Papers by Xiao Yang
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? (2025.acl-long)
Copied to clipboard
Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Chong Sun, Xiaoshuai Song, Jiapeng Wang, Zhuoma GongQue, Shanglin Lei, YiFan Zhang, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Xiao Zong, Yida Xu, Peiqing Yang, Zhimin Bao, Muxi Diao, Chen Li, Honggang Zhang
| Challenge: | Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization. |
| Approach: | They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation. |
| Outcome: | The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts. |
On Isotropy, Contextualization and Learning Dynamics of Contrastive-based Sentence Representation Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Incorporating contrastive learning objectives in sentence representation learning has yielded significant improvements on many sentence-level NLP tasks. |
| Approach: | They aim to examine why contrastive learning works for learning sentence-level semantics . they interpret successes through the geometry of the representation shifts based on isotropy . |
| Outcome: | The proposed model improves on many sentence-level NLP tasks, but it is not well understood why it works. |
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)
Copied to clipboard
Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, null Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong
| Challenge: | Large language models exhibit significant performance discrepancies between high- and low-resource languages. |
| Approach: | They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset. |
| Outcome: | The proposed model achieves consistent multilingual representations across languages. |
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty (2025.findings-emnlp)
Copied to clipboard
Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao, Manuel Mager, Nikolaos Pappas, Kishaloy Halder, Yang Li, Yassine Benajiba, Dan Roth
| Challenge: | Existing methods to gauge model’s uncertainty through self-consistency in responses to the target query are misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same query when answering a knowledge-preserving perturbation of the query. |
| Approach: | They propose a method that uses multi-agent interaction to estimate black-box LLMs' uncertainty. |
| Outcome: | The proposed method outperforms existing self-consistency based methods and improves hallucination detection. |
Shared-Private Bilingual Word Embeddings for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Word embedding is central to neural machine translation, but indirectly interfaces with other layers, making them comparatively isolated. |
| Approach: | They propose a shared-private bilingual word embedding which gives a closer relationship between the source and target embedders and reduces the number of model parameters. |
| Outcome: | The proposed model improves on 5 language pairs belonging to 6 different language families and written in 5 different alphabets and significantly reduces model parameters. |
SELFGOAL: Your Language Agents Already Know How to Achieve High-level Goals (2025.naacl-long)
Copied to clipboard
Ruihan Yang, Jiangjie Chen, Yikai Zhang, Siyu Yuan, Aili Chen, Kyle Richardson, Yanghua Xiao, Deqing Yang
| Challenge: | Existing approaches to improve the performance of language agents without training are not available. |
| Approach: | They propose an automatic approach to break down high-level goals into tree structure of more practical subgoals during interaction with environments while identifying the most useful subgoal. |
| Outcome: | The proposed approach significantly improves the performance of language agents across various tasks, including competitive, cooperative, and deferred feedback environments. |
Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use. |
| Approach: | They propose a benchmark to assess LLMs’ self-reflective reasoning in tool-augmented multi-turn dialogues. |
| Outcome: | The proposed benchmark covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior. |
FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner (2026.acl-long)
Copied to clipboard
Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming, Xiao Luo, Wenbin Zhang, Jiahong Zhao, Yi Guo, Jie Yang
| Challenge: | Existing approaches to mathematical reasoning rely on static heuristics or pre-determined reasoning strategies. |
| Approach: | They propose an adaptive framework that integrates fuzzy theory into LLM-based mathematical reasoning. |
| Outcome: | The proposed framework outperforms state-of-the-art models while offering effective and interpretable diagnostics of intermediate problem-solving states. |
Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but struggle with some more complex reasoning tasks including logical reasoning. |
| Approach: | They propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW to evaluate LLMs’ capability of logical fallacy understanding. |
| Outcome: | The proposed dataset can be used to evaluate LLMs’ LFU capability and to fine-tune LLM models to obtain significantly enhanced performance on logical reasoning. |
Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)
Copied to clipboard
null Ymyang, Jiang Zhong, Li Jin, Xiao Sun, Jingwang Huang, null Gaojinpeng, Qing Liu, Yang Bai, Jingyuan Zhang, Rui Jiang, Qin Lei, Kaiwen Wei
| Challenge: | Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts. |
| Approach: | They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis. |
| Outcome: | The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents. |
Text Fluoroscopy: Detecting LLM-Generated Text through Intrinsic Features (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have revolutionized the field of natural language processing because of their excellent performance on various tasks. |
| Approach: | They propose a black-box method with better generalizability for detecting LLM-generated text by mining the intrinsic features of the text to be detected. |
| Outcome: | The proposed method achieves 7.36% and 2.84% improvement in detection performance compared to baselines in detecting texts from different domains generated by GPT-4 and Claude3 respectively. |
Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search (2026.findings-acl)
Copied to clipboard
Yifei Zhang, Xu Yang, Xiao Yang, Bowen Xian, Qizheng Li, Shikai Fang, Jingyuan Li, Jian Wang, Minrui Xu, Yuge Zhang, Weiqing Liu, Jiang Bian
| Challenge: | LLM-based agents for machine learning engineering rely on tree search to rank candidates. |
| Approach: | They propose an LLM-based agent that operationalizes gradient-based optimization. |
| Outcome: | The proposed agent achieves a state-of-the-art 35.1% any-medal rate on MLE-Bench with a limited budget on a single GPU. |
Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning (2023.findings-emnlp)
Copied to clipboard
Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Mohammad Shoeybi, Ming-Yu Liu, Yuke Zhu, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar
| Challenge: | Existing methods for image-to-text generation store all knowledge within parameters, thus requiring computational-expensive fine-tuning. |
| Approach: | They propose a Retrieval-augmented Visual Language Model that stores all the knowledge within parameters and can be used to retrieve it from the external database. |
| Outcome: | The proposed model significantly boosts performance for image-to-text generation tasks with 4x less parameters compared with baseline methods. |
DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)
Copied to clipboard
Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton
| Challenge: | commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools . |
| Approach: | They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression . |
| Outcome: | The proposed approach outperforms human experts in medical examinations on diverse datasets. |
TexSmart: A System for Enhanced Natural Language Understanding (2021.acl-demo)
Copied to clipboard
Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, ZhanHui Kang, Shuming Shi
| Challenge: | TexSmart supports fine-grained named entity recognition (NER) Large-scale fine-granular entity types are expected to provide richer semantic information for downstream NLP applications. |
| Approach: | They introduce TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. |
| Outcome: | The proposed system supports fine-grained named entity recognition (NER) and enhanced semantic analysis functions. |
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)
Copied to clipboard
Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen
| Challenge: | Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy. |
| Approach: | They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges. |
| Outcome: | The proposed framework reduces retrieval time while maintaining high model performance. |
Distract Large Language Models for Automatic Jailbreak Attack (2024.emnlp-main)
Copied to clipboard
| Challenge: | Commercial large language models (LLMs) have made great progress in various NLP tasks. |
| Approach: | They propose a black-box jailbreak framework for automated red teaming of Large language models using an iterative optimization algorithm to conceal malicious content and memory reframing. |
| Outcome: | The proposed framework outperforms existing jailbreak defense methods and highlights the need to develop more effective and practical defense strategies. |
Effective Distillation of Table-based Reasoning Ability from LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing work on table-based reasoning distillation has focused on smaller models with limited performance. |
| Approach: | They propose a table-based reasoning distillation approach to distill LLMs into smaller models . their results show that a 220 million parameter model fine-tuned using distilled data improves performance . |
| Outcome: | The proposed model improves on a scientific table-to-text generation dataset and surpasses specific LLMs. |
Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)
Copied to clipboard
Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu
| Challenge: | Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers. |
| Approach: | They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights. |
| Outcome: | The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers. |
On the Robustness of Reading Comprehension Models to Entity Renaming (2022.naacl-main)
Copied to clipboard
| Challenge: | SpanBERT model is more robust than RoBERTa, despite having similar accuracy on unperturbed test data. |
| Approach: | They propose a pipeline to replace entity names with names from a variety of sources. |
| Outcome: | The proposed model performs worse when entities are renamed, the authors show . SpanBERT, which is pretrained with span-level masking, is more robust than RoBERTa . |
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning (2025.findings-acl)
Copied to clipboard
Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li
| Challenge: | Large Language Models (LMMs) struggle with simple tasks such as geometry, e.g., arithmetic, and reasoning. |
| Approach: | They propose to leverage code as supervision for cross-modal alignment . they propose to use FigCodifier and ImgCode-8.6M to synthesize novel mathematical figures . |
| Outcome: | The proposed model surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%. |
Large Language Model-Enhanced Multi-Armed Bandits (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been used to sequential decision-making tasks like multi-armed bandits where an LLM is tasked with selecting arms in each iteration is often suboptimal. |
| Approach: | They propose to combine MAB and LLMs to leverage the in-context learning capability of LLM for reward prediction. |
| Outcome: | The proposed approach outperforms LLM-based direct arm selection on synthetic tasks where only preference feedback between arm pairs is available. |
ExplainaBoard: An Explainable Leaderboard for NLP (2021.acl-demo)
Copied to clipboard
Pengfei Liu, Jinlan Fu, Yang Xiao, Weizhe Yuan, Shuaichen Chang, Junqi Dai, Yixin Liu, Zihuiwen Ye, Graham Neubig
| Challenge: | Using leaderboards, researchers can track the performance of various systems on various NLP tasks. |
| Approach: | They propose a new conceptualization and implementation of NLP evaluation using a leaderboard. |
| Outcome: | The ExplainaBoard is an evaluation tool for natural language processing (NLP) it covers more than 400 systems, 50 datasets, 40 languages, and 12 tasks. |
SQUiD: Synthesizing Relational Databases from Unstructured Text (2025.emnlp-main)
Copied to clipboard
| Challenge: | Relational databases are central to modern data management, but most data exists in unstructured forms like text documents. |
| Approach: | They propose a framework that decomposes the task into four stages, each with specialized techniques. |
| Outcome: | The proposed framework outperforms baselines across diverse datasets. |
MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain Agents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | achieving synergistic improvements between generalization and domain specialization remains a challenge in pre-training and post-training. |
| Approach: | They propose a test-time cross-domain knowledge integration method that integrates general-purpose and domain-specific models to enhance their performance on complex, domainspecific tasks. |
| Outcome: | The proposed method combines the outputs of general-purpose and domain-specific models to improve their performance on complex, domainspecific tasks. |
Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for extending the maximum context lengths of language models are lacking a strong baseline for in-context few-shot classification and on more challenging Chain-of-Thought reasoning, such as HotpotQA, deteriorate question miscomprehension and false inference. |
| Approach: | They propose to harness window-wise attention and positional embedding techniques to extend the maximum context lengths of language models. |
| Outcome: | The proposed method is able to extend the maximum context lengths of language models, e.g., 2048 for LLaMA, by harnessing window-wise attention and positional embedding techniques. |
More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020.aacl-main)
Copied to clipboard
Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Jie Zhou, Maosong Sun
| Challenge: | Existing methods for extracting relational facts from text have been successful . but with explosion of Web text, human knowledge is increasing drastically . |
| Approach: | They propose to improve relation extraction methods to extract relational facts from text . they analyze existing methods and show promising directions towards more powerful RE . |
| Outcome: | The proposed methods can extract relational facts from text, but they are still lacking in the current field. |
Incomplete In-context Learning (2026.acl-long)
Copied to clipboard
Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang, Xiaochun Cao
| Challenge: | Existing in-context learning assumes the retrieval dataset contains demonstrations for all output label spaces. |
| Approach: | They propose a framework with train-free and train-based variants to address IICL . they propose to integrate a dataset with labeled demonstrations for each output space . |
| Outcome: | The proposed framework outperforms existing methods under incomplete retrieval datasets and even outperformed ICL with complete labels. |
GLM: General Language Model Pretraining with Autoregressive Blank Infilling (2022.acl-long)
Copied to clipboard
| Challenge: | Existing pretraining frameworks do not perform well for all tasks of three main categories, such as natural language understanding (NLU), unconditional generation, and conditional generation. |
| Approach: | They propose a general language model based on autoregressive blank infilling to address this challenge. |
| Outcome: | The proposed model outperforms BERT, T5, and GPT on a wide range of tasks across NLU, conditional and unconditional generation tasks. |
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results. |
| Approach: | They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment. |
| Outcome: | The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining. |
Chinese Automatic Readability Assessment Using Adaptive Pre-training and Linguistic Feature Fusion (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for classification of reading difficulty of texts are insufficiently trained and lack of linguistic features. |
| Approach: | They propose a method that combines adaptive pre-training with feature fusion to capture different text difficulties and an interactive attention mechanism to integrate linguistic and deep features. |
| Outcome: | The proposed method achieves state-of-the-art (SOTA) performance on Chinese textbook dataset and can be applied to other languages. |
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)
Copied to clipboard
Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs. |
| Approach: | They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge. |
| Outcome: | Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 . |
Each graph is a new language: Graph Learning with LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Natural language is used to describe graphs, but graph descriptions become verbose and only relying on attribute embeddings limits LLM’s ability to capture adequate graph structural information. |
| Approach: | They propose a graph-defined language for large language model that translates the graph into a corpus instead of graph descriptions and pre-trains LLMs on this corpus to adequately understand the graph. |
| Outcome: | Experiments on five datasets show that the proposed framework outperforms description-based and embedding-based baselines by efficiently modeling different orders of neighbors. |
Rethinking Multi-Modal Alignment in Multi-Choice VideoQA from Feature and Sample Perspectives (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to VideoQA focus on utilizing frame- or object-level visual representations, but they neglect visual-language interactions. |
| Approach: | They propose to break down video into trajectories and first leverage trajectory feature in VideoQA to enhance alignment between two modalities. |
| Outcome: | The proposed method outperforms all the state-of-the-art models on the NExT-QA benchmark. |
MccSTN: Multi-Scale Contrast and Fine-Grained Feature Fusion Networks for Subject-driven Style Transfer (2024.lrec-main)
Copied to clipboard
| Challenge: | Stylistic style transfer is an important part of the image processing field . due to the low semantic similarity between the original image and the style image, many fine-grained style features are discarded. |
| Approach: | They propose a new style representation and transfer framework that can be adapted to existing image style transfers. |
| Outcome: | The proposed framework can be adapted to existing image style transfers. |
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)
Copied to clipboard
Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu
| Challenge: | Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects. |
| Approach: | They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt. |
| Outcome: | The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks. |
Attention Mechanism with Energy-Friendly Operations (2022.findings-acl)
Copied to clipboard
| Challenge: | Empirical results show that attention mechanism can be improved from the energy consumption aspects. |
| Approach: | They propose to replace multiplications with either selective operations or additions to reduce energy consumption. |
| Outcome: | The proposed model achieves competitable accuracy while saving 99% and 66% energy during alignment calculation and the whole attention procedure. |
iMOVE : Instance-Motion-Aware Video Understanding (2025.findings-acl)
Copied to clipboard
Jiaze Li, Yaya Shi, Zongyang Ma, Haoran Xu, Yandong.bai Yandong.bai, Huihui Xiao, Ruiwen Kang, Fan Yang, Tingting Gao, Di Zhang
| Challenge: | Recent advances in Video Large Language Models have led to rapid development, significantly enhancing the capture of overall video semantics and achieving remarkable performance in general video understanding tasks. |
| Approach: | They propose a large-scale instance-motion-aware video instruction-tuning dataset iMOVE that utilizes Event-awful Spatiotemporal Efficient Modeling to retain informative instance spatiotemporal motion details while maintaining computational efficiency. |
| Outcome: | The proposed model excels in video temporal understanding and general video understanding. |
Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, including instruction following, mathematical problem solving, and coding generation. |
| Approach: | They propose a method that truncates both preferred and dispreferred responses to match the shorter one’s length. |
| Outcome: | The proposed approach improves over standard implementations and achieves 11.8 points in AlpacaEval 2 and overall improvements across downstream tasks. |
Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models (2026.findings-acl)
Copied to clipboard
Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong
| Challenge: | Vision-Language Models (VLMs) have advanced multimodal learning, driving progress in cross-modal reasoning. |
| Approach: | They propose to examine moral robustness of vision-language models by analyzing their moral stances under multimodal perturbations. |
| Outcome: | The proposed model-agnostic multimodal perturbations expose VLMs to a variety of moral vulnerabilities, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion. |
FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)
Copied to clipboard
Junzhe Jiang, Chang Yang, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Danny Dongning Sun, Xinrun Wang
| Challenge: | Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation. |
| Approach: | a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 . |
| Outcome: | a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 . |
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection (2025.acl-long)
Copied to clipboard
Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu
| Challenge: | Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer. |
| Approach: | They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions. |
| Outcome: | The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios. |
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2024.findings-naacl)
Copied to clipboard
Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang
| Challenge: | i-Code V2 is one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data. |
| Approach: | They propose to create a model that can generate natural language from any combination of Vision, Language, and Speech data. |
| Outcome: | i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks. |
RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing solutions to reasoning tasks require extensive human annotations or fail in scenarios with inconsistent responses. |
| Approach: | They propose a new method that enables LLMs to self-rank their responses without additional resources. |
| Outcome: | The proposed method improves reasoning performance of ChatGPT and GPT-4 with 13% improvement over existing methods. |
EET: Experience-Driven Early Termination for Cost-Efficient Software Engineering Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models are reshaping modern software development, but they often incur substantial monetary cost. |
| Approach: | They propose an experience-driven early termination approach that extracts structured experience from prior issue-resolution executions and leverages it to guide early termination during patch generation and selection. |
| Outcome: | The proposed approach reduces cost by 19%–55% with negligible loss in resolution rate (at most 0.2%) EET extracts structured experience from prior issue-resolution executions and leverages it to guide early termination during patch generation and selection. |
Med-SRAF: A Multi-Agent Framework for Medical Reasoning via Semantic Routing and Agentic Fusion (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing RAG methods suffer from a two-part problem: semantic drift and concatenation fallacy . et al.: rapid development of Large Language Models has led to a paradigm shift in artificial intelligence . |
| Approach: | They propose a multi-agent retrieval augmentation framework guided by medical domain knowledge to address these challenges. |
| Outcome: | The proposed framework outperforms existing general RAG baselines on five widely used medical benchmarks. |
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)
Copied to clipboard
Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui
| Challenge: | coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored . |
| Approach: | They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding. |
| Outcome: | The proposed benchmark aims to accelerate the development of more scaffold-aware agents. |
EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation (2026.acl-long)
Copied to clipboard
Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao
| Challenge: | Existing methods for story evaluation lack reasoning capabilities for open-source models . evolvR framework provides high-fidelity evaluators for story generation tasks . |
| Approach: | They propose a framework that self-synthesizes chain-of-thought data via a multi-persona strategy . they propose evolvR to provide a reward model for story generation . |
| Outcome: | The proposed framework achieves state-of-the-art performance on three evaluation benchmarks . it also enhances the quality of generated stories, validating the superiority of the framework . |
Revisiting Interpolation Augmentation for Speech-to-Text Generation (2024.findings-acl)
Copied to clipboard
Chen Xu, Jie Wang, Xiaoqian Liu, Qian Dong, Chunliang Zhang, Tong Xiao, JingBo Zhu, Dapeng Man, Wu Yang
| Challenge: | Existing approaches to speech-to-text generation tasks are limited by the lack of extensive labeled datasets. |
| Approach: | They propose to use interpolation augmentation to construct virtual training samples by transforming inputs and labels to enhance generalization in other domains. |
| Outcome: | The proposed approach significantly improves performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings. |
Similarity Based Auxiliary Classifier for Named Entity Recognition (D19-1)
Copied to clipboard
| Challenge: | Named entity recognition (NER) tasks are a fundamental challenge for name recognition tasks that aim to reduce the boundary error when entities become longer. |
| Approach: | They propose a similarity based auxiliary classifier which can distinguish entity words from non-entity words by using vectors to indicate tags. |
| Outcome: | Empirical results show that the proposed classifier can perform better than baseline approaches. |
Past Meets Present: Creating Historical Analogy with Large Language Models (2025.acl-long)
Copied to clipboard
Nianqi Li, Siyu Yuan, Jiangjie Chen, Jiaqing Liang, Feng Wei, Zujie Liang, Deqing Yang, Yanghua Xiao
| Challenge: | Historical analogies are important abilities that help people make decisions and understand the world. |
| Approach: | They propose a historical analogy acquisition task that uses large language models to acquire historical analogies. |
| Outcome: | The proposed method mitigates hallucinations and stereotypes when LLMs generate historical analogies. |
Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency (2024.lrec-main)
Copied to clipboard
| Challenge: | Negation understanding is crucial to many downstream tasks such as sentiment analysis, question answering, Web search and natural language inference. |
| Approach: | They propose a novel negation triplet extraction task which aims to extract negation subject along with negation cue and scope. |
| Outcome: | The proposed model is based on a generative pretrained language model with a multi-task learning framework and achieves the best performance compared to baselines. |
A Survey of RAG-Reasoning Systems in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, Philip S. Yu
| Challenge: | a survey of RAG-based reasoning-based approaches shows that it is not effective for multi-step inferences. |
| Approach: | They map how advanced reasoning optimizes each stage of RAG . they show how retrieved knowledge supply missing premises and expand context for complex inference . |
| Outcome: | The proposed frameworks achieve state-of-the-art across knowledge-intensive benchmarks. |
Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on evaluating large language models' ability to handle disagreement cases. |
| Approach: | They evaluate the performance of large language models in detecting offensive language at varying levels of agreement. |
| Outcome: | The proposed model improves detection accuracy and model alignment with human judgment by using disagreement samples in training. |
NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)
Copied to clipboard
Changyu Zeng, Yifan Wang, Zimu Wang, Wei Wang, Zhengni Yang, Muyi Bao, Jimin Xiao, Anh Nguyen, Yutao Yue
| Challenge: | Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning. |
| Approach: | They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs. |
| Outcome: | The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs. |
Legal Fact Prediction: The Missing Piece in Legal Judgment Prediction (2025.emnlp-main)
Copied to clipboard
Junkai Liu, Yujie Tong, Hui Huang, Bowen Zheng, Yiran Hu, Peicheng Wu, Chuan Xiao, Makoto Onizuka, Muyun Yang, Shuyuan Zheng
| Challenge: | Existing studies use legal facts to predict judgments, but legal facts are difficult to obtain in early stages of litigation. |
| Approach: | They propose a legal fact prediction task that takes evidence from trial as input to make predictions in the absence of ground-truth legal facts. |
| Outcome: | The proposed task can predict court rulings without ground-truth legal facts . the first benchmark dataset, LFPBench, is used to evaluate the task . |
CSLM: A Framework for Question Answering Dataset Generation through Collaborative Small Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Collecting high-quality question-answer (QA) pairs is vital for training large language models, but computational demands and associated costs often render such approaches prohibitive for the average researcher. |
| Approach: | They propose a small-scaled, open-source solution that generates QA pairs from documents or raw corpora using large-scale models like Llama-70B. |
| Outcome: | Experiments on domain-specific datasets show that the proposed model can generate high-quality QA pairs, making it accessible to a broader range of researchers. |
Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on classical Chinese poetry are limited by modality constraints, dataset size, or the level of refinement. |
| Approach: | They propose to construct a large-scale and fine-grained multimodal knowledge graph of classical Chinese poetry using an informative ontology graph and a text-image alignment method. |
| Outcome: | The proposed method collects knowledge about classical Chinese poetry from ontology graphs and performs four tasks that demonstrate its comprehensiveness and high quality. |
Guide the Many-to-One Assignment: Open Information Extraction via IoU-aware Optimal Transport (2023.acl-long)
Copied to clipboard
Kaiwen Wei, Yiran Yang, Li Jin, Xian Sun, Zequn Zhang, Jingyuan Zhang, Xiao Li, Linhao Zhang, Jintao Liu, Guo Zhi
| Challenge: | Open Information Extraction (OIE) aims to extract structured information from text without the limitations of close ontology. |
| Approach: | They propose a method to assign ground truth labels to parallelly generated tuple proposals . they leverage intersection-over-union (IoU) as assignment quality measurement . |
| Outcome: | The proposed method outperforms the state-of-the-art models on three benchmarks. |
Improving Continual Relation Extraction through Prototypical Contrastive Learning (2022.coling-1)
Copied to clipboard
| Challenge: | Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks. |
| Approach: | They propose a Continual Relation Extraction framework with Contrastive Learning which is built with a classification network and a prototypical contrastive network to achieve incremental-class learning of CRE. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on two public datasets and proves its effectiveness on improving performance. |
LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)
Copied to clipboard
Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang
| Challenge: | Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics. |
| Approach: | They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks. |
| Outcome: | The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring. |
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite excelling at many natural language processing tasks, large language models fail to grasp the layered semantics of Drivelological text. |
| Approach: | They construct a benchmark dataset of over 1,200+ carefully curated and diverse examples across English, Mandarin, Spanish, French, Japanese, and Korean to examine their Drivelological characteristics. |
| Outcome: | The proposed models lack conceptual understanding and lack conceptual and semantic accuracy. |
Similarizing the Influence of Words with Contrastive Learning to Defend Word-level Adversarial Text Attack (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural language models are vulnerable to word-level adversarial text attacks . previous word-based search methods assume important words influence prediction . |
| Approach: | They propose a method for similarizing the influence of words with contrast learning that encourages model to learn sentence representations in which words of varying importance have a more uniform influence on prediction. |
| Outcome: | The proposed method is compatible with various training methods and improves model robustness against various adversarial attacks. |
Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference (2026.findings-acl)
Copied to clipboard
| Challenge: | Distributed LLMs avoid raw inputs by transmitting intermediate hidden states, a practice widely assumed to preserve privacy. |
| Approach: | They propose a distributed inference framework that transmits intermediate hidden states to avoid sending raw inputs by exposing sensitive user attributes. |
| Outcome: | The proposed approach achieves Top-1 accuracy of 0.997 on CMS, 0.980 on Skytrax, and 0.986 on ECHR. |
SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams (2026.findings-acl)
Copied to clipboard
Chenglong Wang, Canjia Li, Xingzhao Zhu, Yifu Huo, Huiyu Wang, Weixiong Lin, Yun Yang, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Tong Xiao
| Challenge: | Existing approaches to generate relevance judgments are limited due to dynamic nature of query distributions. |
| Approach: | They propose a self-evolving relevance model approach to generalize queries to practical search scenarios . they use a multi-agent sample miner and a relevance annotator to generate reliable labels . |
| Outcome: | The proposed approach can achieve significant performance gains on a large-scale industrial platform, validated by offline multilingual evaluations and online testing. |
Human-in-the-loop Robotic Grasping Using BERT Scene Representation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches for robotic grasping in cluttered scenes are expensive and lack structure information. |
| Approach: | They propose a human-in-the-loop framework for robotic grasping in cluttered scenes . they substitute scene-graph representation with a text representation of the scene using BERT . |
| Outcome: | The proposed framework outperforms object-agnostic and scene-graph based methods on robots and physical robots. |
DCFEE: A Document-level Chinese Financial Event Extraction System based on Automatically Labeled Training Data (P18-4)
Copied to clipboard
| Challenge: | Existing methods to extract events from documents are limited due to the high cost of labeling . Experimental results demonstrate the effectiveness of a document-level Chinese financial event extraction system. |
| Approach: | They propose a document-level Chinese financial event extraction framework which detects event mentions and extracts events from financial news. |
| Outcome: | The proposed system detects event mentions and extracts events from financial news . it can generate large scale labeled data and extract events from entire document . |
Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models (2025.acl-long)
Copied to clipboard
Huanhuan Wei, Xiao Luo, Hongyi Yu, Jinping Liang, Luning Yang, Lixing Lin, Alexandra Popa, Xiting Yan
| Challenge: | Spatial transcriptomic technologies allow measuring gene expression profile and spatial information of cells in tissues simultaneously. |
| Approach: | They propose a spatial transcriptomic approach to identify spatial niches using a zero-shot large language models by transforming spatial transcriptomics data into spatial context prompts. |
| Outcome: | The proposed model improves performance by leveraging gene expression of neighboring cells/spots, cell type composition, tissue information, and external knowledge. |
Dangling-Aware Entity Alignment with Mixed High-Order Proximities (2022.findings-naacl)
Copied to clipboard
Juncheng Liu, Zequn Sun, Bryan Hooi, Yiwei Wang, Dayiheng Liu, Baosong Yang, Xiaokui Xiao, Muhao Chen
| Challenge: | Existing methods for dangling-aware entity alignment are underexplored but important problem. |
| Approach: | They propose a framework that uses high-order proximities to detect dangling entities and align matchable entities. |
| Outcome: | The proposed framework detects dangling entities and aligns matchable entities better than existing methods. |
Topic-Oriented Open Relation Extraction with A Priori Seed Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for open relation extraction give sub-optimal results on specific topics. |
| Approach: | They propose a method that leverages the built-in knowledge of large language models to maintain a dynamic seed relation dictionary for the topic. |
| Outcome: | The proposed approach empowers better topic-oriented control over the generated relations and improves ORE performance along the five dimensions, especially on specialized and narrow topics. |
Skeletons Matter: Dynamic Data Augmentation for Text-to-Query (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on a single query language, resulting in limited generalizability . a new task paradigm is proposed to unify semantic parsing tasks across different query languages . |
| Approach: | They propose a task paradigm that unifies parsing tasks across query languages . they identify query skeletons as a shared optimization target of Text-to-Query tasks . |
| Outcome: | The proposed method achieves state-of-the-art performance using only a small amount of synthesized data. |
Knowledge Graph Unlearning with Schema (2025.coling-main)
Copied to clipboard
| Challenge: | Unlearning on knowledge graphs has not been extensively studied. |
| Approach: | They propose a new unlearning method based on schema for knowledge graph (KG) they update the representation of the deleted element’s neighborhood with an unlearning object that regulates the affinity between the affected neighborhood and the instances within the same schema. |
| Outcome: | The proposed method is evaluated on various KG embedding models with benchmark datasets. |
JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents (2026.acl-long)
Copied to clipboard
Ada Chen, Yongjiang Wu, Junyuan Zhang, Jingyu Xiao, Shu Yang, Jen-tse Huang, Kun Wang, Wenxuan Wang, Shuai Wang
| Challenge: | Recent advances in computer-using agents have created new safety and security risks . despite the impressive capabilities of CUAs, there are still significant security risks. |
| Approach: | They propose a systematization of knowledge on the safety and security threats of Computer-Using Agents. |
| Outcome: | The proposed framework provides a framework for assessing the safety and security risks of computer-using agents. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation (2024.emnlp-main)
Copied to clipboard
Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Mahong Xia, Zhang Li, Boxing Chen, Hao Yang, Bei Li, Tong Xiao, JingBo Zhu
| Challenge: | Existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset. |
| Approach: | They propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR). |
| Outcome: | The proposed method outperforms Alpaca's existing methods by 32.1% in GPT-4 evaluations. |
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition (2025.coling-main)
Copied to clipboard
Yuming Yang, Wantong Zhao, Caishuang Huang, Junjie Ye, Xiao Wang, Huiyuan Zheng, Yang Nan, Yuran Wang, Xueying Xu, Kaixin Huang, Yunke Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current Large Language Models struggle with complex entity taxonomies in open domains and lack NER capabilities. |
| Approach: | They propose a dataset to guide LLMs' generalization in Open NER under a universal entity taxonomy. |
| Outcome: | The proposed model outperforms GPT-4 in 3 out-of-domain benchmarks across 15 datasets and 6 languages. |
Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries (2025.findings-acl)
Copied to clipboard
Ganlin Xu, Zhoujia Zhang, Wangyi Mei, Jiaqing Liang, Weijia Lu, Xiaodong Zhang, Zhifei Yang, Xiaofeng Ma, Yanghua Xiao, Deqing Yang
| Challenge: | Current dense retrieval methods compute similarities between dense vectors but overlook the real query intents. |
| Approach: | They propose a neuro-symbolic information retrieval method that leverages first-order logic to optimize the embeddings of naive natural language by considering the logical consistency between queries and documents. |
| Outcome: | The proposed method outperforms existing methods on negative-constraint queries under zero-shot and low-resource retrieval tasks. |
SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction only implicitly learn to model relevant contexts and entity types while being trained for RE. |
| Approach: | They propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for RE. |
| Outcome: | The proposed method outperforms the runner-up method on three benchmarks by 5.04% . textual contexts and entity types are the major information sources that lead to the success of previous approaches. |
RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)
Copied to clipboard
Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang
| Challenge: | Existing benchmarks for large language models focus on simple, flat table structures. |
| Approach: | They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG. |
| Outcome: | The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG. |
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)
Copied to clipboard
Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths. |
| Approach: | They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO. |
| Outcome: | The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages. |
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)
Copied to clipboard
Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance. |
| Approach: | They propose to use data diversity to measure instruction tuning of large language models. |
| Outcome: | The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning. |
Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but their performance drops substantially on low-resourced languages due to the limited data availability. |
| Approach: | They propose a Depth-Aware Model Adaptation framework that allocates adaptation capacity according to each layer’s role. |
| Outcome: | The proposed framework matches or surpasses state-of-the-art accuracy with 80% fewer trainable parameters and achieves 29% error reduction under extreme data scarcity. |
Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)
Copied to clipboard
Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong
| Challenge: | Existing evaluation methods are inadequate to evaluate large language models (LLMs). |
| Approach: | They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models. |
| Outcome: | The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results. |
DeltaNet: Conditional Medical Report Generation for COVID-19 Diagnosis (2022.coling-1)
Copied to clipboard
Xian Wu, Shuxin Yang, Zhaopeng Qiu, Shen Ge, Yangtian Yan, Xingwang Wu, Yefeng Zheng, S. Kevin Zhou, Li Xiao
| Challenge: | X-ray and CT are the gold standard for COVID-19 diagnosis and treatment . however, due to the excessive number of patients, writing reports becomes a heavy burden for radiologists. |
| Approach: | They propose to use X-ray and CT to generate medical reports automatically . they evaluate DeltaNet on a COVID-19 dataset, where it outperforms state-of-the-art approaches . |
| Outcome: | The proposed system outperforms state-of-the-art methods on a COVID-19 dataset. |
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)
Copied to clipboard
Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong
| Challenge: | Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages. |
| Approach: | They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English. |
| Outcome: | The proposed model outperforms open-source and Tibetan-focused models on diverse tasks. |
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy (2026.acl-industry)
Copied to clipboard
| Challenge: | Reasoning LLMs often spend tokens on long intermediate reasoning traces when solving new problems. |
| Approach: | They propose to store reusable reasoning skills distilled from extensive deliberation and trial-and-error exploration and retrieve these skills at inference time to guide future reasoning. |
| Outcome: | The proposed approach reduces reasoning tokens while improving overall performance on coding and mathematical reasoning tasks. |
CTC-based Non-autoregressive Speech Translation (2023.acl-long)
Copied to clipboard
Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu
| Challenge: | End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency. |
| Approach: | They develop a model that uses connectionist temporal classification to predict the source and target texts. |
| Outcome: | The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67. |
AD-LLM: Benchmarking Large Language Models for Anomaly Detection (2025.findings-acl)
Copied to clipboard
Tiankai Yang, Yi Nian, Li Li, Ruiyao Xu, Yuangang Li, Jiaqi Li, Zhuo Xiao, Xiyang Hu, Ryan A. Rossi, Kaize Ding, Xia Hu, Yue Zhao
| Challenge: | Anomaly detection (AD) is an important machine learning task with many real-world uses, including fraud detection, medical diagnosis, and industrial monitoring. |
| Approach: | They propose a benchmark that evaluates how large language models (LLMs) can help with NLP anomaly detection. |
| Outcome: | The proposed model can perform zero-shot detection without tasks-specific training, data augmentation and model selection, and it can suggest unsupervised AD models. |
Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction (2024.findings-acl)
Copied to clipboard
| Challenge: | Chinese Spelling Correction (CSC) lacks large-scale high-quality corpora due to labor-intensive labeling of spelling errors in real-life writing or typing scenarios. |
| Approach: | They propose to use OCR/ASR-based generation to refine Chinese Spelling Correction models on random replacement-based corpora and filter them based on prediction confidence. |
| Outcome: | The proposed model outperforms existing models on three widely-used benchmarks while significantly alleviating over-correction. |
Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing large language models can extract triples from simple sentences with few-shot learning or fine-tuning, but they often miss out when extracting from complex sentences. |
| Approach: | They propose an evaluation-filtering framework that integrates large language models with small models for relational triple extraction tasks. |
| Outcome: | The proposed framework integrates large language models with small models for relational triple extraction tasks. |
Towards Robust Evidence-Aware Fake News Detection via Improving Semantic Perception (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods lack sufficient semantic perception and are easily blinded by textual expressions. |
| Approach: | They propose a model-agnostic training framework to improve the semantic perception of evidence-aware fake news detection by combining two kinds of data augmentations with synthetic data. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on the extended test set while achieving competitive performance on the original one. |
Are All the Datasets in Benchmark Necessary? A Pilot Study of Dataset Evaluation for Text Classification (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing benchmark datasets contribute little to discriminating top-scoring systems, while those less used datasets exhibit impressive discriminative power. |
| Approach: | They examine the distinguishability of benchmark datasets when comparing different systems . they find that existing benchmark dataset contribute little to discriminating top-scoring systems - whereas those less used datasets exhibit impressive discriminative power. |
| Outcome: | The proposed datasets are released on DataLab. |
From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding (2025.emnlp-industry)
Copied to clipboard
Xiangfeng Wang, Xiao Li, Yadong Wei, null Songxueyu, Yang Song, null Xiaxiaoqiang, Fangrui Zeng, Zaiyi Chen, null Liuliu, Gu Xu, Tong Xu
| Challenge: | Existing methods for video editing rely on textual cues from ASR transcripts and segment selection, often neglecting rich visual context. |
| Approach: | They propose a human-inspired automatic video editing framework that leverages multimodal narrative understanding to address these limitations. |
| Outcome: | The proposed framework outperforms existing baselines across general and advertisement-oriented editing tasks. |
Enhanced Reasoning for Biomedical Document-Level Relation Extraction via a Novel Cascade Language Model Framework (2026.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are the leading paradigm in document-level relation extraction. |
| Approach: | They propose a cascade framework that leverages the complementary strengths of PLMs and LLMs through a detect-then-rethink paradigm. |
| Outcome: | The proposed framework improves on BioRED and CDR datasets and improves existing models. |
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing jailbreak research exhibits limitations in universality, validity, and efficiency . Existing methods for jailbreaking LLMs have limited validity and effectiveness . |
| Approach: | They propose a black-box approach that uses wordplay-guided mapping rule sampling to create universal adversarial prompts. |
| Outcome: | The proposed method efficiently identifies security vulnerabilities across various LLMs, achieving an average success rate of over 80% with fewer than 10 queries. |
Triviality Corrected Endogenous Reward (2026.acl-long)
Copied to clipboard
Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao
| Challenge: | Recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards focuses on open-ended text generation, requiring either annotated data or powerful closed-source models. |
| Approach: | They propose a method that rewards the relative information gain between a specialist and a generalist reference policy, modulated by a probability-dependent correction mechanism. |
| Outcome: | The proposed model improves on multiple writing benchmarks and model architectures without external supervision and validates generality across different generation tasks. |
MoE-I2: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition (2024.findings-emnlp)
Copied to clipboard
Cheng Yang, Yang Sui, Jinqi Xiao, Lingyi Huang, Yu Gong, Yuanlin Duan, Wenqi Jia, Miao Yin, Yu Cheng, Bo Yuan
| Challenge: | emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. |
| Approach: | They propose a two-stage compression method tailored for Mixture of Experts to reduce the model size and decrease the computational cost. |
| Outcome: | The proposed method reduces model size and improves inference efficiency while maintaining performance in various zero-shot tasks. |
Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)
Copied to clipboard
Bohan Li, Jiannan Guan, Longxu Dou, Yunlong Feng, Dingzirui Wang, Yang Xu, Enbo Wang, Qiguang Chen, Bichen Wang, Xiao Xu, Yimeng Zhang, Libo Qin, Yanyan Zhao, Qingfu Zhu, Wanxiang Che
| Challenge: | Existing data on MBTI personality detection are based on self-reported labels and fail to capture the full range of population personality traits. |
| Approach: | They construct a manually annotated MBTI personality detection dataset with soft labels under the guidance of psychologists and use them to identify the task. |
| Outcome: | The MBTIBench is the first manually annotated MBti personality detection dataset with soft labels under the guidance of psychologists. |
Capturing Minds, Not Just Words: Enhancing Role-Playing Language Models with Personality-Indicative Data (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing role-playing models focus on character knowledge and tones, but lack personality-indicative data to capture characters' minds. |
| Approach: | They propose to enhance role-playing agents (RPAs) via personality-indicative data by asking psychological scales to capture broad aspects of personality traits in individuals. |
| Outcome: | The proposed model exhibits advanced role-playing capabilities for both general and personality-related evaluations. |
Robust and Scalable Model Editing for Large Language Models (2024.lrec-main)
Copied to clipboard
Yingfa Chen, Zhengyan Zhang, Xu Han, Chaojun Xiao, Zhiyuan Liu, Chen Chen, Kuai Li, Tao Yang, Maosong Sun
| Challenge: | Existing methods that ignore contextual knowledge fail to reliably fall back to parametric knowledge when presented with irrelevant context. |
| Approach: | They propose to use contextual knowledge to update and correct LLMs' knowledge by in-context editing instead of retraining. |
| Outcome: | The proposed method outperforms current state-of-the-art methods by a large margin on a dataset that contains irrelevant questions. |
BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing document translation pipelines face a tension between linguistic processing and layout preservation. |
| Approach: | They propose a framework for layout-preserving PDF translation that decouples visual layout metadata from semantic content. |
| Outcome: | The proposed framework improves layout fidelity, visual aesthetics, and terminology consistency over representative baselines while maintaining competitive translation precision. |
PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are too large to be fine-tuned with budget constraints and some are only accessible via APIs. |
| Approach: | They propose a pluggable Reward-Driven Contextual Adapter that integrates large language models as generators and trains them to refine the retrieved information. |
| Outcome: | The proposed method improves ReQA performance on three datasets by up to 20% compared to existing methods. |
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)
Copied to clipboard
Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song
| Challenge: | Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage. |
| Approach: | They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality. |
Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to extract relationships from texts depend on memory size and replay these memorized samples in subsequent tasks. |
| Approach: | They propose to use a model to extract relations between entities from texts where the samples of different relations are delivered into the model continuously. |
| Outcome: | The proposed model outperforms the state-of-the-art models and avoids catastrophic forgetting. |
Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Decompilation is the process of converting compiled code back into a high-level programming language for analysis when source code is unavailable. |
| Approach: | They propose two methods to improve decompilation performance without fine-tuning and fine-grained alignment enhancement to achieve further improvements. |
| Outcome: | The proposed methods achieved a Re-Executability performance improvement of approximately 3.90% on the Decompile-Eval benchmark, establishing a new state-of-the-art performance of 52.41%. |
Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing attempts to enhance LLM-based world models through prompting or fine-tuning approaches are either requiring human knowledge or computationally extensive. |
| Approach: | They propose a framework that leverages retrieval-augmented generation to integrate external knowledge to LLM-based world models. |
| Outcome: | The proposed framework outperforms baseline models and exhibits strong generalizability. |
Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for hierarchical text classification are lacking in the field of natural language processing. |
| Approach: | They propose a hierarchy-aware T5 model with path-adaptive attention mechanism to exploit hierarchical dependency across different levels. |
| Outcome: | The proposed model outperforms state-of-the-art models especially in Macro-F1 and low Macro. |
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)
Copied to clipboard
Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang
| Challenge: | Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases. |
| Approach: | They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs. |
| Outcome: | The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs. |
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)
Copied to clipboard
Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu
| Challenge: | Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says . |
| Approach: | They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions. |
| Outcome: | a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures . |
Identifying Tension in Holocaust Survivors’ Interview: Code-switching/Code-mixing as Cues (2022.lrec-1)
Copied to clipboard
| Challenge: | Using CS/CM as a linguistic phenomenon could be a sign of tension in Holocaust survivors’ interviews. |
| Approach: | They annotated CS/CM codes and annotate silence situations in an open corpus . they found that most annotations were captured in the tension places . |
| Outcome: | The proposed method shows that annotations are captured in the tension places . the study calls for more research endeavors on tension detection . |
Curse of Knowledge: Your Guidance and Provided Knowledge are biasing LLM Judges in Complex Evaluation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study has focused on simple settings, but their reliability in complex tasks remains understudied. |
| Approach: | They propose to use large language models as judges to evaluate reliability in complex tasks . they use a challenge benchmark to expose and quantify Auxiliary Information Induced Biases . |
| Outcome: | The proposed benchmark exposes and quantifies Auxiliary Information Induced Biases across 12 basic and 3 advanced scenarios. |
Representation-Guided Parameter-Efficient LLM Unlearning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to unlearning large language models often memorize sensitive or harmful information, but they struggle with the forget-retain trade-off due to the polysemantic nature of LLMs parameters. |
| Approach: | They propose a representation-guided low-rank unlearning approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning. |
| Outcome: | The proposed approach outperforms state-of-the-art models on TOFU and WMDP benchmarks while maintaining higher model utility. |
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks. |
| Approach: | They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically. |
| Outcome: | The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios. |
Not All Citations Are Equal:Entropy-Guided Citation Selection for Noise-Resistant Medical LLM (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models have demonstrated extensive potential in medical applications . however, their practical deployment in healthcare faces significant challenges . |
| Approach: | They propose a training-free multi-turn reasoning framework and a post-training methodology that provides external knowledge support for large language models. |
| Outcome: | The proposed framework elicits internal thought, external thought, and fusion thought, with an entropy-based reward that encourages selective citation of beneficial external knowledge while penalizing noisy citations. |
PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning (2025.emnlp-industry)
Copied to clipboard
Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong
| Challenge: | Existing methods to improve factuality of large language models (LLMs) rely on human-engineered instructions. |
| Approach: | They propose a retrieval-augmented generation framework that trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages and instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without extensive human engineered instructions. |
| Outcome: | The proposed framework outperforms state-of-the-art solutions across 12 open-book RAG QA benchmarks and is being deployed in production. |
RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks. |
| Approach: | They propose a new framework for routing using large language models . they formalize routing as node selection through edge-weight prediction . |
| Outcome: | The proposed framework outperforms the best single LLM and baselines on five datasets . it achieves 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%. |
InstructDiff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing data selection methods suffer from severe domain specificity . existing methods for general instruction-following fail on reasoning tasks . |
| Approach: | They propose a framework that operationalizes contrastive entropy as a domain-adaptive selection criterion through warmup calibration, bi-directional NLL filtering, and entropic-based ranking. |
| Outcome: | Experiments show that InstructDiff outperforms baseline training on reasoning tasks while using only 10% of the data. |
KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing to retrieve knowledge strictly necessary for answer generation. |
| Approach: | They propose a retrieval-filtering-summarization pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information. |
| Outcome: | The proposed pipeline surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%. |
ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base (2024.acl-long)
Copied to clipboard
| Challenge: | ANALOGYKB is a million-scale analogy knowledge base based on existing knowledge graphs (KGs) based upon relational knowledge triples, we can discover new analogies using the corresponding relations between concepts. |
| Approach: | They propose a million-scale analogy knowledge base derived from existing knowledge graphs (KGs) ANALOGYKB identifies analogies of the same relations and analogies from analogous relations . |
| Outcome: | The proposed model enables both smaller LMs and LLMs to gain better analogical reasoning capabilities. |
BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored. |
| Approach: | They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases. |
| Outcome: | The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods. |
UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)
Copied to clipboard
Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang
| Challenge: | Recent advances in large language models (LLMs) have expanded their potential applications in finance. |
| Approach: | They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions. |
| Outcome: | The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios. |
HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy (2024.acl-long)
Copied to clipboard
Mengxi Xiao, Qianqian Xie, Ziyan Kuang, Zhicheng Liu, Kailai Yang, Min Peng, Weiguang Han, Jimin Huang
| Challenge: | Large Language Models (LLMs) can be used in psychotherapy to overcome challenges such as shame, distrust, and resource scarcity. |
| Approach: | They propose a cognitive reframing therapy method that uses empathetic dialogue to address deep-rooted negative thoughts and fosters rational, balanced perspectives. |
| Outcome: | The proposed model outperforms other models in terms of empathy, guidance, and logical coherence, demonstrating its effectiveness and potential positive impact on psychotherapy. |
Teaching Your Models to Understand Code via Focal Preference Alignment (2025.emnlp-main)
Copied to clipboard
Jie Wu, Haoling Li, Xin Zhang, Xiao Liu, Yangyu Huang, Jianwen Luo, Yizhen Zhang, Zuchao Li, Ruihang Chu, Yujiu Yang, Scarlett Li
| Challenge: | Existing methods for supervised fine-tuning focus on unit test feedback to construct preference pairs. |
| Approach: | They propose a preference alignment framework that mimics human iterative debugging to refine Code LLMs. |
| Outcome: | Experiments show that Preference Learning improves on BigCodeBench and BigCodeBind tasks. |
HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)
Copied to clipboard
Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, Deyi Xiong
| Challenge: | a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models . |
| Approach: | They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams . |
| Outcome: | The proposed model is based on o1-like models and a high-level model. |
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies treat named entity recognition as a sequential labeling problem. |
| Approach: | They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted . |
| Outcome: | The proposed framework outperforms competing models on four benchmark datasets. |
IndoCL: Benchmarking Indonesian Language Development Assessment (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent interest has surged in applying natural language processing (NLP) and machine learning (ML) to evaluate language development in both first (L1) and second (L2) language acquisition. |
| Approach: | They propose to use an Indonesian corpus as a benchmark for LDA tasks and to use existing large-scale language models to improve performance. |
| Outcome: | The proposed model extracts language-independent features, relieving laborious computation and reliance on specific language. |
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)
Copied to clipboard
Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
| Challenge: | Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. |
| Approach: | They propose a comprehensive benchmark covering 29 languages, built on an English benchmark. |
| Outcome: | The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark. |
Enhancing Multilingual Reasoning via Steerable Model Merging (2026.findings-acl)
Copied to clipboard
Zhuoran Li, Rui Xu, Jian Yang, Junnan Liu, Zhijun Chen, Qianren Mao, Hongcheng Guo, Jiaheng Liu, Likang Xiao, Ming LI, Xiaojie Wang
| Challenge: | Model merging is an effective technique for composing the capabilities of a multilingual model and a reasoning model. |
| Approach: | They propose a model merging framework that modulates the contribution of each source model. |
| Outcome: | Experiments show that the proposed model merging framework outperforms strong baselines on multilingual reasoning benchmarks across 21 different languages. |
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to lexically constrained neural machine translation suffer from high latency. |
| Approach: | They propose a plug-in algorithm for non-autoregressive translation for this problem . they propose ACT to familiarize the model with the source-side context of constraints . |
| Outcome: | The proposed model improves over the backbone constrained NAT model in constraint preservation and translation quality, especially for rare constraints. |
Task-Agnostic Low-Rank Adapters for Unseen English Dialects (2023.emnlp-main)
Copied to clipboard
| Challenge: | a recent study found that LLMs are trained on corpora disproportionally weighted in favor of Standard American English . prior work on dialect struggle with generalizing to evolving and emerging dialects in a scalable manner. |
| Approach: | They propose a method that leverages linguistic knowledge to enable resource-efficient adaptation . their method disentangles dialect-specific and cross-dialectal information . |
| Outcome: | a new method improves generalization to unseen dialects in a task-agnostic fashion . it achieves the best or most competitive performance across 5 dialects . |
Causality-aware Concept Extraction based on Knowledge-guided Prompting (2023.acl-long)
Copied to clipboard
| Challenge: | Concepts in knowledge graphs (KGs) are far from complete in existing knowledge graph models. |
| Approach: | They propose to equip a PLM-based extractor with a knowledge-guided prompt to alleviate concept bias by removing spurious co-occurrence correlations from existing knowledge. |
| Outcome: | The proposed prompt can alleviate concept bias and improve the performance of existing models. |
SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)
Copied to clipboard
| Challenge: | Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication. |
| Approach: | They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness. |
| Outcome: | The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%. |
NLP-ADBench: NLP Anomaly Detection Benchmark (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Anomaly detection (AD) is an important machine learning task, but its effectiveness in detecting harmful content, phishing attempts, and spam reviews is limited. |
| Approach: | They introduce NLP-ADBench, the most comprehensive NLP anomaly detection benchmark to date . it includes eight curated datasets and 19 state-of-the-art algorithms . |
| Outcome: | The NLP-ADBench benchmark includes 19 state-of-the-art methods and 8 curated datasets . no single model dominates across all datasets, indicating need for automated model selection . |
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are inherently dual-use and can be leveraged for both beneficial and harmful purposes. |
| Approach: | They propose a retention-prioritized gradient synthesis framework that decouples task-specific gradient extraction from conflict-aware combination. |
| Outcome: | The proposed method achieves tighter alignment on WMDP Bio and RWKU benchmarks. |
Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models (2026.findings-acl)
Copied to clipboard
He Xiao, Qingyao Yang, Dirui Xie, Wendong XU, Zunhai Su, Runming Yang, Haobo Liu, Wenyong Zhou, Zhengwu Liu, Ngai Wong
| Challenge: | Large language models with billions of parameters are often over-provisioned . smaller models exhibit lower robustness under extreme low-bit quantization . |
| Approach: | They propose a hardware-native, metric-driven post-training quantization framework that keeps uniform bit-width within each layer while mixing precision across layers. |
| Outcome: | LieQ reduces large accuracy gap observed for large language models with billions of parameters while preserving standard multiplication kernels. |
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)
Copied to clipboard
Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo
| Challenge: | Existing research on reinforcement learning for LLMs under data scarcity has not been unified. |
| Approach: | They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric. |
| Outcome: | The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area. |
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks assess basic Theory of Mind abilities but neglect temporal evolution of mental states in real-world social contexts. |
| Approach: | They propose a benchmark specifically designed to evaluate Large Language Models' ability to understand and track the temporal progression of mental states across interconnected scenarios. |
| Outcome: | The proposed benchmarks underperform humans by 44.7% and show that they can model the dynamic nature of human mental states better than existing models. |
Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have suggested that the composition of the pretraining corpus exerts a significant impact upon the performance of LLMs. |
| Approach: | They analyze the impact of 48 datasets from 5 major categories of pretraining data of Large Language Models and measure their impacts on LLMs using benchmarks about nine major categories. |
| Outcome: | The proposed analysis provides insights into the organization of data to support more efficient pretraining of Large Language Models. |
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are capable of detecting software vulnerabilities, but lack of reasoning data hinders their ability to capture underlying vulnerability patterns. |
| Approach: | They propose a framework that excels at mining vulnerability patterns through reasoning data synthesizing and vulnerability-specific preference optimization. |
| Outcome: | The proposed framework improves on SVEN and PrimeVul datasets and improves 12.24%-22.77% accuracy. |
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)
Copied to clipboard
Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin
| Challenge: | Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain . |
| Approach: | They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora. |
| Outcome: | The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions. |
Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns (2025.acl-long)
Copied to clipboard
| Challenge: | Currently, LLMs learn in a data-driven schema while the instructions about complex tasks are both scarce and hard to collect or construct. |
| Approach: | They employ a gradient-based method to dissect the process that the Supervised Fine-tuning Process (SFT) adapts LLMs to downstream tasks via the perspective of attention patterns. |
| Outcome: | The proposed method dissects the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns. |
COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing paradigms treat facts independently or employ myopic search, failing to optimize collective subgraph utility. |
| Approach: | They propose a framework that formalizes evidence retrieval as a constrained submodular maximization problem. |
| Outcome: | The proposed framework captures the trade-off between information relevance and structural complexity. |
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on the models, neglecting the full deployment pipeline . previous studies have underestimated the practical success of these attacks . |
| Approach: | They evaluate the effectiveness of jailbreak attacks targeting LLM safety alignment . they highlight critical gaps and call for further refinement of detection accuracy and usability . |
| Outcome: | The proposed attacks can detect at least one safety filter across the entire deployment pipeline. |
Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework (2025.findings-emnlp)
Copied to clipboard
Bohao Yang, Dong Liu, Chenghao Xiao, Kun Zhao, Chen Tang, Chao Li, Lin Yuan, Yang Guang, Chenghua Lin
| Challenge: | Large Language Models (LLMs) are capable of generating human-like text, but the potential for freely customisable characters remains underexplored. |
| Approach: | They propose a framework which employs Large Language Models to create freely customisable characters through personalised characteristic feature injection. |
| Outcome: | The proposed framework provides valuable insights for developing more accurate and customisable human simulacra. |
Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions (2026.acl-long)
Copied to clipboard
Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong
| Challenge: | Existing methods for geometry theorem proving in Euclidean geometry are challenging and require a neural network to perform. |
| Approach: | They propose a method for adding auxiliary points in geometry that runs on CPUs without relying on neural network-based inference. |
| Outcome: | The proposed method achieves silver-medal-level human performance on IMO-30 benchmark. |
Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)
Copied to clipboard
Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge. |
| Approach: | They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy. |
| Outcome: | The proposed model protects private data while enhancing the model's knowledge. |
Prior Relational Schema Assists Effective Contrastive Learning for Inductive Knowledge Graph Completion (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing knowledge graphs lack robustness and incompleteness to provide link prediction. |
| Approach: | They propose to capture prior schema-level interactions related to relations by leveraging entity type information and introduce schema-guided negatives to bolster the efficiency of normal contrastive representation learning. |
| Outcome: | The proposed method achieves state-of-the-art performance on multiple established metrics across multiple datasets for link prediction. |
AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting (2025.findings-acl)
Copied to clipboard
| Challenge: | Keyword spotting (KWS) is a useful mechanism to identify spoken commands in voice-enabled systems, but catastrophic forgetting is causing models to lose their ability to recognize earlier keywords. |
| Approach: | They propose an exemplar-free method that updates model parameters without revisiting earlier data. |
| Outcome: | The proposed method outperforms existing continual learning methods on a variety of datasets and settings. |
Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)
Copied to clipboard
Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li
| Challenge: | Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate . |
| Approach: | They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module. |
| Outcome: | The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks . |
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. |
SpiderFlow: Efficient Topology-Aware Scheduling for LLM Training Across Decentralized GPU Clusters (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training large language models lack topologyaware task scheduling mechanisms and model parallelization strategies. |
| Approach: | They propose a topology-aware scheduling system specifically designed for decentralized GPU clusters . they propose heuristic methods at the inter-cluster level with ILP-based optimization within clusters. |
| Outcome: | The proposed system reduces job completion time by 1.2-1.3 and improves throughput by 1.12-1.25 . it also reduces scheduling overhead by 20-90 on average compared to state-of-the-art scheduling systems. |
Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts (2026.tacl-1)
Copied to clipboard
| Challenge: | Evaluating natural language generation systems is challenging due to the diversity of valid outputs. |
| Approach: | They propose an inversion learning method that learns effective reverse mappings from model outputs back to their input instructions. |
| Outcome: | The proposed method requires only a single evaluation sample and eliminates manual prompt engineering. |
DataLab: A Platform for Data Analysis and Intervention (2022.acl-demo)
Copied to clipboard
Yang Xiao, Jinlan Fu, Weizhe Yuan, Vijay Viswanathan, Zhoumianze Liu, Yixin Liu, Graham Neubig, Pengfei Liu
| Challenge: | Existing tools and research focus on how to interpret and manipulate data, despite its crucial role in machine learning, . existing tools and researchers focus on systems on top of existing data, rather than how to use it. |
| Approach: | They propose a unified data-oriented platform that allows users to interactively analyze the characteristics of data and provides a standard interface for many data processing operations. |
| Outcome: | The proposed platform allows users to analyze the characteristics of data and provides a standardized interface so that many data processing operations can be provided within a single interface. |
CharacterGLM: Customizing Social Characters with Large Language Models (2024.emnlp-industry)
Copied to clipboard
Jinfeng Zhou, Zhuang Chen, Dazhen Wan, Bosi Wen, Yi Song, Jifan Yu, Yongkang Huang, Pei Ke, Guanqun Bi, Libiao Peng, JiaMing Yang, Xiyao Xiao, Sahand Sabour, Xiaohan Zhang, Wenjing Hou, Yijia Zhang, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Character-based dialogue systems (CharacterDial) allow users to customize social characters for social interactions. |
| Approach: | They will collect a large-scale Chinese corpus of characters with diverse categories and behaviors and develop CharacterGLM models to address these challenges. |
| Outcome: | Experiments show that CharacterGLM outperforms most popular open- and closed-source LLMs and performs comparable to GPT-4. |
GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models generate human-like content, but they also pose a problem with generation diversity, negatively impacting generation diversity and user experience. |
| Approach: | They propose a Logits-Addition watermark and three variants that aim to enhance diversity to overcome generation diversity challenges. |
| Outcome: | The Logits-Addition watermark outperforms the Logits+Trick-based watermark in diversity tests and outperformed other decoding-based methods by 0.1 to 0.3. |
What Makes an Ideal Quote? Recommending “Unexpected yet Rational” Quotations via Novelty (2026.acl-long)
Copied to clipboard
| Challenge: | Prior systems focus on topical relevance and overlook what makes quotes memorable. |
| Approach: | They propose a system that maps quotations and contexts into deep-meaning labels for label-enhanced retrieval. |
| Outcome: | The proposed system can recommend quotations that are contextually novel while semantically coherent. |
NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs (2026.acl-long)
Copied to clipboard
Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang, MuRun Yang, DingYang Lin, Kaiyan Chang, Tong Zheng, Bei Li, Peinan Feng, Quan Du, Tong Xiao, JingBo Zhu
| Challenge: | Large language models have significantly advanced Multilingual Machine Translation (MMT) yet scaling to many languages while maintaining robust performance across directions remains challenging. |
| Approach: | They propose a strategy to reduce the number of translations in one direction . they propose auxiliary parallel sentences to promote cross-lingual transfer . |
| Outcome: | The proposed model performs on par with or better than substantially larger baselines. |
BOOKWORLD: From Novels to Interactive Agent Societies for Story Creation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled social simulation through multi-agent systems. |
| Approach: | They propose a system for constructing and simulating book-based multi-agent societies that simulates established fictional worlds and characters. |
| Outcome: | The proposed system generates high-quality stories while maintaining fidelity to the source books, surpassing previous methods with a win rate of 75.36%. |
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, Xiao Huang
| Challenge: | Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) however, traditional RAG attacks are difficult to pose an effective threat to GraphRAg systems. |
| Approach: | They propose a novel attack framework that targets logical reasoning rather than injecting false contents into GraphRAG systems by grounding their responses in structured knowledge graphs. |
| Outcome: | The proposed framework outperforms state-of-the-art attacks on GraphRAG systems in both effectiveness and stealth. |
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)
Copied to clipboard
Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Zhou Xiao, Yang Yu, Jie Zhou
| Challenge: | Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications. |
| Approach: | They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts. |
| Outcome: | The proposed model outperforms existing models and improves on annotated documents. |
Generative Entity Typing with Curriculum Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Entity typing fails to assign an entity to the types beyond the predefined type set. |
| Approach: | They propose a generative entity typing paradigm that assigns types to entities . traditional classification-based approaches fail to assign entities to the types beyond the predefined set . they employ curriculum learning to train the model on heterogeneous data . |
| Outcome: | The proposed model outperforms the state-of-the-art model on heterogeneous training data. |
Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography (2026.acl-industry)
Copied to clipboard
Sudharshan Balaji, Zhiyu Liu, Zhengyuan Jiang, Shuo Lei, Yimin Chen, Yang Xiao, Shone O. Almeida, Mathew Joseph Karivelil, Christopher Malanga, Ning Wang
| Challenge: | CCTA reports provide an assessment of coronary disease severity to guide patient management. |
| Approach: | They propose a pipeline that decouples structuring from classification by an LLM-based parser . CCTA-RADS is the largest publicly available dataset of CCDA reports . |
| Outcome: | The proposed approach improves the F1-score by 6%-13% compared with direct methods. |
Coarse-to-Fine Grounded Memory for LLM Agent Planning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to enhance LLM with offline experiences or online trajectory analysis focus on single-granularity memory derived from dynamic environmental interactions. |
| Approach: | They propose a framework that grounds coarse-to-fine memories with LLM to enable flexible adaptation to diverse scenarios. |
| Outcome: | Extensive experiments on AlfWorld, Webshop and ScienceWorld show that the proposed framework outperforms baselines and comprehensively optimizes memory-enhanced LLM Agent system. |
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)
Copied to clipboard
Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu
| Challenge: | a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide. |
| Approach: | They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions . |
| Outcome: | The proposed agents are based on operating systems (OS) and operating systems frameworks. |
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective (2025.acl-long)
Copied to clipboard
Yiyao Yu, Yuxiang Zhang, Dongdong Zhang, Xiao Liang, Hengyuan Zhang, Xingxing Zhang, Mahmoud Khademi, Hany Hassan Awadalla, Junjie Wang, Yujiu Yang, Furu Wei
| Challenge: | Existing work shows that LLMs rely on single-paradigm reasoning that limits their effectiveness across diverse tasks. |
| Approach: | They propose a new framework that integrates multiple reasoning paradigms to enable synergistic collaboration. |
| Outcome: | The proposed model outperforms current SOTA models in theorem proving tasks and the MATH benchmark in arithmetic tasks. |
MultiAgentESC: A LLM-based Multi-Agent Collaboration Framework for Emotional Support Conversation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on generating responses directly and neglect integration of domain-specific reasoning and expert interaction. |
| Approach: | They propose a training-free multi-agent collaboration framework for ESC to emulate human-like process of providing emotional support through dialogue analysis, strategy deliberation, and response generation. |
| Outcome: | The proposed framework excels at providing emotional support and diversifying support strategy selection. |
Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026.acl-long)
Copied to clipboard
Hengyuan Zhang, Shiping Yang, Xiao Liang, Chenming Shang, Yuxuan Jiang, Chaofan Tao, Jing Xiong, Hayden Kwok-Hay So, Ruobing Xie, Angel X. Chang, Ngai Wong
| Challenge: | Existing studies show that stronger models are not always optimal teachers, suggesting a mismatch between the teacher’s output and the student’s learning ability. |
| Approach: | They propose a method that routes each prompt to its optimal teacher via a query-level router that jointly considers the student models’ learnability and teacher models’ response quality. |
| Outcome: | The proposed method outperforms baselines on six benchmarks including instruct tuning and math reasoning settings. |
Multi-Task Neural Model for Agglutinative Language Translation (2020.acl-srw)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has been gaining popularity in high-resource translation tasks, but struggles in low-ressource and morphologically-rich scenarios. |
| Approach: | They propose a multi-task neural model that jointly learns to perform bi-directional translation and agglutinative language stemming. |
| Outcome: | The proposed model can significantly improve translation performance on agglutinative languages by using a small amount of monolingual data. |
Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing, Qingyi Si, Zhuoran Li, Weikang Gong, Deqing Yang, Yanghua Xiao, Hongcheng Guo
| Challenge: | Group Relative Policy Optimization (GRPO) uses a coarse-grained credit assignment mechanism that propagates group-level rewards uniformly to to every token in a sequence, neglecting the varying contribution of individual reasoning steps. |
| Approach: | They introduce Outcome-grounded Advantage Reshaping (OAR) which redistributes advantages based on how much each token influences the model’s final answer. |
| Outcome: | Empirical results show that OAR-G outperforms GRPO on a high-fidelity attribution signal and suppresses low-impact tokens while preserving the advantage mass. |
Large Language Models Are Still Misled by Simple Bias Ensembles (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for large language models are constrained to datasets where each sample is manually injected with only one type of bias. |
| Approach: | They propose a multi-bias benchmark where each sample contains multiple types of biases. |
| Outcome: | The proposed benchmark shows that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating compounded biases. |
Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) allow repeatable experiments in which individual characteristics can be precisely defined. |
| Approach: | They propose a scalable experimental paradigm using Large Language Models to simulate multi-stage supply chain dynamics. |
| Outcome: | The proposed model systematically replicates and validates the results of a behavioral simulation on agents in multi-stage supply chain dynamics. |
APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation (2026.findings-acl)
Copied to clipboard
Dongliang Chen, Xinlin Zhuang, Junjie Xu, Luojian Xie, Zehui Wang, Jiaxi Zhuang, Haolin Yang, Liang Dou, Xiao He, Xingjiao Wu, Ying Qian
| Challenge: | APEX optimizes for text-to-image generation by combining learning potential, conflict penalty, and progress need. |
| Approach: | They propose an algorithm that stabilizes heterogeneous rewards and dynamically schedules objectives . they propose a method that achieves better Pareto trade-offs across four heterogenous objectives based on P3 Adaptive Priorities . |
| Outcome: | The proposed algorithm achieves better pareto trade-offs across four heterogeneous objectives while maintaining competitive OCR accuracy. |
P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks (2022.acl-short)
Copied to clipboard
| Challenge: | Existing methods of prompt tuning cannot handle hard sequence labeling tasks. |
| Approach: | They propose to optimize prompt tuning to tune continuous prompts with a frozen language model. |
| Outcome: | The proposed method matches finetuning with prompt tuning while having only 0.1%-3% tuned parameters. |
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2026.acl-long)
Copied to clipboard
Keyu Li, Junhao Shi, Yang Xiao, Mohan Jiang, Jie Sun, Yunze Wu, Dayuan Fu, Shijie Xia, Xiaojie Cai, Tianze Xu, Weiye Si, Wenjie Li, Dequan Wang, Pengfei Liu
| Challenge: | Existing benchmarks focus on single agentic capability, failing to capture long-horizon real-world scenarios. |
| Approach: | They propose a benchmark that evaluates 6 agentic capabilities across 32 real-world scenarios. |
| Outcome: | Experiments show that closed-source models outperform open-source model (48.4% vs 32.1%) integrating models with advanced scaffolds to form autonomous agents is a paradigm shift. |
CONSTRUCTURE: Benchmarking CONcept STRUCTUre REasoning for Multimodal Large Language Models (2024.findings-emnlp)
Copied to clipboard
Zhiwei Zha, Xiangru Zhu, Yuanyi Xu, Chenghua Huang, Jingping Liu, Zhixu Li, Xuwu Wang, Yanghua Xiao, Bei Yang, Xiaoxiao Xu
| Challenge: | Existing multimodal large language models lack the ability to perceive the visual world with a deep concept structure cognition. |
| Approach: | They propose a concept-level benchmark to assess MLLMs’ hierarchical concept understanding and reasoning abilities. |
| Outcome: | The proposed model outperforms state-of-the-art models in concept structure reasoning evaluation. |
UNIVID: Unified Vision-Language Model for Video Moderation (2026.acl-industry)
Copied to clipboard
Kejuan Yang, Yizhuo Zhang, Mingyuan Du, Yue Zhang, Dixin Zheng, Kaili Zhao, Yang Xiao, Hanzhong Liang, Kenan Xiao
| Challenge: | Existing video moderation systems rely on fragmented black-box classification models that are difficult to maintain and lack transparency. |
| Approach: | They propose a Unified Vision-Language model for Video Moderation that generates policy-aware captions that serve as an interpretable intermediate representation. |
| Outcome: | The proposed model reduces violation leakage and overkill rate by 42.7% while reducing maintenance costs. |
Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing prompt-based methods craft meticulous text guidelines and examples to facilitate SQL generation, but their accuracy is hindered by the large semantic gap between the texts and the low-resource SQL programs. |
| Approach: | They propose to use Python as a pivot to bridge between natural language query and SQL program. |
| Outcome: | The proposed method improves the execution accuracy of the best-performing baseline by up to 3.20. |
Why Can Distillation Work with Limited Resources? A Systematic Study (2026.findings-acl)
Copied to clipboard
Xiao Hu, Xingyu Lu, Liyuan Mao, YiFan Zhang, Tianke Zhang, Bin Wen, Fan Yang, Tingting Gao, Guorui Zhou
| Challenge: | Recent advances in large language models have driven reasoning performance . low-resource distillation can boost models' performance, but a framework is missing . |
| Approach: | They conduct a controlled experiment to find out why low-resource distillation can boost model performance . they find that distillation enhances the presence of advanced cognitive behaviors . |
| Outcome: | The proposed model shows more flexible reasoning, the authors show . they show that distillation enhances the presence of advanced cognitive behaviors . |
ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger (2024.naacl-long)
Copied to clipboard
| Challenge: | Textual backdoor attacks are increasingly challenging to detect due to the use of advanced generative models such as GPT-4. |
| Approach: | They propose a framework that harnesses advanced generative models to execute stealthier backdoor attacks on text classifiers. |
| Outcome: | The proposed framework achieves state-of-the-art attack success rate of 97.35% over four sentiment classification tasks and four human cognition stealthiness tests. |
Online Iterative Self-Alignment for Radiology Report Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for RRG rely on supervised fine-tuning based on data pairs of radiological images and corresponding radiologist-annotated reports. |
| Approach: | They propose a method that performs supervised fine-tuning on data pairs of radiological images and corresponding radiologist-annotated reports. |
| Outcome: | The proposed method surpasses existing methods and achieves state-of-the-art performance across multiple evaluation metrics. |
Polymorphic Universal Transformer (2026.acl-long)
Copied to clipboard
Yilong Chen, Zitian Gao, Yihao Xiao, Jason Klein Liu, Xinyu Yang, Yifan Luo, Haoming Luo, Zhengmao Ye, Tingwen Liu, Ran Tao, Bryan Dai
| Challenge: | Compute Distribution Skew is a pathological phenomenon in ultra-deep recurrent models . it causes over-smoothing, representation rank collapse, and degraded reasoning performance. |
| Approach: | They propose a dynamic architecture that redefines recursive computation by decoupling parameter count from depth. |
| Outcome: | The proposed model significantly improves representation rank and reasoning robustness while reducing computation by 64.7%. |
Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have focused on word analogies, but they neglect structures that underpin analogical reasoning. |
| Approach: | They propose a task to abduct structures that form an analogy between two systems to evaluate their analogical reasoning abilities. |
| Outcome: | The proposed task is based on 400 scientific analogies from 13 different fields and is compared with a standard SCAR benchmark. |
SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026.findings-acl)
Copied to clipboard
Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Lintao Ma, Xingyu Lu, Jun Zhou, Pengfei Liu, Jiancan Wu, Xiang Wang
| Challenge: | Existing large-scale large-context models suffer from performance degradation when processing long numerical sequences. |
| Approach: | They propose a framework to mitigate attention dispersion by strategically inserting separator tokens into the model to recalibrat attention to local segments while preserving global context. |
| Outcome: | The proposed framework improves accuracy and reduces inference token consumption by 16.4% on 9 widely-adopted LLMs. |
Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications (2026.acl-long)
Copied to clipboard
| Challenge: | Existing safety evaluation paradigms rely on constructed benchmarks or dynamic red-teaming to probe potential vulnerabilities. |
| Approach: | They propose a framework that integrates specification-based software testing with AI safety. |
| Outcome: | The proposed framework achieves higher coverage and attack success counts compared to baselines. |
Allies: Prompting Large Language Model with Beam Search (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to build LLMs with stacking are limited by their information coverage and low fault tolerance. |
| Approach: | They propose a method that leverages large language models to iteratively generate new queries from an input query. |
| Outcome: | The proposed method outperforms baselines on open-domain question answering benchmarks. |
FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation (2025.acl-long)
Copied to clipboard
Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo
| Challenge: | Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years, but there is a notable lack of effective and specialized multimodal evaluation datasets in the financial domain. |
| Approach: | They introduce FinMME, a multimodal large language model with 11,000 financial research samples and 20 annotators. |
| Outcome: | The proposed model performs better than state-of-the-art models, highlighting its challenging nature. |
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)
Copied to clipboard
Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). |
| Approach: | They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other. |
| Outcome: | The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters. |
Modeling Semantic Compositionality with Sememe Knowledge (P19-1)
Copied to clipboard
| Challenge: | Semantic compositionality (SC) is defined as the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents. |
| Approach: | They propose to incorporate sememes into SC models and employ them in learning multiword expressions. |
| Outcome: | The proposed models achieve significant performance boost compared to baseline methods without sememe knowledge. |
StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models struggle to maintain temporal, spatial, and narrative coherence across image sequences . existing models lack depth and engagement of human-authored stories . |
| Approach: | They propose a topic-driven narrative optimizer that integrates image descriptions, topic generation, and GPT-4-based refinements. |
| Outcome: | The proposed framework outperforms existing models in visual relevance, coherence, and fluency. |
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Xiaolong Wei, Zerun Zhu, Simin Niu, Xingyu Zhang, Peiying Yu, Changxuan Xiao, Yuchen Li, Jicheng Yang, Zhejun Zhao, Chong Meng, Long Xia, Daiting Shi
| Challenge: | Existing alignment paradigms for creative writing use static reward signals and supervised data. |
| Approach: | They propose a constraint-aware reward model that synthesizes query-specific criteria to provide fine-grained preference judgments. |
| Outcome: | The proposed framework aligns models with human preferences across content quality and structural paradigms without supervised fine-tuning and ground-truth references. |
Contrastive Learning with Adversarial Examples for Alleviating Pathology of Language Model (2023.acl-long)
Copied to clipboard
| Challenge: | Existing interpretation methods fail to obtain faithful attributions on these models, thereby failing to reveal potential flaws and biases. |
| Approach: | They propose a Contrastive learning regularization method which calibrates the sentence representation of out-of-distribution examples and utilizes adversarial examples to introduce direction information in regularization. |
| Outcome: | The proposed method alleviates the model pathology while impacting generalization ability on in-distribution examples and thus helps interpretation methods obtain more faithful results. |
Distilling Script Knowledge from Large Language Models for Constrained Language Planning (2023.acl-long)
Copied to clipboard
Siyu Yuan, Jiangjie Chen, Ziquan Fu, Xuyang Ge, Soham Shah, Charles Jankowski, Yanghua Xiao, Deqing Yang
| Challenge: | Existing work exploits language models to plan for abstract goals of stereotypical activities, but leaves more specific goals with multi-facet constraints understudied. |
| Approach: | They propose an over-generate-then-filter approach to improve large language models on constrained language planning task by distilling a constrained script dataset. |
| Outcome: | The proposed approach improves the constrained language planning ability of large language models on constraint faithfulness and also in smaller LMs. |
Navigating the OverKill in Large Language Models (2024.acl-long)
Copied to clipboard
Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin
| Challenge: | Recent studies have highlighted a tendency among large language models to refuse to answer benign queries. |
| Approach: | They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding. |
| Outcome: | The proposed approach reduces the refusal rate by 20% while having little impact on safety. |
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance (2026.acl-long)
Copied to clipboard
Yuchun Fan, Bei Li, Peiguang Li, Yilin Wang, Yongyu Mu, Jian Yang, Xin Chen, Rongxiang Weng, Jingang Wang, Xunliang Cai, JingBo Zhu, Tong Xiao
| Challenge: | Existing methods for enhancing multi-step reasoning have not fully translated to multilingual contexts. |
| Approach: | They propose a framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks. |
| Outcome: | Empirical results show that the proposed framework improves reasoning performance without compromising language consistency. |