Shujie Liu, Junyang Chen, Yanzhe Zhang, Shiwan Zhao, Jinyu Li, Jiaming Zhou, Haoqin Sun, Yan Lu, Yong Qin
| Challenge: | Existing methods for evaluating the perceptual quality of synthetic speech are limited due to the complexity of perceptual quality factors and the diversity of speech generation tasks. |
| Approach: | They propose a new paradigm for enabling large language models to conduct structured speech quality evaluation using a large-scale dataset. |
| Outcome: | The proposed model performs well across tasks and languages. |
Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods that confuse tool utilization with knowledge reasoning harm readability and give rise to tool invocation hallucinations. |
| Approach: | They propose to decouple LLM from tool invocation tasks by establishing a memory module with explicit descriptions of query statements and a query memory module to facilitate the KGQA process. |
| Outcome: | The proposed method achieves state-of-the-art on WebQSP and CWQ benchmarks. |
Representative Demonstration Selection for In-Context Learning with Two-Stage Determinantal Point Process (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods tend to select different demonstrations for each test instance, which is time-consuming and poses limitations in practical scenarios. |
| Approach: | They propose to select a representative subset of in-context demonstrations that can prompt different test instances in a specific task. |
| Outcome: | The proposed method can be used to generate representative in-context demonstrations. |
RLShield: Dynamic Jailbreak Detection for LLMs via Reinforced Adaptive Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to detect jailbreak prompts rely on static model components or fixed decision thresholds. |
| Approach: | They propose a dynamic jailbreak detection framework that employs reinforcement learning for adaptive threshold selection. |
| Outcome: | Experimental results show that the framework outperforms baselines in detection performance while maintaining high computational efficiency. |
Multimodal Machine Translation with Text-Image In-depth Questioning (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal machine translation (MMT) models focus on intermodal interactions, but focus on simple interactions between nouns and entities in image, overlooking global semantic alignment. |
| Approach: | They propose a Text-Image In-depth Questioning method to deepen interactions and optimize translations by utilizing visual data to capture global semantic alignment. |
| Outcome: | The proposed method achieves state-of-the-art results on five translation directions of Multi30K and AmbigCaps, with +2.35 BLEU on the challenging MSCOCO benchmark. |
Steering LLM Thinking with Budget Guidance (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing budget control methods for large language models are inadequate for long reasoning . budget guidance can be used to control reasoning length without fine-tuning . |
| Approach: | They propose a budget guidance method that models a Gamma distribution over remaining thinking length during next-token generation and uses it to guide generation in a soft, token-level manner. |
| Outcome: | The proposed method achieves up to 26% accuracy gain on the MATH-500 benchmark compared to baseline methods while maintaining competitive accuracy with only 63% of the thinking tokens used by the full-thinking model. |
A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | a recent study shows that large language models are biased to their pre-training data, leading to poor performance in prompt templates. |
| Approach: | They propose a domain-agnostic data construction method to de-bias a given prompt template . they show that domain-based generic responses are superior to in-domain ground-truth data . |
| Outcome: | The proposed method improves sentiment analysis tasks across domains and domains . it also yields better performance than existing in-domain models . |