Papers by Hao Huang
Snapshot-Guided Domain Adaptation for ELECTRA (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain-specific knowledge of domain-related tasks is lacking in pre-trained language models. |
| Approach: | They propose a domain-adaptation method which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters. |
| Outcome: | The proposed method can capture domain-specific knowledge of domain-related tasks without introducing new training parameters. |
Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for code retrieval struggle to balance scalability and annotation quality. |
| Approach: | They propose a method that integrates functions called within the repository and information on third-party APIs to enhance the annotation context. |
| Outcome: | The proposed method improves the annotation context by incorporating functions called within the repository and information on third-party API functionalities. |
Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. |
| Approach: | They propose to apply world knowledge to enhance OOD detection performance through selective generation from large language models (LLMs) they propose to extract visual objects from each image to fully capitalize on the aforementioned world knowledge. |
| Outcome: | The proposed method outperforms the state-of-the-art on visual OOD detection on in-distribution (ID) samples. |
Argumentation Mining on Essays at Multi Scales (2020.coling-main)
Copied to clipboard
| Challenge: | Argumentation mining on essays is a new task in natural language processing. |
| Approach: | They propose a multi-scale argumentation mining model which aims to identify the types and locations of argumentation components from essay text. |
| Outcome: | The proposed model outperforms existing models on mining all types of argumentation components on the Persuasive Essay dataset. |
An Effective Span-based Multimodal Named Entity Recognition with Consistent Cross-Modal Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to name entity recognition rely on word-based sequence labeling and align image and text at inconsistent semantic levels. |
| Approach: | They propose a span-based method which achieves a more consistent multimodal alignment from the perspectives of information-theoretic and cross-modal interaction. |
| Outcome: | Experiments on two datasets show that SMNER outperforms the state-of-the-art methods. |
Conversation Disentanglement with Bi-Level Contrastive Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on pairwise utterance relations but pay inadequate attention to utterant-to-context relation modeling. |
| Approach: | They propose a general disentangle model based on bi-level contrastive learning that brings closer utterances in the same session while encouraging each utterrance to be near its clustered session prototypes in representation space. |
| Outcome: | The proposed model achieves state-of-the-art performance on both settings across public datasets. |
Code Representation Pre-training with Complements from Program Executions (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing languages have syntactic representations of code to improve code intelligence, but they are difficult to learn from code. |
| Approach: | They propose to embed dynamic information of programs revealed by their test cases into feature representations of code as complements. |
| Outcome: | The proposed method yields 6%/19% mAP improvements over its masked language modeling counterparts. |
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. |
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts (2025.acl-long)
Copied to clipboard
Ziwei Huang, Wanggui He, Quanyu Long, Yandi Wang, Haoyuan Li, Zhelun Yu, Fangxun Shu, Weilong Dai, Hao Jiang, Fei Wu, Leilei Gan
| Challenge: | Existing studies on text-to-image (T2I) models focus on text alignment, image quality, and object composition capabilities. |
| Approach: | They propose a T2I-FactualBench benchmark to evaluate the factuality of knowledge-intensive concept generation. |
| Outcome: | The proposed framework evaluates the factuality of knowledge-intensive concept generation tasks. |
Align2LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation (2025.findings-acl)
Copied to clipboard
Hongzhe Huang, Jiang Liu, Zhewen Yu, Li Cai, Dian Jiao, Wenqiao Zhang, Siliang Tang, Juncheng Li, Hao Jiang, Haoyuan Li, Yueting Zhuang
| Challenge: | Recent advances in Multi-modal Large Language Models (MLLMs) introduce significant variability in data quality. |
| Approach: | They propose to use human and LLM preference alignment to compress large corpus of machine-generated multimodal instructions into a compact and high-quality form. |
| Outcome: | The proposed algorithm outperforms LLaVA-series models in MLLM benchmarks by 90% . it uses human and LLM preference alignment to compress a large dataset . |
Correctable-DST: Mitigating Historical Context Mismatch between Training and Inference for Improved Dialogue State Tracking (2022.emnlp-main)
Copied to clipboard
Hongyan Xie, Haoxiang Su, Shuangyong Song, Hao Huang, Bo Zou, Kun Deng, Jianghua Lin, Zhihui Zhang, Xiaodong He
| Challenge: | Existing dialogue state tracking approaches predict the dialogue state of a target turn sequentially based on the ground-truth previous dialogue state. |
| Approach: | They propose a method that predicts dialogue state sequentially based on previous dialogue state . they propose generating a previously “predicted” dialogue state using ground-truth previous dialogue states . |
| Outcome: | The proposed method achieves 67.51%, 68.24%, 70.30%, 71.38%, and 81.27% joint goal accuracy on MultiWOZ 2.0-2.4 datasets. |
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline (2022.naacl-main)
Copied to clipboard
Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
| Challenge: | Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability. |
| Approach: | They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks. |
| Outcome: | The proposed model outperforms or performs on par with SOTA compressed and early exiting models. |
TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Long-context Document Visual Question Answering (DocVQA) methods struggle with visual semantics or handling finite context windows. |
| Approach: | They propose a new approach to longcontext document visual question answering that transforms retrieval into adaptive evidence chain construction using a Bi-Layered Graph. |
| Outcome: | The proposed approach achieves an average accuracy improvement of 14.07% on M5BookVQA and exhibits robust generalization with a 13.38% gain across four established benchmarks. |
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors (2024.findings-emnlp)
Copied to clipboard
Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang
| Challenge: | Existing tools for detecting safety issues in LLMs are expensive and inefficient. |
| Approach: | They propose an LLM-based safety detector which annotates the safety of queries and provides explanations for its decisions. |
| Outcome: | The proposed detector outperforms baselines on four sets of query-response pairs and is effective as a safety evaluator for advanced LLMs. |
Knowledge-enhanced Prompt Tuning for Dialogue-based Relation Extraction with Trigger and Label Semantic (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to determine semantic relation between two arguments in dialogues are limited due to the low information density of text. |
| Approach: | They propose a Knowledge-Enhanced Prompt-Tuning method to enhance DRE model by exploiting trigger and label semantics. |
| Outcome: | The proposed method achieves state-of-the-art in F1 and F1c scores on a DialogRE dataset. |
R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference (2022.emnlp-main)
Copied to clipboard
| Challenge: | Document-level natural language inference (DOCNLI) is a new task in natural language processing. |
| Approach: | They propose a document-level natural language inference framework that fuses sentence-level tasks into a set of sentence-based tasks. |
| Outcome: | The proposed framework improves interpretability and performance with evidence. |
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)
Copied to clipboard
Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang
| Challenge: | Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand. |
| Approach: | They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages. |
| Outcome: | Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages. |
DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling (2025.emnlp-main)
Copied to clipboard
Hao Sun, Zile Qiao, Bo Wang, Guoxin Chen, Yingyan Hou, Yong Jiang, Pengjun Xie, Fei Huang, Yan Zhang
| Challenge: | Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs). |
| Approach: | They propose a framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. |
| Outcome: | The proposed framework decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. |
InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing safety detection systems have limitations in terms of their versatility and interpretability. |
| Approach: | They introduce a safety detection framework that unifies 7 common sub-tasks into a uniform formulation and process 39 human-annotated datasets for instruction tuning. |
| Outcome: | The proposed framework unifies 7 common sub-tasks into a uniform formulation and then runs on 39 human-annotated datasets to fine-tune it. |
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning (2025.emnlp-main)
Copied to clipboard
Yu Sun, Xingyu Qian, Weiwen Xu, Hao Zhang, Chenghao Xiao, Long Li, Deli Zhao, Wenbing Huang, Tingyang Xu, Qifeng Bai, Yu Rong
| Challenge: | Existing medical reasoning datasets are limited in scale and typically rely on incomplete data. |
| Approach: | They propose to use ReasonMed to train medical reasoning models using a multi-agent generation, verification, and refinement pipeline. |
| Outcome: | The largest medical reasoning dataset to date surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%. |
Generating Sentences from Disentangled Syntactic and Semantic Spaces (P19-1)
Copied to clipboard
| Challenge: | Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. |
| Approach: | They propose to generate sentences from disentangled syntactic and semantic spaces by using the linearized tree sequence. |
| Outcome: | The proposed method achieves similar or better performance in various tasks compared with state-of-the-art models. |
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)
Copied to clipboard
Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang
| Challenge: | Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool. |
| Approach: | They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images . |
| Outcome: | The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images. |
Fine-Tuning Language Models with Reward Learning on Policy (2024.naacl-long)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is an effective approach to align large language models (LLMs) to human preferences. |
| Approach: | They propose a framework that refines a reward model using policy samples to keep it on-distribution. |
| Outcome: | The proposed framework outperforms the state-of-the-art on three benchmark datasets showing that it can learn robust representations of policy samples. |
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. |
| Approach: | They propose an unsupervised reference-free metric which evaluates controlled text generation from different aspects by formulating each aspect into multiple text infilling tasks. |
| Outcome: | The proposed metric has higher correlations with human judgments while obtaining better generalization of evaluating generated texts from different models and with different qualities. |
EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge-grounded conversation models lack knowledge that occurs in training data, resulting in incomplete knowledge generation. |
| Approach: | They propose an Entity-Agnostic Representation Learning method to introduce knowledge graphs to informative conversation generation using context of conversations and relational structure of knowledge graph. |
| Outcome: | The proposed model generates more informative, coherent, and natural responses than baseline models. |
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs (2025.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Sun Ao, Hao Zhou, Jie Zhou, Zhiyuan Liu, Maosong Sun
| Challenge: | Long-context inference is crucial for advancing large language models, but its prefill speed remains a bottleneck. |
| Approach: | They propose an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed. |
| Outcome: | The proposed framework achieves speedups of 9.2, 4.2, and 1.6 without any degradation in performance. |
Se2: Sequential Example Selection for In-Context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Prior work has explored the selection of examples for in-context learning, neglecting the internal relationships between examples and exist an inconsistency between training and inference. |
| Approach: | They propose a sequential-aware method that leverages the LLM’s feedback on varying context, aiding in capturing inter-relationships and sequential information among examples. |
| Outcome: | Experiments on 23 NLP tasks show that Se2 surpasses baselines and achieves 42% relative improvement over random selection. |
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)
Copied to clipboard
Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun
| Challenge: | Existing benchmarks focus on character-centric approach and fail to reflect real-world applications. |
| Approach: | RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds. |
| Outcome: | RMTBench features 80 diverse characters and over 8,000 dialogue rounds. |
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. |
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)
Copied to clipboard
Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang
| Challenge: | Simultaneous translation is notoriously dif- ficult due to word-order differences. |
| Approach: | They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model. |
| Outcome: | The proposed framework achieves low latency and reasonable qual- ity on 4 directions. |
Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to detect toxic generation of pretrained language models rely on templates, data extraction, crowdsourcing workers or automatic generation. |
| Approach: | They propose a method to construct adversarial contexts conditioned on a given response . they augment existing dataset BAD+ and construct a new dataset B AD+ . |
| Outcome: | The proposed method can detect toxic or biased content in large pretrained language models. |
Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies employ autoregressive translation (AT) methods to encode sentences . however, the AT methods struggle with error accumulation when the length of sentences increases. |
| Approach: | They propose a context-aware non-autoregressive framework with the sentence-aligned connectionist temporal classification loss for document-level neural machine translation. |
| Outcome: | The proposed framework achieves 46X speedup on three benchmarks compared to strong baselines. |
Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for OOD intent detection are limited to single dialogue turns. |
| Approach: | They propose a context-aware OOD intent detection framework to model multi-turn contexts in OOD context detection tasks using unlabeled data. |
| Outcome: | The proposed framework improves the F1-OOD score by 29% on multi-turn OOD detection tasks compared to the previous best method. |
Text-Attributed Graph Learning with Coupled Augmentations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models focus on either the text attribute or the graph structure, neglecting the other aspect. |
| Approach: | They propose a model that combines the strengths of both text-learning and graph-learning models in parallel. |
| Outcome: | The proposed model outperforms existing models on diverse datasets. |
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)
Copied to clipboard
Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang
| Challenge: | Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. |
| Approach: | AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks. |
| Outcome: | Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% . |
GeAR: Generation Augmented Retrieval (2025.findings-acl)
Copied to clipboard
Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang
| Challenge: | Document retrieval techniques are used to compute semantic similarity between a query and documents, but the scalar similarity fails to reflect enough information, hindering the interpretation of retrieval results. |
| Approach: | They propose a method which improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules. |
| Outcome: | The proposed method improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules. |
Tackling Distractor Documents in Multi-Hop QA with Reinforcement and Curriculum Learning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing work on retrieval-augmented generation systems has shown that retrievers exhibit imperfect recall and precision, limiting downstream performance. |
| Approach: | They propose a retrieval-augmented generation model that generates answers from larger sets of retrieved contexts. |
| Outcome: | The proposed model generates answers and cites relevant information from larger sets of retrieved contexts. |
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)
Copied to clipboard
Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu
| Challenge: | Existing slot filling models memorize inherent patterns of entities and contexts from training data. |
| Approach: | They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution . |
| Outcome: | The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts. |
Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems (2026.acl-long)
Copied to clipboard
| Challenge: | Rapid urbanization and surging vehicle ownership intensify congestion . rapid urbanization drives crash rates, slow emergency response, and burden transit-poor communities . |
| Approach: | They introduce a 3B-parameter foundation model with human-like reasoning for Traffic signal control (TSC) they use reinforcement learning and network communication to convert LLM into a traffic-control model that operates like a human traffic agent. |
| Outcome: | The proposed model outperforms baselines and training-intensive RL controllers on a simulated traffic environment and reduces queue lengths by more than 5%. |
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents (2026.acl-long)
Copied to clipboard
Jiahe Guo, Xiangran Guo, Yulin Hu, Zimo Long, Xingyu Sui, Xuda Zhi, Yongbo Huang, Hao He, Weixiang Zhao, Yanyan Zhao, Bing Qin
| Challenge: | Existing research on personalized LLM agents focuses on the effectiveness of personalized responses. |
| Approach: | They propose a benchmark to quantify intent legitimation in personalized interactions . they propose 'detection-reflection' method that detects intent legititimation from internal representation space . |
| Outcome: | The proposed method reduces safety degradation by using internal representation space. |
Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area . current code-switching methods suffer from term boundary detection issues and out-of-dictionary problems. |
| Approach: | They propose a test-time code-switching framework which bridges the gap between bilingual training and monolingual test- time prediction. |
| Outcome: | The proposed framework achieves an average improvement of 3.7% on four cross-lingual datasets. |
One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Current paradigms for empowering Large Language Models with multilingual capabilities rely heavily on massive instruction tuning. |
| Approach: | They propose a hybrid cross-alignment approach that fuses a frozen NLLB encoder with a Qwen decoder via a closed-loop dual-adapter architecture. |
| Outcome: | The proposed model outperforms towerPlus-9B and Aya-101 on language-agnostic projection protocols. |
A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)
Copied to clipboard
Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang
| Challenge: | Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs . |
| Approach: | They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding . |
| Outcome: | The proposed model shows an increase in performance in KIE and VQA tasks. |
LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been successful in understanding language and processing text, but their cost prohibits their practical applications. |
| Approach: | They propose a multi-agent collaboration method that breaks down lengthy documents into smaller, more manageable chunks and organizes the member agents to read their assigned chunks. |
| Outcome: | The proposed method achieves 16.42% and 1.63% accuracy gains over existing models on single-hop and multi-hop QA settings. |
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)
Copied to clipboard
An-Lan Wang, Jingqun Tang, Lei Liao, Hao Feng, Qi Liu, Xiang Fei, Jinghui Lu, Han Wang, Hao Liu, Yuliang Liu, Xiang Bai, Can Huang
| Challenge: | Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world . |
| Approach: | They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions. |
| Outcome: | The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents. |
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)
Copied to clipboard
Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang
| Challenge: | Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. |
| Approach: | They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants. |
| Outcome: | The proposed approach improves performance across benchmarks and representation space. |
Scalable-DSC: A Structural Template Prompt Approach to Scalable Dialogue State Correction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to correct wrong slot values in dialogue state tracking are intertwined with specific DST models, limiting their applicability to other DSTs. |
| Approach: | They propose a Scalable Dialogue State Correction model that corrects wrong slot values in predicted dialogue states by using a structural template prompt. |
| Outcome: | The proposed model achieves state-of-the-art results on MultiWOZ 2.0-2.4. |
VLSBench: Unveiling Visual Leakage in Multimodal Safety (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that textual unlearning does not achieve comparable safety performance with image-text alignment. |
| Approach: | They propose to use textual unlearning to align MLLMs with image-text pairs to explain this problem . they construct a visual leakless safety bench with 2.2k image- text pairs to test this problem. |
| Outcome: | The proposed model can refuse image-text pairs according to textual queries, leading to unreliable safety evaluations. |
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)
Copied to clipboard
Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen
| Challenge: | Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities. |
| Approach: | They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance. |
| Outcome: | The proposed method achieves a superior balance between downstream learning and general capability retention. |
RePair: Automated Program Repair with Process-based Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Commercial-scale language models (LMs) have taken APR to unprecedented levels, but they are limited by parameters and humans interact with them through explicit prompts. |
| Approach: | They propose a method that utilizes process supervision to improve program repair by allowing users to input feedback from compilers and test cases. |
| Outcome: | The proposed method outperforms large outcome-based generation methods and is inspired by strategies used in programming competitions. |
Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View (2026.findings-acl)
Copied to clipboard
Hao Liao, Jiwei Zhang, Jianxun Lian, Wensheng Lu, Mingqi Wu, null Shuowangg, Yong Zhang, Yitian Huang, Mingyang Zhou, Rui Mao
| Challenge: | Existing approaches to reduce OOD recommendations fall into three grounding paradigms: retrieval, constrained generation and discrete item tokenizer generation. |
| Approach: | They propose a framework that instantiates three grounding paradigms under a single architecture . embedding-based retrieval, constrained generation and discrete item-tokenizer methods are implemented . |
| Outcome: | The proposed framework eradicates OOD recommendations across all variants and achieves state-of-the-art accuracy compared to strong ID-based and LLM-based baselines. |
Dynamic Oracle for Neural Machine Translation in Decoding Phase (L18-1)
Copied to clipboard
| Challenge: | Existing methods to improve NMT performance but there is a discrepancy between training and inference when decoding. |
| Approach: | They propose to use Scheduled Sampling to reduce the discrepancy between training and inference in NMT when decoding to mitigate the discrépancy. |
| Outcome: | The proposed methods improve translation quality over standard NMT system. |
QDMR-based Planning-and-Solving Prompting for Complex Reasoning Tasks (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing Plan-and-Solve prompting methods are difficult to implement for complex questions. |
| Approach: | They propose a plan-and-solve prompting method based on Question Decomposition Meaning Representation (QDMR) it allows LLM to generate a QDMR graph to represent problem-solving logic . |
| Outcome: | The proposed method can represent and execute the problem-solving logic of complex questions more accurately than existing methods. |
CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)
Copied to clipboard
Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu
| Challenge: | a recent study shows that large language models have limited generalization in low-resource languages like Chinese. |
| Approach: | They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private . |
| Outcome: | The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language. |
Continual Learning for Multilingual Neural Machine Translation via Dual Importance-based Model Division (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods focus on preventing catastrophic forgetting by making compromises between the original and new language pairs, leading to sub-optimal performance on both translation tasks. |
| Approach: | They propose a dual importance-based model division method to divide the model parameters into two parts and separate the translation of the original and new tasks. |
| Outcome: | The proposed method outperforms strong baselines under different incremental translation scenarios. |
Rethinking Document-level Neural Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence . |
| Approach: | They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly . |
| Outcome: | The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages. |
Improved Pseudo Data for Machine Translation Quality Estimation with Constrained Beam Search (2023.emnlp-main)
Copied to clipboard
Xiang Geng, Yu Zhang, Zhejian Lai, Shuaijie She, Wei Zou, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang
| Challenge: | evaluating the quality of machine translation outputs becomes increasingly essential with the rapid development of machine language (MT). |
| Approach: | They propose to generate pseudo data using the MT model with constrained beam search (CBSQE) they propose to preserve the reference parts with high MT probabilities as correct translations . |
| Outcome: | The proposed model outperforms strong baselines in both supervised and unsupervised settings. |
Reasoning over Entity-Action-Location Graph for Procedural Text Understanding (2021.acl-long)
Copied to clipboard
| Challenge: | Procedural text understanding aims at tracking the states and locations of entities mentioned in a paragraph. |
| Approach: | They propose a framework to model entities-entity, action, and location relations using a graph neural network. |
| Outcome: | The proposed approach outperforms strong baselines on two datasets, ProPara and Recipes. |
Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Mistake Notebook Learning (MNL) is a new memory framework for large language model agents . it allows agents to distill shared error patterns into structured "mistake notes" |
| Approach: | They propose a new memory framework that enables agents to self-curate generalizable guidance from batch-clustered failures. |
| Outcome: | The proposed framework achieves competitive performance compared to existing memory mechanisms. |
IMCI: Integrate Multi-view Contextual Information for Fact Extraction and Verification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models for fact extraction and verification fail to utilize multi-view contextual information. |
| Approach: | They propose to integrate multi-view contextual information (IMCI) for fact extraction and verification by combining contextual information with inter-document context. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the open-domain Wikipedia task with a winning FEVER score of 73.96% and label accuracy of 77.25% on the online blind test set. |
Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2025.findings-emnlp)
Copied to clipboard
Hao Zhang, Bo Huang, Zhenjia Li, Xi Xiao, Hui Yi Leong, Zumeng Zhang, Xinwei Long, Tianyang Wang, Hao Xu
| Challenge: | Low-Rank Adaptation (LoRA) is a promising approach to adapting LLMs to specialized tasks . existing rank allocation techniques remain computationally inefficient and unstable . |
| Approach: | They propose a low-rank adapted model that approximates model weight updates using low-ranked decomposition. |
| Outcome: | The proposed method is limited by its uniform rank allocation to each incremental matrix . it leverages the second-order derivatives of the loss function to capture weight sensitivity . |
Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations (2025.findings-naacl)
Copied to clipboard
Hao Yang, Hongyuan Lu, Xinhua Zeng, Yang Liu, Xiang Zhang, Haoran Yang, Yumeng Zhang, Shan Huang, Yiran Wei, Wai Lam
| Challenge: | a new paradigm for dialogue systems is being developed to mimic human interactions . the current single-step dialogue paradigm lacks the depth and fluidity of human interactions. |
| Approach: | They propose a step-by-step dialogue paradigm that mimics human interactions . they use a dataset to fine-tune existing language models . |
| Outcome: | The proposed system mimics the dynamic nature of human conversations . it is compared with existing paradigms and will be released later this year . |
EvoHyper: Evolving Hypergraph Topologies for Unified Collaboration in Multi-Agent Communication (2026.findings-acl)
Copied to clipboard
Heng Zhang, Yihao Zhong, Lubin Gan, Zhihe Chen, Jiajun Wu, Yuling Shi, Xiaodong Gu, Hao Zhang, Haochen You, Jin Huang
| Challenge: | Existing methods for multi-agent collaboration use a fixed communication graph and manage collaboration structure and shared memory in separate modules. |
| Approach: | They propose a framework that uses an evolving hypergraph topology for multi-agent collaboration. |
| Outcome: | The proposed framework achieves 3.2% to 7.8% accuracy gains over state-of-the-art methods and efficient, reducing token consumption by up to 23.5%. |
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing knowledge-driven dialog data is limited due to the lack of dialog data which consists of multi-turn conversations on multiple topics and with knowledge annotations. |
| Approach: | They propose a Chinese multi-domain knowledge-driven conversation dataset which grounds the topics in multi-turn conversations to knowledge graphs. |
| Outcome: | The proposed dataset can be enhanced by introducing background knowledge, but there is still a large space for leveraging knowledge to model multi-turn conversations for further research. |
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark (2022.findings-acl)
Copied to clipboard
Hao Sun, Guangxuan Xu, Jiawen Deng, Jiale Cheng, Chujie Zheng, Hao Zhou, Nanyun Peng, Xiaoyan Zhu, Minlie Huang
| Challenge: | Dialogue safety problems severely limit the real-world deployment of generative conversational models. |
| Approach: | They propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings. |
| Outcome: | The proposed taxonomy captures unsafe behaviors in human-bot dialogue settings with rich context-sensitive unsafe examples. |
VisualEDU: A Benchmark for Assessing Coding and Visual Comprehension through Educational Problem-Solving Video Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . advanced proprietary models show promise, but struggle with increasing task complexity . |
| Approach: | VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to enhance output quality. |
| Outcome: | VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to improve output quality. |
PAL: Persona-Augmented Emotional Support Conversation Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work has demonstrated the effectiveness of dialogue models in providing emotional support due to the lack of human resources for mental health support. |
| Approach: | They propose a framework for dynamically inferring and modeling seekers’ persona from the conversation history and a model that leverages persona information to provide personalized emotional support. |
| Outcome: | The proposed model outperforms baseline models on the studied benchmark. |
StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing tool environments face challenges in balancing stability, scale, and realism, especially for benchmarking purposes. |
| Approach: | They propose a framework that trains specialized LLMs to accurately simulate real API responses by supervised fine-tuning and chain-of-thought reasoning. |
| Outcome: | The proposed framework achieves superior accuracy and stability compared to state-of-the-art methods on the newly constructed MirrorAPI-Bench and its integration into StableToolBench. |
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention (2026.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Ao Sun, Ziqi Yuan, Hao Zhou, Fandong Meng, Zhiyuan Liu
| Challenge: | Existing methods for long-video inference use compression or sparse attention . existing methods restrict LMMs from handling longer, more complex videos . |
| Approach: | They propose a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. |
| Outcome: | The proposed framework delivers speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB without significant performance loss. |
Pretraining Context Compressor for Large Language Models with Embedding-Based Memory (2025.acl-long)
Copied to clipboard
| Challenge: | Efficient processing of long contexts in large language models is essential for real-world applications such as retrieval-augmented generation and in-context learning. |
| Approach: | They propose a decoupled compressor-LLM framework that preserves contextual information within condensed embedding representations. |
| Outcome: | The proposed framework outperforms baseline models in three domains and across eight datasets while adapting to different downstream LLMs. |
HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)
Copied to clipboard
Hao Zhang, Zhenjia Li, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, null Xiaoxincc, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu
| Challenge: | Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers. |
| Approach: | They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters . |
| Outcome: | The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork. |
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning . |
| Approach: | a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path . |
| Outcome: | Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness. |
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)
Copied to clipboard
Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu
| Challenge: | Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models. |
| Approach: | They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression. |
| Outcome: | Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution. |
Robust Neural Machine Translation with Joint Textual and Phonetic Embedding (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation models are sensitive to noises in input sentences . one special kind of noise is the homophone noise, where words are replaced by other words with similar pronunciations. |
| Approach: | They propose to embed phonetic and textual information into neural machine translation datasets to improve robustness to homophone noises. |
| Outcome: | The proposed method improves the robustness of neural machine translation to homophone noises on clean test sets. |
Domain Incremental Lifelong Learning in an Open World (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to lifelong learning (LL) models require access to task identities in the testing phase or cannot handle samples from unseen tasks. |
| Approach: | They propose a dynamic architecture-based lifelong learning model that tries to learn a sequence of tasks with a prompt-enhanced language model. |
| Outcome: | The proposed model outperforms state-of-the-art models in handling unseen tasks and focuses on task-level prompts to capture knowledge from different granularities. |
Don’t Corrupt the Fact: A Trustworthy RAG Watermarking Framework based on Dual Factual Shield (2026.acl-long)
Copied to clipboard
| Challenge: | Existing watermarking methods are fact-agnostic and cause "faithfulness hallucinations" a novel framework to enforce knowledge loyalty is proposed to improve watermarks . |
| Approach: | They propose a new framework that enforces knowledge loyalty by spoofing terms from retrieved contexts and prompt-based semantic guidance to protect against factual corruption. |
| Outcome: | The proposed framework reduces the Knowledge Corruption Rate while maintaining its original high security and robustness. |
Long-Tailed Question Answering in an Open World (2023.acl-long)
Copied to clipboard
| Challenge: | Existing QA approaches require access to seen tasks or do not explicitly model samples from unseen tasks. |
| Approach: | They propose an open-tailed QA model that encourages knowledge sharing between head, tail and unseen tasks and explicitly mines knowledge from a large pre-trained language model. |
| Outcome: | The proposed model outperforms the state-of-the-art on a large-scale dataset. |
Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management (2026.acl-long)
Copied to clipboard
Weitao Ma, Xiaocheng Feng, Lei Huang, Xiachong Feng, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Bing Qin
| Challenge: | Existing approaches to memory management rely on final task performance as the primary reward, resulting in severe reward sparsity and ineffective credit assignment. |
| Approach: | They propose a framework for fine-grained feedback alignment using a Chunk-level step reward and Evidence-Anchored Reward Attribution to redistribute global rewards based on memory items utilized as evidence in reasoning. |
| Outcome: | The proposed framework outperforms baselines and supports generalization across different model configurations and backbones. |
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. |
Data-Centric Perspectives on Agentic Retrieval-Augmented Generation: A Survey (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel at natural language understanding and generation, yet rely on static pre-training data. |
| Approach: | They propose to augment Large Language Models with external retrieval to ground model outputs . traditional RAG is constrained by a fixed retrieve-then-generate routine . authors aim to guide creation of high-quality datasets for next generation of adaptive LLM agents . |
| Outcome: | The proposed model can decompose tasks, issue exploratory queries, and refine evidence through iterative retrieval. |
Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach (2026.acl-industry)
Copied to clipboard
| Challenge: | Literary translation requires balancing expression fluency with literary effect due to the scarcity of high-quality training data and the difficulty of capturing nuanced quality trade-offs. |
| Approach: | They propose a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators. |
| Outcome: | The proposed models outperform the ground truth for SFT by 8.65 CEA100 points while leveraging an explicit reward model for GRPO yields an additional 1.51 point improvement. |
Language Models Hallucinate, but May Excel at Fact Verification (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have produced non-factual outputs . however, current LLMs suffer from the hallucination issue . |
| Approach: | They propose to use instruction-tuned LLMs to generate factual outputs . they find that FLAN-T5-11B performs best as a fact verifier . |
| Outcome: | The proposed method outperforms more capable LLMs like GPT3.5 and ChatGPT in the human evaluation. |
Re3Dial: Retrieve, Reorganize and Rescale Conversations for Long-Turn Open-Domain Dialogue Pre-training (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing pre-training models lack long-turn dialogue sessions due to the scarcity of long-term sessions. |
| Approach: | They propose a framework that can automatically construct billion-scale long-turn dialogues by reorganizing existing short-turn ones. |
| Outcome: | The proposed framework can automatically construct billion-scale long-turn dialogues by reorganizing existing short-turn ones. |
UCL-Bench: A Chinese User-Centric Legal Benchmark for Large Language Models (2025.findings-naacl)
Copied to clipboard
Ruoli Gan, Duanyu Feng, Chen Zhang, Zhihang Lin, Haochen Jia, Hao Wang, Zhenyang Cai, Lei Cui, Qianqian Xie, Jimin Huang, Benyou Wang
| Challenge: | Existing legal benchmarks focusing on knowledge and logic evaluate LLMs on various tasks in legal domain, but few have explored the practical application of LLM by actual users. |
| Approach: | They propose a Chinese user-centric legal benchmark that aims to assess the practical application of LLMs by real users. |
| Outcome: | The proposed model outperforms existing models on various tasks in legal domain but does not outperfect ChatGPT. |
Communication-Efficient Desire Alignment for Proactive Embodied Human–Agent Interaction (2026.acl-long)
Copied to clipboard
| Challenge: | Effective real-world human–agent interactions are long-term and repeated. |
| Approach: | They propose a simulation that uses a proxy user with value-driven preferences and natural language behavior to evaluate how agents adapt to users across interactions and satisfy their desires. |
| Outcome: | HA-Desire, a home assistance simulation, shows that agents can adapt to user needs and provide proactive assistance within limited communication. |
RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection (2026.acl-long)
Copied to clipboard
Zhaoheng Huang, Dacheng Wen, Yutao Zhu, Xiaoying Lian, Yushi Liang, Kai Hao, Nan Li, Liangjie Zhang, Qi Zhang, Ji-Rong Wen, Zhicheng Dou, Fangzhao Wu
| Challenge: | Recent work addresses this problem by training span-level hallucination detectors using reinforcement learning and chain-of-thought reasoning. |
| Approach: | They propose a framework that explicitly enforces active evidence seeking during CoT reasoning by requiring quotation of relevant source segments at each verification step. |
| Outcome: | The proposed framework improves hallucination span detection performance with limited reasoning overhead and improved robustness in out-of-domain settings. |
ACEBench: A Comprehensive Evaluation of LLM Tool Usage (2025.findings-emnlp)
Copied to clipboard
Chen Chen, Xinlong Hao, Weiwen Liu, Xu Huang, Xingshan Zeng, Shuai Yu, Dexun Li, Yuefeng Huang, Xiangcheng Liu, Wang Xinzhi, Wu Liu
| Challenge: | Existing benchmarks for evaluating LLMs’ tool usage face several limitations: limited evaluation scenarios, lacking assessments in real multi-turn dialogue contexts; narrow evaluation dimensions, with insufficient detailed assessments of how LLM use tools; and reliance on LLM or real API executions for evaluation, which introduces significant overhead. |
| Approach: | ACEBench is a benchmark for evaluating tool usage in Large Language Models . it categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. |
| Outcome: | ACEBench categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. |
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. |
Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Chinese word segmentation have high performance on benchmarks but are limited by the small-scale annotated corpus. |
| Approach: | They propose a framework that incorporates a lexicon-based graph convolutional network into the Transformer encoder to improve Chinese word segmentation (CWS) Chinese word is an essential and pre-processing step for many downstream NLP tasks. |
| Outcome: | The proposed framework captures the information of candidate words and improves performance on benchmarks and datasets. |
MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents (2026.acl-long)
Copied to clipboard
Pengxiang Zhao, Guangyi Liu, Yaozhen Liang, Weiqing He, Zhengxi Lu, WenHao Wang, Yuehao Huang, Yuxiang Chai, Zhaolu Kang, Yaxuan Guo, Hao Wang, Kexin Zhang, Liang Liu, Yong Liu
| Challenge: | Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, but systematic evaluation of GUI–shortcut hybrid agents remains underexplored. |
| Approach: | They propose a benchmark that evaluates GUI-shortcut hybrid agents with a specific focus on the mobile domain. |
| Outcome: | MAS-Bench evaluates agent's ability to generate shortcuts by discovering and creating reusable, low-cost workflows. |
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) can reveal toxic or offensive content inadvertently or intentionally. |
| Approach: | They propose to control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their impact. |
| Outcome: | The proposed approach improves the performance of large language models after fine-tuning. |
Zero-Shot Spoken Language Understanding via Large Language Models: A Preliminary Study (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have shown promising results in zero-shot settings, which motivates us to explore prompt-based methods. |
| Approach: | They propose a two-stage framework which transforms the SLU task into a question-answering problem by directly prompting LLMs. |
| Outcome: | The proposed framework can be built by directly prompting LLMs to understand user needs without training data. |
Multi-Source Probing for Open-Domain Conversational Understanding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models of open-domain dialogue comprehension have limited conversational understanding and response generation. |
| Approach: | They propose a multi-source probing method to probe dialogue comprehension abilities of open-domain dialogue models. |
| Outcome: | The proposed method aggregates features from multiple sources to accomplish diverse task goals and conducts downstream tasks in a generative manner consistent with dialogue model pre-training to leverage model capabilities. |
METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks evaluate contextual causal reasoning in fragmented settings, failing to ensure context consistency or cover the full causal hierarchy. |
| Approach: | They use a unified context to benchmark large language models' contextual causal reasoning skills. |
| Outcome: | The proposed benchmarks show that LLMs are susceptible to distraction by irrelevant but factually correct information at lower level of causality. |
PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) has shown strong promise for LLM-based machine translation . however, translation-oriented RL remains challenged by high-variance policy gradients induced by Monte Carlo baselines and large trajectory space that favors global exploration over fine-grained local optimization. |
| Approach: | They propose a two-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization. |
| Outcome: | The proposed framework supports global exploration and fine-grained optimization while supporting global exploration. |
Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Generating accurate SQL queries for user questions rely on the capability of large language models (LLMs) however, some knowledge is not explicitly included in the database schema and user question or has been learned by LLMs. |
| Approach: | They propose a Knowledge-to-SQL framework that employs tailored Data Expert LLM (DELLM) to provide helpful knowledge for all text-to SQL models. |
| Outcome: | The proposed framework improves the state-of-the-art approaches for text-to-SQL tasks by leveraging a data expert LLM (DELLM) to provide useful knowledge for all text- to-SqL models. |
MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions (2023.acl-long)
Copied to clipboard
| Challenge: | A moral dialogue system aligned with users’ values could enhance conversation engagement and user connections. |
| Approach: | They propose a framework to train and evaluate moral dialogue systems based on communication mechanisms of morality and a method to construct moral discussions between simulated users and the dialogue system. |
| Outcome: | The proposed framework can train and evaluate moral dialogue systems based on simulated users and their values . |
ERCThinker: Fast-Slow Thinking for Emotion Recognition in Conversation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for ERC lack interpretability and shallow semantics capture deep semantics. |
| Approach: | They propose a Fast-Slow thinking framework for Emotion Recognition in Conversation . they use fine-grained emotion reasoning chains to capture deep semantics . |
| Outcome: | The proposed framework achieves state-of-the-art in explanation and judgment on a benchmark dataset. |
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. |
Understanding Generalization in Role-Playing Models via Information Theory (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to characterize RPM generalization are inadequate . existing methods do not provide a fine-grained diagnosis of distribution shifts . |
| Approach: | They propose a reasoning-based effective mutual information difference (R-EMID) to measure RPM performance degradation in an interpretable way. |
| Outcome: | The proposed model predicts the worst-case generalization performance of RPMs and reveals how shifts contribute to degradation. |
DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking. |
| Approach: | They propose an end-to-end generative approach for jailbreak rewriting inspired by diffusion models that uses a sequence-tosequence (seq2sequ) diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss. |
| Outcome: | Experiments on Advbench and Harmbench show that the proposed method outperforms autoregressive jailbreak models across evaluation metrics including ASR, fluency, diversity and diversity. |
TLUE: A Tibetan Language Understanding Evaluation Benchmark (2025.emnlp-main)
Copied to clipboard
Fan Gao, Cheng Huang, Yutong Liu, Nyima Tashi, Xiangxiang Wang, Thupten Tsering, Ban Ma-bao, Renzeng Duojie, Gadeng Luosang, Rinchen Dongrub, Dorje Tashi, Xiao Feng Cd, Yongbin Yu, Hao Wang
| Challenge: | Low-resource languages, like Tibetan, remain underrepresented in large language models' evaluations. |
| Approach: | They propose a Tibetan Language Understanding Evaluation Benchmark to assess LLMs' proficiency in Tibetan . they use a multi-task understanding benchmark and a safety benchmark to evaluate models . |
| Outcome: | The proposed benchmark shows that most large language models perform below the random baseline, especially in Tibetan language processing. |
Retrieved In-Context Principles from Previous Mistakes (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in in-context learning (ICL) have limited customization and inadequate error coverage. |
| Approach: | They propose a method to retrieve in-context principles from mistakes to improve model performance. |
| Outcome: | The proposed framework enhances model performance when applied to various prompting strategies. |
Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) training with Mixture-of-Experts policies remains fragile and prone to reward collapse. |
| Approach: | They propose a router shift-based policy optimization method that computes a per-token router-shift ratio conditioned on the previously activated experts and applies stop-gradient and a lower-bound floor. |
| Outcome: | The proposed method achieves better performance and greater stability than previous methods. |
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)
Copied to clipboard
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu
| Challenge: | Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent. |
| Approach: | They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs. |
| Outcome: | The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models. |
Understand before Answer: Improve Temporal Reading Comprehension via Precise Question Understanding (2022.naacl-main)
Copied to clipboard
| Challenge: | Temporal reading comprehension (TRC) is a natural way to study temporal relations since natural language questions are flexible to capture divergent temporal relationships. |
| Approach: | They propose a reading comprehension approach that uses precise question understanding . they embed a temporal ordering question into two vectors and evaluate the temporal relation based on that . |
| Outcome: | The proposed approach outperforms strong baselines and achieves state-of-the-art performance on the TORQUE dataset. |
LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing hierarchical transducers suffer from negative transfer and unstable target-language generation, while training separate models for each direction is computationally prohibitive. |
| Approach: | They propose a hierarchical transducer with language-conditional Mixture-of-Experts adapters to improve multilingual joint automatic speech recognition and speech translation. |
| Outcome: | Experiments on Europarl-ST (9 languages, 72 directions) show that LCMA-SRT improves both ASR and ST within a single joint model, reducing average WER and improving BLEU and COMET over strong hierarchical transducer baselines. |
Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | HKVE selectively accepts gradient optimization results based on the distribution of attention scores across different layers, ensuring that every optimization step positively contributes to the attack. |
| Approach: | They propose a framework that selectively accepts gradient optimization results based on the distribution of attention scores across different layers and selectively takes them into account when calculating the attack success rate. |
| Outcome: | The proposed framework outperforms existing methods by achieving success rates of 75.08% on MiniGPT4, 85.84% on LLaVA and 81.00% on Qwen-VL. |
latent-GLAT: Glancing at Latent Variables for Parallel Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Recent advances in text generation have limited applications due to multimodality problem. |
| Approach: | They propose a method which uses latent variables to capture word categorical information and invoke an advanced curriculum learning technique to overcome multi-modality problem. |
| Outcome: | The proposed method outperforms strong baselines without an autoregressive model, which further broadens the application scenarios of the parallel decoding paradigm. |
Estimating Soft Labels for Out-of-Domain Intent Detection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to detect out-of-dominance (OOD) intents are limited by the lack of OOD samples. |
| Approach: | They propose an adaptive soft pseudo labeling method that can estimate soft labels for pseudo OOD samples when training OOD detectors. |
| Outcome: | The proposed method outperforms competing methods on three benchmark datasets and consistently outperformed previous methods. |
Dynamic Emotion and Personality Profiling for Multimodal Deception Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for deception detection lack sample-level dynamic annotations for emotions and personality. |
| Approach: | They propose a multi-model multi-prompt annotation scheme and a strict label quality evaluation standard for deception, emotion, and personality annotations. |
| Outcome: | The proposed framework outperforms state-of-the-art models on the MDPE and DDEP datasets. |
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)
Copied to clipboard
Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang
| Challenge: | Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence. |
| Approach: | They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included . |
| Outcome: | The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model. |
Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to enhance reasoning capabilities of language models are expensive and often lack the ability to perform complex reasoning tasks. |
| Approach: | They propose a token-level multi-model collaboration strategy to enhance reasoning capabilities in language models by selecting the optimal tokens from the next token distributions. |
| Outcome: | The proposed method is superior to existing methods and will be released soon. |
Unveiling the Implicit Toxicity in Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies focus on probing toxic outputs that can be easily detected with existing toxicity classifiers, but LLMs can generate diverse implicit toxic output that are difficult to detect via simply zero-shot prompting. |
| Approach: | They propose a reinforcement learning based attacking method to induce the implicit toxic outputs in large language models by fine-tuning toxicity classifiers. |
| Outcome: | The proposed method generates implicit toxic outputs that are difficult to detect via zero-shot prompting on five widely-adopted toxicity classifiers. |
AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)
Copied to clipboard
Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu
| Challenge: | Significant concerns emerge when addressing cultural sensitivity and local values. |
| Approach: | They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. |
| Outcome: | The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks. |
Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)
Copied to clipboard
| Challenge: | Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences. |
| Approach: | They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences. |
| Outcome: | Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs. |
Enhancing Explainable Rating Prediction through Annotated Macro Concepts (2024.acl-long)
Copied to clipboard
| Challenge: | Existing models learn user and item embeddings and generate reasons based on these embedds. |
| Approach: | They propose a concept-based explanation framework that leverages macro concepts to bridge the gap between the user/item embeddings and the recommendation reasons. |
| Outcome: | Extensive experiments on three datasets prove the proposed model is superior to existing models. |
ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings (2024.emnlp-main)
Copied to clipboard
| Challenge: | Attaching suffixes to harmful instructions can hack the defense of Large language models (LLMs) However, due to the unreadable of adversarial suffix, it can be relatively easily penetrated by common defense methods such as perplexity filters. |
| Approach: | They propose an algorithm to embed adversarial suffixes into coherent and understandable text to attack Large language models (LLMs) using a Advbench dataset. |
| Outcome: | The proposed approach reduces the computation time of adversarial suffixes and achieves a much better attack success rate than existing techniques. |
Benchmarking Large Language Models on Communicative Medical Coaching: A Dataset and a Novel System (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing applications of natural language processing (NLP) focus on patient-centered services, but the potential of NLP to benefit inexperienced doctors remains unexplored. |
| Approach: | They propose a human-AI cooperative framework to assist medical learners in practicing communication skills during patient consultations. |
| Outcome: | The proposed framework enables medical learners to practice communication skills during patient consultations while a coach agent provides immediate, structured feedback. |
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments (2026.acl-long)
Copied to clipboard
Alejandro Hernández-Cano, Alexander Hägele, Allen Hao Huang, Angelika Romanou, Antoni-Joan Solergibert, Barna Pásztor, Bettina Messmer, Dhia Garbaya, Eduard Frank Ďurech, Ido Hakimi, Juan Garcia Giraldo, Mete Ismayilzada, Negar Foroutan, Skander Moalla, Tiancheng Chen, Vinko Sabolčec, Yixuan Xu, Michael Aerni, Badr AlKhamissi, Inés Altemir Marinas, Mohammad Hossein Amani, Matin Ansaripour, Ilia Badanin, Harold Benoit, Emanuela Boros, Nicholas John Browning, Fabian Bösch, Maximilian Böther, Niklas Canova, Camille Challier, Clément Charmillot, Jonathan Coles, Jan Milan Deriu, Arnout Devos, Lukas Drescher, Daniil Dzenhaliou, Maud Ehrmann, Dongyang Fan, Simin Fan, Silin Gao, Miguel Gila, María Grandury, Diba Hashemi, Alexander Miserlis Hoyle, Jiaming Jiang, Mark Klein, Andrei Kucharavy, Anastasiia Kucherenko, Frederike Lübeck, Roman Machacek, Theofilos Ioannis Manitaras, Andreas Marfurt, Kyle Matoba, Simon Matrenok, Henrique Mendonça, Fawzi Roberto Mohamed, Syrielle Montariol, Luca Mouchel, Sven Najem-Meyer, Jingwei Ni, Gennaro Oliva, Matteo Pagliardini, Elia Palme, Andrei Panferov, Léo Paoletti, Marco Passerini, Ivan Pavlov, Auguste Poiroux, Kaustubh Ponkshe, Nathan Ranchin, Javier Rando, Mathieu Sauser, Jakhongir Saydaliev, Mukhammadali Sayfiddinov, Marian Schneider, Stefano Schuppli, Marco Scialanga, Andrei Semenov, Kumar Shridhar, Raghav Singhal, Anna Sotnikova, Alexander Sternfeld, Ayush Kumar Tarun, Paul Teiletche, Jannis Vamvas, Xiaozhe Yao, Hao Zhao, Alexander Ilic, Ana Klimovic, Andreas Krause, Caglar Gulcehre, David Rosenthal, Elliott Ash, Florian Tramèr, Joost VandeVondele, Livio Veraldi, Martin Rajman, Thomas C. Schulthess, Torsten Hoefler, Antoine Bosselut, Martin Jaggi, Imanol Schlag
| Challenge: | Apertus is a fully open suite of large language models (LLMs) designed to address responsibility shortcomings in today’s open model ecosystem, namely data responsibility and global representation. |
| Approach: | They propose to release a fully open suite of large language models (LLMs) that address data responsibility and global representation shortcomings in today’s open model ecosystem. |
| Outcome: | The proposed model is pretrained on openly available data and suppresses verbatim recall of data while retaining task performance. |
INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling (2025.findings-acl)
Copied to clipboard
Di Wu, Liting Jiang, Bohui Mao, Hongyan Xie, Haoxiang Su, Zhongjiang He, Ruiyu Fang, Shuangyong Song, Hao Huang, Xuelong Li
| Challenge: | Existing studies struggle to achieve performance comparable to that on high-resource languages due to inherent linguistic diversity of multilingual SLU tasks. |
| Approach: | They propose a multilingual information transfer network to solve these challenges . they propose to reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages. |
| Outcome: | The proposed model outperforms baseline models on the MASSIVE and MASSIV-UG datasets in overall accuracy across all languages. |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)
Copied to clipboard
Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive. |
| Approach: | They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory . |
| Outcome: | The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient. |
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (2023.emnlp-main)
Copied to clipboard
Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, Qi Zhang
| Challenge: | Large Language Models (LLMs) have impressive capabilities but need for task-specific prompt engineering can hinder their generalization. |
| Approach: | They propose a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input. |
| Outcome: | The proposed model is universally applicable across tasks and models . it mitigates hallucination problem in chatGPT, and it improves even the strongest LLMs. |
RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches for knowledge graph embedding have limitations in complex vector space . embeddability of one-to-many relations is not explicitly alleviated . |
| Approach: | They propose a relation-adaptive translating embedding function that can be extended to complex vector space. |
| Outcome: | The proposed translation function improves expressive power and alleviates embedding ambiguity problem. |
JoPR: Joint Emotion Perception and Reasoning for Conversational Emotion Recognition (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for ERC lack human-like emotion reasoning and discrimination between similar emotions. |
| Approach: | They propose a multi-dimension curriculum with long CoT fine-tuning to clone human-like emotion reasoning for conversational emotion recognition. |
| Outcome: | The proposed model outperforms existing methods on three widely used datasets and shows that it is more intuitive and more accurate. |
Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have focused on replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs). |
| Approach: | They propose a self-supervised preference optimization framework that replaces the reward model with a preference loss and alignment loss to improve LLMs' ability to understand human preferences. |
| Outcome: | The proposed framework can be integrated with existing preference optimization methods and significantly boost their performance. |
Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have revolutionized open-domain dialogue agents but face challenges in multi-character role-playing (MCRP) scenarios. |
| Approach: | They propose a framework for efficient multi-character role-playing that employs a dynamic low-rank adapter strategy and distinct LoRA blocks for each character. |
| Outcome: | Neeko employs a dynamic low-rank adapter (LoRA) strategy, enabling it to adapt seamlessly to diverse characters. |
PruneVid: Visual Token Pruning for Efficient Video Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to video token pruning face significant computational challenges due to the redundancy inherent in video data. |
| Approach: | They propose a training-free visual token pruning method that reduces the redundancy inherent in video data and leverages LLMs’ inherent ability to selectively prune visual tokens irrelevant to specific queries. |
| Outcome: | The proposed method can prune over 80% of tokens while maintaining competitive performance when combined with different video LLMs. |
COLD: A Benchmark for Chinese Offensive Language Detection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Offensive language detection is crucial for maintaining a civilized social media platform and deploying pre-trained language models. |
| Approach: | They propose a benchmark benchmark for Chinese offensive language analysis including a Chinese Offensive Language Dataset and a baseline detector which is trained on the dataset. |
| Outcome: | The proposed benchmark contributes to Chinese offensive language detection which is challenging for existing resources. |
Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)
Copied to clipboard
Zixuan Huang, Zhihong Zhu, Xiaolong Liu, Yanchao Hao, Manman Zhang, Zheng Wei, Bowen Xing, Xian Wu, Ye Li, Fen Miao, Yefeng Zheng
| Challenge: | Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal. |
| Approach: | They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs. |
| Outcome: | The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs. |
PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing research on text-based mental health counseling is limited due to the lack of relevant corpora in Chinese language. |
| Approach: | They propose a Chinese dataset of psychological health support in the form of question and answer pair that is crawled from a mental health service platform and contains 22K questions and 56K long and wellstructured answers. |
| Outcome: | The proposed dataset contains 22K questions and 56K long and wellstructured answers. |
Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED (2022.acl-long)
Copied to clipboard
| Challenge: | Document-level relation extraction is a challenging task as it requires reasoning across multiple sentences. |
| Approach: | They propose to use a recommend-revise scheme to reduce the workload of annotators by providing them with candidate relation instances from distant supervision to supplement and remove relational facts. |
| Outcome: | The proposed dataset is the first large-scale and human-annotated dataset for relation extraction. |
TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have improved the functional correctness of code translation, but execution efficiency remains overlooked. |
| Approach: | They propose a benchmark to explicitly assess execution efficiency in LLM-translated code. |
| Outcome: | The proposed benchmark identifies that execution efficiency is an essential dimension of code translation . the results highlight that correctness and efficiency are often misaligned . |
A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for length control summarization treat the length requirement as a soft constraint, which may not always be satisfied. |
| Approach: | They propose a novel length-control decoding algorithm based on the directed acyclic Transformer (DAT) their approach allows for multiple plausible sequence fragments and predicts a path to connect them. |
| Outcome: | The proposed algorithm allows for multiple plausible sequence fragments and predicts a path to connect them. |
InterIDEAS: Philosophical Intertextuality via LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | a new dataset aims to bridge philosophy, literary studies, and natural language processing (NLP) by integrating theories of intertextuality with bibliometric techniques. |
| Approach: | They propose a dataset that bridges philosophy, literary studies, and natural language processing (NLP) it combines theories of intertextuality from literary studies with bibliometric techniques and recent LLMs . |
| Outcome: | a new dataset bridges philosophy, literary studies, and natural language processing (NLP) to analyze intertextuality . the proposed method helps scholars understand the intellectual, social, and historical relations embedded in texts . it also contributes to the development of language models, authors say . |
Rethinking Translation Memory Augmented Neural Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to enhance neural machine translation (NMT) by using a TM have been reported to be effective. |
| Approach: | They propose a translation memory augmented neural machine translation model that is good at fitting data but more sensitive to fluctuations in training data. |
| Outcome: | The proposed model achieves consistent gains over conventional and existing models under two variance-preferable scenarios as well as the high resource scenario. |
GenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQL (2025.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results on BIRD and Spider benchmarks validate the effectiveness of GenLink. |
| Approach: | They propose a generation-driven schema-linking framework based on multi-model learning . experimental results validate the effectiveness of GenLink . |
| Outcome: | Experimental results show that GenLink improves schema-linking recall rate and cross-domain adaptability. |
360∘REA: Towards A Reusable Experience Accumulation with 360∘ Assessment for Multi-Agent System (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. |
| Approach: | They propose a hierarchical multi-agent framework that uses 360 assessment to accumulate experience through fine-grained assessment. |
| Outcome: | The proposed framework is based on corporate organizational practices and employs a dual-level experience pool for agents to accumulate experience through fine-grained assessment. |
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)
Copied to clipboard
Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
| Challenge: | Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness . |
| Approach: | They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image. |
| Outcome: | The proposed model outperforms existing models on key downstream tasks. |
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)
Copied to clipboard
Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang
| Challenge: | Current document image parsing solutions rely on specialized models or generate content autoregressively. |
| Approach: | They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation. |
| Outcome: | The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency. |
LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)
Copied to clipboard
Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang
| Challenge: | Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs. |
| Approach: | They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal . |
| Outcome: | The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts. |
Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation (2025.acl-long)
Copied to clipboard
| Challenge: | Quality Estimation (QE) models evaluate the quality of machine translations without reference translations, serving as the reward models for the translation task. |
| Approach: | They propose a framework for alleviating distribution shift in synthetic QE data . they employ a constrained beam search algorithm and distinct generation models to enhance translation diversity. |
| Outcome: | The proposed framework outperforms SOTA baselines like CometKiwi in supervised and unsupervised settings. |