Papers by Dong Yu
Verified Critical Step Optimization for LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Critical Step Optimization (CSO) focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Approach: | They propose a method which focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Outcome: | The proposed method outperforms the existing methods on GAIA-Text-103 and XBench-DeepSearch while requiring supervision at only 16% of trajectory steps. |
Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing supervised models struggle to make correct predictions on rare word senses due to limited training data. |
| Approach: | They propose a gloss alignment algorithm that can align definition sentences with the same meaning from different sense inventories to collect rich lexical knowledge. |
| Outcome: | The proposed method outperforms previous methods on both frequent and rare word senses. |
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large reasoning models have performance enhancements but still suffer from shortcomings due to limitations of the underlying language models. |
| Approach: | They propose a framework that allows the model to choose when to trust or ignore the tool results based on the confidence score of generated code blocks. |
| Outcome: | The proposed framework reduces the "Tool Ignored" issue by 4.1% to 7.5%. |
Friend-training: Learning from Models of Different but Related Tasks (2023.eacl-main)
Copied to clipboard
| Challenge: | Current self-training methods focus on improving model performance on a single task. |
| Approach: | They propose a cross-task self-training framework where models trained to do different tasks are used in iterative training, pseudo-labeling, and retraining processes to help each other for better selection of pseudo-labeled labels. |
| Outcome: | The proposed framework achieves the best performance compared to baselines on two dialogue understanding tasks. |
When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives (2024.emnlp-main)
Copied to clipboard
| Challenge: | Using sports data, an LLM can analyze sports narratives to infer points from actions, identify related entities, attribute points accurately to players and teams, and draw conclusions. |
| Approach: | They propose a method to synthesize NBA basketball game narratives using real NBA basketball data and propose 'SportsGen' they find that most models fail to accurately aggregate basketball scores due to frequent scoring patterns and open-source models suffer from significant score hallucinations. |
| Outcome: | The proposed method can evaluate LLMs’ reasoning capabilities under complex scenarios with varying narrative lengths and density of information. |
Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models require associated image with input sentence, which is difficult to satisfy at inference. |
| Approach: | They propose to use synthetic and authentic images to generate translations using text-to-image generation models. |
| Outcome: | The proposed model achieves state-of-the-art performance on En-De and En-Fr datasets while remaining independent of authentic images during inference. |
Recall with Reasoning: Chain-of-Thought Distillation for Mamba’s Long-Context Memory and Extrapolation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing long-context memory methods such as Mamba struggle with long-constituency when the length of the processed text exceeds the model's training length. |
| Approach: | They propose a method that uses chain-of-thought summarization to teach Mamba to actively recall and reason over long contexts. |
| Outcome: | Experiments on LONGMEMEVAL and HELMET show that RwR outperforms existing long-term memory methods while preserving short-context capabilities. |
SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing closed-source LLMs have a performance gap in text-to-SQL reasoning tasks. |
| Approach: | They propose a SQL-based approach to synthesize reliable data to enhance text-to-SQL reasoning in LLMs. |
| Outcome: | The proposed model achieves state-of-the-art accuracy on the widely recognized Spider and BIRD benchmarks, significantly narrowing the performance gap with closed-source methods. |
Exophoric Pronoun Resolution in Dialogues with Topic Regularization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on pronoun coreference resolution focus on anaphora and cataphores . exophoric pronounos are common in daily communications, but can be disambiguated by general topics of the dialogue. |
| Approach: | They propose to leverage local context and global topics of dialogues to solve out-of-text PCR problem by adding topic regularization. |
| Outcome: | Extensive experiments show that topic regularization can be used to solve the out-of-text PCR problem. |
The Impact of Reasoning Step Length on Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Long reasoning steps in LLMs improve reasoning abilities, but the correlation between their effectiveness and the length of reasoning steps remains largely unknown. |
| Approach: | They conducted experiments that expand and compress the rationale reasoning steps within CoT demonstrations while keeping all other factors constant. |
| Outcome: | The results show that lengthening the reasoning steps in prompts significantly enhances LLMs’ reasoning abilities across multiple datasets. |
BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition (2025.coling-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) that aims to detect the entity spans of text and classify them into pre-defined set of entity types. |
| Approach: | They propose a boundary-aware contrastive learning strategy to enhance the LLM’s ability to perceive entity boundaries for generalized entity spans. |
| Outcome: | The proposed framework outperforms prior methods and validates its effectiveness across a range of LLM architectures. |
OpenWebAgent: An Open Toolkit to Enable Web Agents on Large Language Models (2024.acl-demos)
Copied to clipboard
Iat Long Iong, Xiao Liu, Yuxuan Chen, Hanyu Lai, Shuntian Yao, Pengbo Shen, Hao Yu, Yuxiao Dong, Jie Tang
| Challenge: | OpenWebAgent integrates large language models and large multimodal models to improve web automation. |
| Approach: | They propose to integrate large language models and large multimodal models into an open toolkit to optimize web automation. |
| Outcome: | The open toolkit integrates both large language models (LLMs) and large multimodal models (LMMs) it enables the development of powerful, task-oriented web agents, significantly enhancing user experience and operational efficiency on the web. |
Event Semantic Classification in Context (2024.findings-eacl)
Copied to clipboard
| Challenge: | In this work, we focus on the semantic classification of events in context to help machines gain a deeper understanding of events. |
| Approach: | They propose to integrate event semantics into downstream tasks to help machines understand events better. |
| Outcome: | The proposed model improves the understanding of events in context. |
Self-Consistency Boosts Calibration for Math Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing solutions for math reasoning tasks use semantic parsing or AST decoding, but performance can degrade dramatically even with slight changes to the questions. |
| Approach: | They propose three calibration methods based on self-consistency for math reasoning tasks. |
| Outcome: | The proposed methods bridge model confidence and accuracy better than existing methods based on p(True) or logit. |
CLOMO: Counterfactual Logical Modification with Large Language Models (2024.acl-long)
Copied to clipboard
Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song
| Challenge: | Existing studies on evaluating model reasoning are limited in both form and content. |
| Approach: | They propose a task to cultivate counterfactual thought processes within large language models and an evaluation metric to evaluate their natural language output instead of modeling the task as a multiple-choice problem. |
| Outcome: | The proposed evaluation metric aligns well with human preference. |
Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on the confidence calibration of LLMs have not explored the effects of different prompting strategies on LLM performance. |
| Approach: | They propose Fact-and-Reflection prompting which improves LLM confidence calibration . they propose to use human cognition to elicit known "facts" and ask model to "reflect" over them . |
| Outcome: | The proposed method lowers the expected calibration error by 23.5% on multi-purpose QA tasks. |
Generating User-Engaging News Headlines (2023.acl-long)
Copied to clipboard
| Challenge: | Personalized news recommendation systems present the same headline to all users, making it difficult for them to understand the connection between their interests and the recommended article. |
| Approach: | They propose a framework that incorporates user profiling to generate personalized headlines and a combination of automated and human evaluation methods to determine user preference for personalized headline generation. |
| Outcome: | The proposed framework can generate personalized headlines that meet the needs of a diverse audience. |
Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective (2025.acl-long)
Copied to clipboard
| Challenge: | a number of attention-based large language models (LLMs) focus on individual head contributions, but the precise interaction mechanisms between attention heads remain poorly understood. |
| Approach: | They propose a game-theoretic attention calibration method that uses the Harsanyi dividend . they selectively retain heads demonstrating significant cooperative gains and apply fine-grained adjustments to remaining heads . |
| Outcome: | The proposed framework is based on the Harsanyi dividend, a concept from cooperative game theory. |
DeFine: Decision-Making with Analogical Reasoning over Factor Profiles (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models are ideal for decision-making, but they can be difficult to process when they are verbose and include repetition, hedging, and vagueness. |
| Approach: | They propose a framework that constructs probabilistic factor profiles from complex scenarios and integrates them with analogical reasoning to guide LLMs in making decisions in new situations. |
| Outcome: | The proposed framework separates the tasks of quantifying uncertainty and incorporating it into LLM decision-making. |
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. |
Inconsistent dialogue responses and how to recover from them (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods to assess and bolster utterance consistency of chat systems have been shown difficult to detect. |
| Approach: | They propose to use annotators to write dialogue responses and recovery utterances to assess and bolster utteration consistency of chat systems. |
| Outcome: | The proposed dataset significantly improves the detection and resolution of inconsistencies in chat conversations. |
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)
Copied to clipboard
Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Jinchuan Tian, Zhenhui Ye, Luping Liu, Zehan Wang, Ziyue Jiang, Xuankai Chang, Jiatong Shi, Chao Weng, Zhou Zhao, Dong Yu
| Challenge: | Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages. |
| Approach: | They propose to use large language models as a general-purpose interface across multiple tasks and languages. |
| Outcome: | The proposed model performs better on 200K hours of 6-language data for voice generation applications. |
How do Words Contribute to Sentence Semantics? Revisiting Sentence Embeddings with a Perturbation Method (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on sentence representation learning focus on human annotation, but they neglect the critical property that essential contents should contribute to sentence semantics more than non-essential contents when encoding a sentence. |
| Approach: | They propose a perturbation method for unsupervised semantic analysis that uses a sentence compression metric to adapt sentence compression datasets for automatic evaluation. |
| Outcome: | The proposed method can capture the main semantics of sentences better than several SOTA unsupervised sentence embedding models. |
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for text generation ignore faithfulness between generated text and table . current methods ignore faithfulity, leading to generated information that goes beyond table content . |
| Approach: | They propose a Transformer-based generation framework to enforce faithfulness between generated text and table . they propose metric to evaluate faithfulness and automatic metric for automatic generating . |
| Outcome: | The proposed framework outperforms state-of-the-art methods in automatic evaluations and human evaluations. |
C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References (2022.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to pretrain open-domain question answering systems lack task-specific annotations. |
| Approach: | They propose to pretrain a two-stage open-domain question answering system with strong transfer capabilities by using a dictionary and a large-scale corpus. |
| Outcome: | The proposed approach leads to 2%-10% gains in top-20 accuracy and improves with reader. |
Multiplex Word Embeddings for Selectional Preference Acquisition (D19-1)
Copied to clipboard
| Challenge: | Existing word embeddings are limited in their ability to represent fixed vectors . instead, they incorporate relational dependencies of different words into their embeddables - a limitation that is addressed by a multiplex model . |
| Approach: | They propose a word embedding model which incorporates relational dependencies of different words into their embeddables. |
| Outcome: | The proposed model can be easily extended according to various relations among words. |
Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations (2024.naacl-long)
Copied to clipboard
Sihao Chen, Hongming Zhang, Tong Chen, Ben Zhou, Wenhao Yu, Dian Yu, Baolin Peng, Hongwei Wang, Dan Roth, Dong Yu
| Challenge: | Sentence embeddings are typically learned to recognize the semantic relation between two text inputs. |
| Approach: | They introduce a contrastively-learned contextual embedding model for fine-grained semantic representation of text. |
| Outcome: | The proposed model is able to produce contextual embeddings corresponding to different atomic propositions, i.e. semantic equivalence between propositions across different text sequences. |
VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents (2026.findings-acl)
Copied to clipboard
Jiliang Hu, Wenfu Wang, Zuchao Li, Chenxing Li, Yiyang Zhao, Hanzhao Li, Liqiang Zhang, Meng Yu, Dong Yu
| Challenge: | despite advances in multimodal conversational systems, current benchmarks lack comprehensive evaluation across key dimensions. |
| Approach: | They propose a Chinese benchmark built exclusively on real human speech to fill this gap . they assess LALMs across three complementary axes: instruction following, knowledge understanding, robustness . |
| Outcome: | VCB Bench assesses LALMs across three complementary axes: instruction following, knowledge understanding, and robustness . VCBM Bench provides reproducible and fine-grained framework for Chinese voice chat bots . results show significant performance disparities and offer tangible insights for future improvements . |
Better Highlighting: Creating Sub-Sentence Summary Highlights (2020.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive summarizations are considered to be less reliable because they distort the original meaning and can be confusing for readers. |
| Approach: | They propose a method to generate summary highlights that are understandable on their own to avoid confusion. |
| Outcome: | The proposed method allows summaries to be understood in context and avoids misdirecting readers to false conclusions. |
Semantic Role Labeling Guided Multi-turn Dialogue ReWriter (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing attentive models attend to all words without prior focus, which results in inaccurate concentration on some dispensable words. |
| Approach: | They propose to use semantic role labeling to provide additional guidance for multi-turn dialogue rewriting models. |
| Outcome: | The proposed model outperforms existing models on multi-turn dialogue rewriting tasks. |
Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents (2023.findings-eacl)
Copied to clipboard
Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, Wee Sun Lee
| Challenge: | Existing datasets do not cover documents with complex spatial structures and a lack of spatial information for document entity classification. |
| Approach: | They propose a new spatial bias in attention calculation based on the K-nearest-neighbor graph of document entities that limits entities’ attention to their local radius. |
| Outcome: | The proposed model outperforms baselines in most entity types and is highly parameter-efficient compared to existing methods. |
Uncertainty-Aware Test-Time Search for Optimization Problem Solving (2026.acl-long)
Copied to clipboard
Linlin Yu, Xujiang Zhao, Dong Li, Yanchi Liu, Wei Cheng, Zhengzhang Chen, Chen Zhao, Feng Chen, Haifeng Chen
| Challenge: | Language model hallucinations and limited availability of labeled datasets often result in misaligned formulations, code errors and feasibility failures. |
| Approach: | They propose a Monte Carlo Tree Search framework that automates optimization problems from natural language descriptions with efficiency and reliability. |
| Outcome: | The proposed framework achieves state-of-the-art solution accuracy and reduces token usage. |
SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are being used in urban planning but there is concern that they reproduce or amplify such biases. |
| Approach: | They propose a framework to evaluate spatial gender bias in large language models . they use a taxonomy of 62 urban micro-spaces, a prompt library and three diagnostic layers . |
| Outcome: | The proposed framework identifies structured gender-space associations that go beyond the public-private divide, forming nuanced micro-level mappings. |
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Knowledge-based open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. |
| Approach: | They propose a benchmark for evaluating multi-source dialogue knowledge selection and response generation using Wikipedia's wizard of Wikipedia. |
| Outcome: | The proposed benchmark is called multi-source Wizard of Wikipedia (Ms.WoW) it contains clean support knowledge, grounded at the utterance level and partitioned into multiple knowledge sources. |
Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination (2022.emnlp-main)
Copied to clipboard
| Challenge: | Large-scale pretrained language models suffer from reporting bias, describing the lack of explicit commonsense knowledge in written text. |
| Approach: | They propose to endow language models with visual imagination capabilities by recalling existing images and synthesizing nonexistent images via text-to-image generation. |
| Outcome: | The proposed model improves the performance of existing language models across a diverse set of language tasks. |
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms (2026.eacl-short)
Copied to clipboard
| Challenge: | Recent studies have adopted a greedy one-way search strategy to deal with dynamic web environments. |
| Approach: | They propose to integrate a rollback mechanism into web agents to allow them to revert back to a previous state in navigation trajectory. |
| Outcome: | The proposed method is able to revert back to a previous state in its navigation trajectory, allowing the models to directly control the search process. |
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (P18-1)
Copied to clipboard
| Challenge: | Existing models for matching dialogue responses rely on semantic and functional dependencies . a recent study only uses the last utterance in context for matching a reply . |
| Approach: | They propose a model that matches a response with its multi-turn context using attention. |
| Outcome: | The proposed model outperforms the state-of-the-art models on two large-scale multi-turn response selection tasks. |
Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | State-of-the-art language models (LMs) sometimes generate that misalign with world knowledge. |
| Approach: | They propose a method to mitigate hallucinations by restoring the LM's internal fact recall pipeline by a targeted restoration of its internal fact-recall pipeline. |
| Outcome: | The proposed method shows superior performance compared to baselines. |
Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making (2021.acl-long)
Copied to clipboard
| Challenge: | Entity Matching (EM) aims at recognizing entity records that denote the same real-world object. |
| Approach: | They propose a novel EM framework that consists of Heterogeneous Information Fusion and Key Attribute Tree Induction to decouple feature representation from matching decision. |
| Outcome: | The proposed framework outperforms SOTA EM models on 6 public datasets and 3 industrial datasets. |
Seeking Rational Demonstrations for Large Language Models: A Domain Generalization Approach to Unsupervised Cross-Domain Keyphrase Generation (2025.acl-short)
Copied to clipboard
| Challenge: | Unsupervised cross-domain keyphrase generation is crucial in real-world natural language processing scenarios, but its accuracy is limited by the distribution shift between source and target domain. |
| Approach: | They propose to seek rational demonstrations from the source domain and to use them to improve their ability in the unsupervised cross-domain keyphrase generation setting. |
| Outcome: | The proposed model achieves state-of-the-art on widely used cross-domain KG benchmarks and the results are published in the journal Nature. |
FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to correct factually inaccurate outputs are lacking the semantic richness needed to properly understand its internal states of trustworthiness and honesty. |
| Approach: | They propose a framework for factuality alignment that integrates natural-language uncertainty signals with external knowledge and computes confidence scores and semantic entropy from LLM outputs. |
| Outcome: | Extensive experiments on four knowledge-intensive benchmarks show that FAITH improves the factual accuracy and truthfulness of Large Language Models (LLMs). |
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack (2024.acl-long)
Copied to clipboard
| Challenge: | Recent developments in balancing usefulness and safety of large language models raise a critical question . current attacks, especially adversarial ones that manipulate malicious prompts, often aim to manipulate the input . |
| Approach: | They show that LLMs can effectively summarize malicious long documents but often refuse to translate them. |
| Outcome: | The findings highlight a vulnerability in LLMs that can't translate or summarize documents . the study focuses on LLM models, Gemini and GPT-4, which can' be exploited . |
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for generating paragraph descriptions for videos require a coherent paragraph and a higher level of coherence. |
| Approach: | They propose a new method that generates a summarized memory state from video segments and sentence history to help better predict the next sentence. |
| Outcome: | The proposed method generates more coherent and less repetitive paragraph captions while maintaining relevance to the input video events. |
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization (2025.acl-long)
Copied to clipboard
Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, Dong Yu
| Challenge: | Existing studies focus on building text-only agents in synthetic environments where the reward signals are clearly defined. |
| Approach: | They propose a multimodal web agent that can autonomously conduct real-world exploration and improve itself after each iteration. |
| Outcome: | The proposed agent improves itself after each iteration, demonstrating strong performance across multiple test sets. |
TabularMath: Understanding Math Reasoning over Tables with Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Mathematical reasoning has long been a key benchmark for evaluating large language models. |
| Approach: | They propose a framework that transforms math word problems into scalable tabular reasoning tasks. |
| Outcome: | The proposed framework transforms math word problems into scalable and verified tabular reasoning tasks. |
Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that Rex can benefit from cross-lingual training and improve the effectiveness of semantic parsers. |
| Approach: | They propose a Representation Mixup Framework for effectively exploiting translations in the cross-lingual Text-to-SQL task. |
| Outcome: | The proposed framework can benefit from cross-lingual training and improve the effectiveness of semantic parsers, achieving state-of-the-art performance. |
Retrieval-augmented GUI Agents with Generative Guidelines (2025.emnlp-main)
Copied to clipboard
| Challenge: | GUI agents powered by vision-language models struggle with real-world tasks due to their complex nature and limited training data. |
| Approach: | They propose a lightweight vision-language model that leverages web tutorials at inferencetime to synthesize GUI agents. |
| Outcome: | The proposed agent outperforms baseline GUI agents and surpasses other inference baselines by 2.6% to 13.3% across two model sizes. |
Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse Domains (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has been effective on structured tasks, but its reliance on simple, rule-based verifiers creates a bottleneck. |
| Approach: | They propose a framework that uses a generative verifier to provide soft, probabilistic rewards. |
| Outcome: | The proposed framework outperforms existing models up to 10x their size and can be scalable and effective. |
Dialogue-Based Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing dialogue-based relation extraction tasks focus on texts from formal genres such as professionally written and edited news reports or well-edited websites. |
| Approach: | They propose to use DialogRE to study cross-sentence relation extraction . they propose to annotate 36 possible relation types between arguments in dialogues . |
| Outcome: | The proposed dataset supports the prediction of relation(s) between two arguments that appear in a dialogue. |
Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance (2025.emnlp-industry)
Copied to clipboard
Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song
| Challenge: | Existing approaches to identifying inappropriate content require extensive human-labeled data and lack cross-issue generalization. |
| Approach: | They propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection. |
| Outcome: | The proposed model improves the MLLM's performance in both zero-shot and supervised fine-tuning settings and shows strong generalization capabilities to emergent, previously unseen issues. |
Investigating Value-Reasoning Reliability in Small Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | sLLMs have been widely deployed in practical applications, but little attention has been paid to their value-reasoning abilities, particularly in terms of reasoning reliability. |
| Approach: | They propose a systematic evaluation framework for assessing the Value-Reasoning Reliability of small Large Language models (sLLMs) . framework includes three core tasks: Repetition Consistency task, Interaction Stability task, and Open-ended Expression Consistencies task. |
| Outcome: | The proposed framework incorporates self-reported confidence scores to evaluate the model’s value reasoning reliability from two perspectives: the model's self awareness of its values, and its value-based decision-making. |
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination – generating content that does not align with realworld facts. |
| Approach: | They propose to extrapolate critical token probabilities beyond the last layer to improve decoding by manipulating the predicted distributions at inference time. |
| Outcome: | The proposed methods surpass state-of-the-art on multiple datasets by large margins. |
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)
Copied to clipboard
Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan
| Challenge: | Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages . |
| Approach: | They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models . |
| Outcome: | The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English . |
Type Enhanced BERT for Correcting NER Errors (2023.findings-acl)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is the task of identifying spans that belong to particular categories, such as person, location, organization, etc. |
| Approach: | They propose a method that integrates named entity’s type information into BERT by an adapter layer and integrates it into a gazetteer. |
| Outcome: | The proposed method outperforms baselines in multiple corpus. |
From Polarity to Intensity: Mining Morality from Semantic Space (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to compute moral intensity are limited to word-level measurement and heavily rely on human labelling. |
| Approach: | They propose a weakly-supervised framework that can automatically measure moral intensity from text. |
| Outcome: | The proposed framework can measure moral intensity from text with moral polarity labels, which are more robust and easier to acquire. |
Covariance Matrix-Driven Image Channel Allocation for Multimodal Fake News Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on designing efficient multimodal fusion frameworks to bridge the semantic gap between images and texts. |
| Approach: | They propose a covariance matrix-driven image channel allocation method that expands the number of original channel maps and assigns importance scores to the expanded channel maps. |
| Outcome: | The proposed method achieves state-of-the-art on three public multimodal fake news detection benchmark datasets. |
RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)
Copied to clipboard
Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji
| Challenge: | We present a new information extraction system that can construct temporal event graphs from news documents. |
| Approach: | They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction . |
| Outcome: | The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities. |
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data (2026.acl-short)
Copied to clipboard
| Challenge: | Strong base models saturate benchmarks, resulting in weaker performance, a paradox . a new approach to Reinforcement Learning (RL) is needed to improve performance . |
| Approach: | They propose a method that uses constrained uniform top-k sampling to flatten the local optimization landscape by sampling uniformly from constrained high-confidence candidates. |
| Outcome: | Experiments show that the proposed approach prevents policy degeneration and boosts out-of-domain generalization. |
PAD-Net: An Efficient Framework for Dynamic Networks (2023.acl-long)
Copied to clipboard
| Challenge: | Dynamic networks can significantly improve the model’s representation power with acceptable computational cost. |
| Approach: | They propose a partially dynamic network to transform redundant dynamic parameters into static ones and iterative mode partition to partition dynamic and static parameters efficiently. |
| Outcome: | The proposed network surpasses fully dynamic networks by +0.7% top-1 acc with only 30% dynamic parameters for DY-Conv and +1.9% average score in language understanding with only 50% dynamic parameters. |
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing web agents only handle one input modality and are evaluated only in simplified web simulators or static web snapshots, greatly limiting their applicability in real-world scenarios. |
| Approach: | They propose a large multimodal model-powered web agent that can complete user instructions end-to-end by interacting with real-world websites. |
| Outcome: | The proposed agent achieves 59.1% task success rate, surpassing both GPT-4 and WebVoyager setups. |
Low-Bit Quantization Favors Undertrained LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Larger models or those trained on fewer tokens exhibit less quantization-induced degradation (QiD), while smaller, well-trained models face significant performance losses. |
| Approach: | They propose to use QiD to measure an LLM’s training levels and determine the number of training tokens required for fully training LLMs of various sizes. |
| Outcome: | The proposed scaling laws can predict the quantization performance of different-sized LLMs trained with tokens. |
From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities (2025.findings-acl)
Copied to clipboard
Shixin Jiang, Jiafeng Liang, Jiyuan Wang, Xuan Dong, Heng Chang, Weijiang Yu, Jinhua Du, Ming Liu, Bing Qin
| Challenge: | MLLMs are able to integrate multiple modalities into a single model to tackle complex tasks in real-world scenarios. |
| Approach: | They propose a comprehensive survey of Omni-MLLMs to address the challenges and opportunities of multimodal modeling. |
| Outcome: | The proposed model can integrate multiple modalities into a single model and provide novel perspectives. |
CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models (2025.findings-naacl)
Copied to clipboard
Shangda Wu, Yashan Wang, Ruibin Yuan, Guo Zhancheng, Xu Tan, Ge Zhang, Monan Zhou, Jing Chen, Xuefeng Mu, Yuejie Gao, Yuanliang Dong, Jiafeng Liu, Xiaobing Li, Feng Yu, Maosong Sun
| Challenge: | Current music information retrieval systems struggle to meet linguistic diversity challenges . current systems struggle with text queries in non-English languages . |
| Approach: | They propose a music information retrieval system that supports both ABC notation and MIDI . CLaMP 2 includes a multilingual text encoder and a multiple-modal music encoder . |
| Outcome: | The proposed system achieves state-of-the-art results in multilingual semantic search and music classification across modalities. |
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models (2026.acl-long)
Copied to clipboard
Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu, Kam-Fai Wong
| Challenge: | Existing agentic systems are retrieval-heavy but reasoning-light . current systems lack compositional reasoning, a key component of deep research . |
| Approach: | They propose a data synthesis pipeline WebAggregator to shift agentic paradigm . they use Proactive Explorer to collect interconnected knowledge and Compositional Logic Proposer to weave knowledge into complex questions . |
| Outcome: | The proposed pipeline surpasses GPT-4.1 and matches Claude-3.7-Sonnet on GAIA, WebWalkerQA, and XBench. |
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)
Copied to clipboard
Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun
| Challenge: | Scientific data visualization is an essential process in research, but its use of large language models remains unexplored. |
| Approach: | They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks. |
| Outcome: | The proposed framework improves performance of commercial and open-source models. |
OpenFact: Factuality Enhanced Open Knowledge Extraction (2023.tacl-1)
Copied to clipboard
Linfeng Song, Ante Wang, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su, Yue Zhang, Dong Yu
| Challenge: | Existing OIE systems organize knowledge into subject-relation-object (SRO) triplets, and they use templates to extract such knowledge triplet. |
| Approach: | They propose a framework to handle expressiveness and groundedness in OpenFact . they propose to use templates, extra constraints, and adopt human efforts to ensure that most triplets contain enough details. |
| Outcome: | The proposed framework improves expressiveness and groundedness of OpenFact . it is more accurate and denser than OPIEC-Linked, which is grounded to Wikidata . |
AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for large language models with extended context lengths face significant computational challenges during the prefill phase. |
| Approach: | They propose a difference-aware, dynamic sparse attention mechanism that efficiently identifies critical attention regions at a finer stripe granularity while adapting to global contextual information. |
| Outcome: | The proposed model achieves a speedup of 1.44 while maintaining higher recall rates. |
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning (2024.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved remarkable success in aligning with user intentions. |
| Approach: | They develop local and global explanation methods and a feed-forward-based method for input-output attribution to investigate the impact of instruction tuning on user intentions. |
| Outcome: | The proposed method compares explanations from pre-trained and instruction-tuned models . it empowers LLMs to recognize the instruction parts of user prompts, it encourages response generation . |
SafeConv: Explaining and Correcting Conversational Unsafe Behavior (2023.acl-long)
Copied to clipboard
| Challenge: | Existing datasets do not provide enough annotation to explain unsafe behavior . current chatbots generate toxic and offensive responses, which can be dangerous . |
| Approach: | They construct a dataset called SafeConv that provides comprehensive annotations for chatbots . they compare safe alternatives to rewrite unsafe responses . |
| Outcome: | The proposed model can explain unsafe behavior and detoxify chatbots, the authors show . the proposed model is able to detect unsafe utterances, extract unsafe spans, and convert unsafe responses to safe versions. |
Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey (2024.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are now commonplace in conversation applications, but their misuse for generating harmful responses has raised serious societal concerns. |
| Approach: | They provide a comprehensive overview of recent studies covering attacks, defenses, and evaluations of Large Language Models (LLMs) . |
| Outcome: | The proposed review summarizes three aspects of LLM conversation safety: attacks, defenses, and evaluations. |
Reason from Future: Reverse Thought Chain Enhances LLM Reasoning (2025.findings-acl)
Copied to clipboard
Yinlong Xu, Yanzhao Zheng, Shuoshuo Sun, Shuaihan Huang, Baohua Dong, Zhu Hangcheng, Ruohui Huang, Gang Yu, Hongxia Xu, Jian Wu
| Challenge: | Existing reasoning paradigms that focus on local optimum reasoning lack global perspective. |
| Approach: | They propose a bidirectional reasoning paradigm that generates reasoning paths by bidirectional planning and bottom-up reasoning accumulation. |
| Outcome: | The proposed reasoning paradigm outperforms conventional paradigms with higher accuracy and less searching space to solve complex tasks. |
Faithful Question Answering with Monte-Carlo Planning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to answer questions using large language models lack the ability to faithfully follow the intermediate reasoning steps from the known premises to the answer. |
| Approach: | They propose a faithful question-answering task that uses a Monte-Carlo planning algorithm to produce faithful reasoning steps from the known premises to the answer. |
| Outcome: | The proposed task can produce valid and faithful reasoning steps compared with large language models with a much smaller model size. |
Your Reasoning Model is Secretly a Reward Model - Optimization-Free Verification from Experience (2026.acl-long)
Copied to clipboard
| Challenge: | Existing verifiers operate on the surface text or on confidence proxies derived from token probabilities, which can be brittle. |
| Approach: | They propose a training-free, non-parametric verifier that summarizes each reasoning trace by an activation delta and compares it to two class centroids computed from labeled experience. |
| Outcome: | The proposed model improves selection and reranking on large and less-calibrated models. |
A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing models of large language models struggle with complex logical reasoning problems. |
| Approach: | They propose to use large language models to identify their own errors to improve their models' performance. |
| Outcome: | The proposed models can identify logical fallacies accurately and improve by themselves. |
Improving LLM Generations via Fine-Grained Self-Endorsement (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated remarkable capabilities but can still fail frequently on knowledge-intensive tasks. |
| Approach: | They propose a self-endorsement framework that leverages fine-grained fact-level comparisons across multiple sampled responses. |
| Outcome: | The proposed framework can improve factuality of generations with simple prompts across scales of LLMs. |
Cautious Next Token Prediction (2025.findings-acl)
Copied to clipboard
Yizhou Wang, Lingzhi Zhang, Yue Bai, Mang Tik Chiu, Zhengmian Hu, Mingyuan Zhang, Qihua Dong, Yu Yin, Sohrab Amirghodsi, Yun Fu
| Challenge: | Existing methods for decoding autoregressive models are temperature scaling and nucleus sampling to balance diversity and coherence. |
| Approach: | They propose a training-free decoding strategy that uses a model with a low perplexity score to select the trial with the lowest perplexities as the most probable and reliable path. |
| Outcome: | The proposed approach outperforms existing standard decoding strategies consistently by a clear margin. |
SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models can handle text and data, but blending text and numerical data presents significant challenges. |
| Approach: | They propose four tasks to evaluate the numerical reasoning and information fusion capabilities of large language models in sports data analytics. |
| Outcome: | The proposed tasks evaluate the numerical reasoning and information fusion capabilities of large language models in sports data analytics. |
Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations (D19-54)
Copied to clipboard
| Challenge: | Determinantal point processes (DPP) is one of the best performing techniques for extractive summarization. |
| Approach: | They propose to combine determinantal point processes with surface indicators for effective identification of summary-worthy sentences. |
| Outcome: | The determinantal point processes (DPP) framework is one of the best performing in summarization competitions. |
EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)
Copied to clipboard
Bin Xu, Yu Bai, Huashan Sun, Yiguan Lin, Siming Liu, Xinyue Liang, Yaolin Li, Zhuangzhi Dong, Jingren Zhang, Yufan Deng, Xinyu Zou, Yang Gao, Heyan Huang
| Challenge: | Existing benchmarks that focus on knowledge-intensive tasks do not reflect diverse educational scenarios. |
| Approach: | They propose a benchmark that incorporates 9 major scenarios and 4,000 educational contexts. |
| Outcome: | The proposed model performs comparable to state-of-the-art large models on the test set. |
Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing semi-parametric language models lack the capacity to perform zero-shot tasks . large language models have shown impressive zero-shoot ability, but huge model size costs . semi-parametric language model can be used to augment a smaller language model with retrieved background knowledge . |
| Approach: | They propose a semi-parametric language model for zero-shot task generalization that augments a smaller language model with retrieved related background knowledge. |
| Outcome: | The proposed model outperforms T0-3B by 16% across seven diverse evaluation tasks while being 3.8x smaller in scale. |
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. |
Structural Information Preserving for Graph-to-Text Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models that mess up or drop the core structural information of input graphs are lacking in graph-to-text generation. |
| Approach: | They propose to leverage richer training signals to guide a graph-to-text generation model by focusing on autoencoding losses and back-propagating the losses to better calibrate the model. |
| Outcome: | Experiments on two benchmarks show the proposed model over a state-of-the-art model . two types of autoencoding losses are used to back-propagate the model based on multitask training . |
Beyond Detection: Evaluating Fallacy Awareness of LLMs in Interactive Scenarios (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models fail to recognize fallacious reasoning in real-world interactions despite strong performance on static fallacy detection tasks. |
| Approach: | They propose a Chinese benchmark to assess fallacy awareness without explicit cues . they propose 'fate' evaluation framework that assesses fallacy without explicit . |
| Outcome: | The proposed framework assesses fallacy awareness without explicit cues, combining natural dialogue responses and reasoning-based decisions. |
Instance-adaptive training with noise-robust losses against noisy labels (2021.emnlp-main)
Copied to clipboard
| Challenge: | Several noise-robust losses have been proposed and evaluated on tasks in computer vision, but they use a single dataset-wise hyperparamter to control the strength of noise resistance. |
| Approach: | They propose to change single dataset-wise hyperparameters of noise resistance to be instance-wise. |
| Outcome: | The proposed frameworks increase noise-robustness on noisy and corrupted NLP datasets. |
Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer (2024.acl-long)
Copied to clipboard
| Challenge: | Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity. |
| Approach: | They propose a hierarchical transformer that quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a transformer architecture. |
| Outcome: | The proposed model outperforms existing speech language models in word error rate, speech quality, and speaker similarity. |
Efficient Zero-shot Event Extraction with Context-Definition Alignment (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Conventional supervised methods cannot generalize to event types out of the pre-defined ontology. |
| Approach: | They propose to use two separate transformer models to model the definition semantics of an event type name into the same embedding space and then minimize their embeddable distance via contrastive learning. |
| Outcome: | The proposed model outperforms all previous zero-shot EE methods with fast inference speed due to the disjoint design. |
Don’t Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls (2025.acl-long)
Copied to clipboard
Ante Wang, Linfeng Song, Ye Tian, Dian Yu, Haitao Mi, Xiangyu Duan, Zhaopeng Tu, Jinsong Su, Dong Yu
| Challenge: | Recent advances in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increased computational resources. |
| Approach: | They propose an e ffici ent tree sear ch framework that is a plug-and-play system compatible with various tree search algorithms. |
| Outcome: | The proposed framework reduces computational costs and prioritizes resource allocation to harder tasks (Levels 3-4) over simpler ones (Level 1-2), addressing both over-exploration in basic problems and under-exploation in complex cases. |
APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities. |
| Approach: | They propose to use self-generated dis-preferred weakness data to enhance model performance with a targeted training approach that minimizes interference with existing knowledge base. |
| Outcome: | The proposed approach ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to existing methods. |
PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)
Copied to clipboard
Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu
| Challenge: | Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback. |
| Approach: | They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states. |
| Outcome: | The proposed model outperforms baselines in faithfulness and pedagogical value. |
Logic-Consistency Text Generation from Semantic Parses (2021.findings-acl)
Copied to clipboard
| Challenge: | Text generation from semantic parses is challenging due to the complexity of the inner logic and the lack of automatic evaluation metrics for logic consistency. |
| Approach: | They propose a framework for logic consistent text generation from semantic parses that employs iterative training procedures and quality control. |
| Outcome: | The proposed framework enhances logic consistency and human evaluation on two benchmark datasets. |
Improving Question Answering with External Knowledge (D19-58)
Copied to clipboard
| Challenge: | ARC-Easy, ARC Challenge, and OpenBookQA use Wikipedia to augment training data . performance degrades when additional instances exhibit higher difficulty than original training data. |
| Approach: | They propose two methods for exploiting external knowledge for QA in science . they enrich the original corpus with relevant text snippets from an open-domain resource . the second method simply increases the amount of training data by appending additional in-domain instances. |
| Outcome: | The proposed methods achieve gains in accuracy of 8.1%, 13.0%, and 12.8% on science QA tasks. |
OASum: Large-Scale Open Domain Aspect-based Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing generic summarization methods generate only one summary for all different requests which is not optimal for diverse demands. |
| Approach: | They use crowd-sourced knowledge on Wikipedia to create a large-scale open-domain aspect-based summarization dataset with 1 million different aspects on 2 million Wikipedia pages. |
| Outcome: | The proposed model can generate diverse aspect-based summarizations on Wikipedia with zero/few-shot and fine-tuning on seven downstream datasets. |
Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reinforcement learning methods rely on sparse outcome rewards, which fail to credit correct intermediate steps in partially successful solutions. |
| Approach: | They propose a process reward model that rewards correct steps only when they detect errors . they propose VPPO, which rewards the correct prefix and an erroneous suffix . |
| Outcome: | a new approach outperforms sparse-reward RL and prior PRM-guided baselines on Pass@1 and Pass@K . a process reward model (PRM) outperformed sparser-rebound RL on multiple reasoning benchmarks . |
On the Dimensionality of Sentence Embeddings (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work focuses on improving the quality of sentence embeddings, but the exploration of sentence dimension is limited. |
| Approach: | They propose a two-step training method where the encoder and pooler are optimized separately to mitigate the overall performance loss in low-dimension scenarios. |
| Outcome: | The proposed method significantly improves the performance of low-dimensional sentence embeddings on seven STS tasks and seven sentence classification tasks. |
UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work lacks direct and fair evaluation of Large Language Models’ ability to express uncertainty effectively in long-form generation. |
| Approach: | They propose a benchmark to evaluate uncertainty expression in both long- and short-form question answering (QA) they propose prompt-based and training-based methods to improve models’ performance. |
| Outcome: | The proposed method mitigates this issue but a misalignment persists in uncertainty expression between long- and short-form generation. |
Vulnerabilities of Large Language Models to Adversarial Attacks (2024.acl-tutorials)
Copied to clipboard
| Challenge: | This tutorial focuses on the vulnerabilities of Large Language Models to adversarial attacks . the tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity . |
| Approach: | This tutorial lays the foundation by explaining safety-aligned LLMs and concepts in cybersecurity. |
| Outcome: | The tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity. |
AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)
Copied to clipboard
Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, Yuxiao Dong
| Challenge: | Existing studies on Android agents lack systematic research on open-source and closed-source models. |
| Approach: | They propose a framework for Android agents that includes an operation environment and a reproducible benchmark. |
| Outcome: | The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM. |
DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes (2025.findings-emnlp)
Copied to clipboard
Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu
| Challenge: | Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding. |
| Approach: | They introduce DivScene, a large-scale dataset with 4,614 houses across 81 scene types and 5,707 kinds of target objects. |
| Outcome: | The proposed dataset provides a much greater diversity of target objects and scene types than existing datasets, enabling a comprehensive task evaluation. |
IPS: In-Prompt Process Supervision for Short Video Content Moderation (2026.acl-industry)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) capture semantics of short video content but fail to account for policy-specific details. |
| Approach: | They propose a framework that integrates In-prompt Process Supervision into MLLMs . they propose sequential reasoning over ancillary questions during fine-tuning . |
| Outcome: | IPS outperforms baseline MLLMs on public and proprietary benchmarks . replacing human-annotated ancillary labels with MLML-generated ones results in performance degradation. |
Multi-Scale Spectral Selection and Entropy-Guided Uncertainty Fusion for Multimodal Rumor Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multimodal content detection fail to capture cross-modal semantic inconsistencies and ignore inherent noise in multimodal features. |
| Approach: | They propose a multimodal rumor detection method based on a frequency domain spectral selection method and entropy-guided uncertainty fusion method to capture cross-modal semantic inconsistencies. |
| Outcome: | The proposed method outperforms state-of-the-art methods in multimodal rumor detection . it shows stronger detection capability and robustness on multiple datasets . |
LoGU: Long-form Generation with Uncertainty Expressions (2025.acl-long)
Copied to clipboard
Ruihan Yang, Caiqi Zhang, Zhisong Zhang, Xinting Huang, Sen Yang, Nigel Collier, Dong Yu, Deqing Yang
| Challenge: | Large Language Models (LLMs) generate factually incorrect content, i.e., hallucinations, despite impressive performance. |
| Approach: | They propose a framework to enable models to express uncertainty when unsure . they propose atomic claims to refine uncertainty and refine it using supervised fine-tuning and direct preference optimization to enhance uncertainty expression. |
| Outcome: | The proposed framework significantly improves accuracy, reduces hallucinations, and maintains comprehensiveness of responses. |
EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to reinforcement learning with verifiable reward (RLVR) are limited by difficulty or lack of exploration. |
| Approach: | They propose a self-evolving curriculum learning framework based on chain-of-thought reasoning optimization that constrains exploration space by self-generating and verifying CoT trajectories. |
| Outcome: | The proposed framework enables LLMs to solve previously unsolved problems without external supervision and is compatible with various RL fine-tuning methods. |
More Than Spoken Words: Nonverbal Message Extraction and Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on extracting NMs from small-scale well-structured corpora such as movie scripts wherein NM is enclosed in parentheses by scriptwriters, which greatly decreases the difficulty of extraction. |
| Approach: | They propose to extract nonverbal messages (NMs) from written text and NMs from spoken text by using a semi-supervised learning algorithm. |
| Outcome: | The extracted NMs can generate more relevant, valid, and factually consistent NM than the purely supervised generator. |
ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods rely on text retrieval and geographic knowledge bases to generate coordinates, and they are prone to error propagation and dependency on structured knowledge bases. |
| Approach: | They propose to use large language models to convert geographic coordinates into geohash sequences and introduce a Chain-of-Thought mechanism to enhance the model’s reasoning over spatial relationships. |
| Outcome: | The proposed framework can handle explicit address queries in single-point predictions and effectively resolve vague relative location queries. |
Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning (2025.coling-main)
Copied to clipboard
| Challenge: | Large Vision-Language Models (LVLMs) have impressive capabilities in multi-modal context comprehension, but they still suffer from hallucination problems due to inconsistent outputs with the image content. |
| Approach: | They propose a training-free framework MVP to reduce hallucinations in Large Vision-Language Models . they propose multi-view information-seeking strategy to perceive the comprehensive information in the image . |
| Outcome: | The proposed framework reduces hallucinations in large vision-language models by combining multi-view multi-path reasoning with multi-vision multi-path reasoning. |
Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data (2021.findings-emnlp)
Copied to clipboard
| Challenge: | despite considerable progress, most machine reading comprehension tasks lack sufficient training data to fully exploit powerful deep neural network models. |
| Approach: | They propose to use QA data to generate more training data for machine reading comprehension tasks by crowdsourcing . they first collect a large-scale multiple-choice QA dataset for Chinese, ExamQA, and then use incomplete, yet relevant snippets returned by a web search engine as the context for each QA instance. |
| Outcome: | The proposed model improves a Chinese MRC task with +5.1% accuracy and +3.8% exact match. |
InFoBench: Evaluating Instruction Following Ability in Large Language Models (2024.findings-acl)
Copied to clipboard
Yiwei Qin, Kaiqiang Song, Yebowen Hu, Wenlin Yao, Sangwoo Cho, Xiaoyang Wang, Xuansheng Wu, Fei Liu, Pengfei Liu, Dong Yu
| Challenge: | Existing methods for evaluating Large Language Models (LLMs) ability to follow instructions have not been able to provide a detailed analysis of their compliance with instructions. |
| Approach: | They propose a new metric for evaluating Large Language Models' ability to follow instructions and a benchmark for DRFR. |
| Outcome: | The proposed metric and benchmark compared with traditional scoring methods and explores annotation sources including human experts, crowd-sourced workers, and GPT-4. |
Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehension (2022.acl-short)
Copied to clipboard
| Challenge: | Existing models for dialogue comprehension are not available for the pre-training of such a model. |
| Approach: | They propose a narrative-guided pre-training strategy that learns by narrating key information from a dialogue input. |
| Outcome: | The proposed model performs better on four dialogue-based tasks and is comparable to existing models. |
Attribution and Application of Multiple Neurons in Multimodal Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to identify multimodal neurons in MLLMs are insufficiently understood . previous studies focused on identifying neurons corresponding to single-tokens . |
| Approach: | They propose a method to identify multimodal neurons in Transformer-based MLLMs . they introduce fuzzy set theory to model the complex relationship between neurons and semantic concepts . |
| Outcome: | The proposed method improves performance on the Visual Question Answering task. |
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark (2026.acl-long)
Copied to clipboard
Kai Zou, Ziqi Huang, Yuhao Dong, Shulin Tian, Dian Zheng, Hongbo Liu, Jingwen He, Bin Liu, Yu Qiao, Ziwei Liu
| Challenge: | Existing evaluations treat visual understanding and generation in isolation or overlook tasks that inherently couple them. |
| Approach: | They propose a benchmark that examines the bidirectional synergy between generation and understanding across eight reasoning-centric domains. |
| Outcome: | The proposed model systematically unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains. |
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback (2025.findings-emnlp)
Copied to clipboard
Minda Hu, Tianqing Fang, Jianshu Zhang, Jun-Yu Ma, Zhisong Zhang, Jingyan Zhou, Hongming Zhang, Haitao Mi, Dong Yu, Irwin King
| Challenge: | Web agents powered by Large Language Models lack the ability to perform in uncertain web environments. |
| Approach: | They propose to reconstruct web agents' reasoning skills into chain-of-thought rationales by fine-tuning their LLM backbone into a web-based model. |
| Outcome: | The proposed approach significantly improves the agent self-improving benchmark OpenWebVoyager, demonstrating that it can be used to improve the agent's reasoning skills. |
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats (2026.acl-long)
Copied to clipboard
| Challenge: | Microscaling Floating-Point (MXFP) is a low-precision format for large language models (LLMs). |
| Approach: | They conduct systematic evaluations of PTQ under Microscaling Floating-Point (MXFP) . they find that MXFP8 consistently achieves near-lossless performance . |
| Outcome: | The proposed method achieves near-lossless performance while MXFP4 introduces substantial accuracy degradation and remains challenging. |
WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model (2025.emnlp-main)
Copied to clipboard
| Challenge: | Agent self-improvement, where agents train their underlying Large Language Model (LLM) on self-sampled trajectories, shows promising results but often stagnates in web environments due to limited exploration and under-utilization of pretrained web knowledge. |
| Approach: | They propose a co-evolving Large Language Model (LLM) that predicts the next observation based on current observation and action within the web environment. |
| Outcome: | The proposed framework shows that agents can perform better in real-world web environments without using any distillation from more powerful close-sourced models. |
Evaluating Moral Beliefs across LLMs through a Pluralistic Framework (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. |
| Approach: | They propose a framework to evaluate the moral beliefs of four large language models . they use a dataset containing 472 moral choice scenarios in Chinese . |
| Outcome: | The proposed framework evaluates the moral beliefs of four large language models. |
SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for preference optimization of large language models use pairs of positive and negative samples, but the quality of positive samples may become similar during training, complicating preference learning. |
| Approach: | SeaPO introduces error types commonly occurring in large language models to improve preference learning. |
| Outcome: | SeaPO introduces error types into model Preference Optimization to improve model performance . negative samples are more erroneous than positive samples, and preference-based training mitigates errors . |
XL-NBT: A Cross-lingual Neural Belief Tracking Framework (D18-1)
Copied to clipboard
| Challenge: | a multi-lingual approach to training dialog systems is expensive and tedious, but it can be useful for cross-lingual support. |
| Approach: | They propose to annotate data for multiple languages and train a multi-lingual dialog system for each language. |
| Outcome: | The proposed framework bypasses the expensive human annotation and achieves promising results. |
When Safety Alignment Fails to Generalize: Probing with Language Game Jailbreaks (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety alignment methods rely on fixed or narrow transformation schemes to generalize . existing methods based on fixed and narrow transformations are often inadequate . |
| Approach: | They propose a framework for discovering and refining language game-based jailbreaks to probe alignment generalization. |
| Outcome: | The proposed framework allows controlled exploration of alignment behavior across closely related linguistic variants. |
Learning a Grammar Inducer from Massive Uncurated Instructional Videos (2022.emnlp-main)
Copied to clipboard
| Challenge: | aims to find more accurate syntactic grammars for accompanying text using video data. |
| Approach: | They build a video-aided grammar induction model that can learn video-span correlation without manual features. |
| Outcome: | The proposed model can learn video-span correlation without manual features adopted by previous systems. |
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models (2025.acl-long)
Copied to clipboard
Zhisong Zhang, Yan Wang, Xinting Huang, Tianqing Fang, Hongming Zhang, Chenlong Deng, Shuaiyi Li, Dong Yu
| Challenge: | Large language models have demonstrated remarkable performance across a wide range of language tasks due to their remarkable ability in context modeling. |
| Approach: | They propose to use parallel context encoding to reduce attention entropy by incorporating attention sinks and selective mechanisms to reduce irregular attention . they also propose to incorporate attention sink mechanisms into the parallel encoded context to reduce the irregular attention. |
| Outcome: | The proposed methods lower irregular attention entropy and narrow performance gaps. |
Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search (2026.acl-long)
Copied to clipboard
Yu Guo, Shenghao Ye, Shuangwu Chen, Zijian Wen, Tao Zhang, Bai Qirui, Dong Jin, Yunpeng Hou, Huasen He, null Jianyang, Xiaobin Tan
| Challenge: | Existing pruning methods rely on sequential revisions and unreliable critique signals . Existing methods fail to detect the loss of answer-critical data . |
| Approach: | They propose a table pruning framework which transforms table pruning to gold trajectory-supervised parallel search. |
| Outcome: | The proposed framework outperforms the strongest baseline pruning framework by 3.2% on various tabular reasoning tasks. |
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. |
Towards Abstractive Grounded Summarization of Podcast Transcripts (2022.acl-long)
Copied to clipboard
| Challenge: | Podcast summarization is of practical benefit to content providers and consumers . however, podcast summarizing faces significant challenges including factual inconsistencies . speech recognizers induce transcription errors and abstractive summarisation models may hallucinate . |
| Approach: | They propose a method to generate podcast summaries while grounding segments in specific regions of the transcript to allow full inspection of summary details. |
| Outcome: | The proposed method can produce an abstractive summary while grounding segments in specific regions of the transcript to allow full inspection of summary details. |
Optimal Partial Transport Based Sentence Selection for Long-form Document Matching (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for document matching are limited by the partial nature of the sentence-level matching signals. |
| Approach: | They propose a matching approach that equips existing document matching models with an Optimal Partial Transport component, namely OPT-Match, which selects the key sentences that play a major role in matching. |
| Outcome: | The proposed approach outperforms existing models on four publicly available datasets and the key sentences selected by it are consistent with human-provided rationales. |
MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods focus on specializing LMs in mathematical reasoning and rely on knowledge distillation. |
| Approach: | They propose a multi-view fine-tuning method that exploits existing mathematical problem datasets with diverse annotation styles. |
| Outcome: | The proposed method outperforms existing methods that rely heavily on LLM teachers . it grants models generalization ability across views and datasets, and the capability to learn from inaccurate or incomplete data. |
What’s the most important value? INVP: INvestigating the Value Priorities of LLMs through Decision-making in Social Scenarios (2025.coling-main)
Copied to clipboard
| Challenge: | Large scale language models (LLMs) have demonstrated impressive performance in various tasks and are increasingly integrated into the decision-making process. |
| Approach: | They propose a framework for INvestigating Value Priorities through decision-making in social scenarios and evaluate seven popular LLMs. |
| Outcome: | The proposed framework covers 1613 scenarios and 3226 decisions across 283 topics and focuses on Universalism and Benevolence, while Power and Hedonism are given lower priority. |
Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding (2026.acl-long)
Copied to clipboard
| Challenge: | Graphical User Interface (GUI) grounding requires mapping natural language instructions to precise pixel coordinates due to visually homogeneous elements and dense layouts. |
| Approach: | They propose to replace static consistency strategies with a learnable selection mechanism that selects the optimal target by critiquing its own proposals rendered on the screenshot. |
| Outcome: | The proposed model significantly improves both grounding and critiquing capabilities over 6 benchmarks. |
Bridging Continuous and Discrete Spaces: Interpretable Sentence Representation Learning via Compositional Operations (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to learn sentence embeddings do not capture the semantic similarity of sentences. |
| Approach: | They propose a framework that integrates compositional sentence operations into the embedding space and optimizes operator networks and a bottleneck encoder-decoder model to produce meaningful and interpretable sentence embeddables. |
| Outcome: | The proposed framework improves the interpretability of sentence embeddings on four textual generation tasks while maintaining strong performance on traditional semantic similarity tasks. |
Reliability-aware Dynamic Feature Composition for Name Tagging (P19-1)
Copied to clipboard
| Challenge: | Word embeddings are used to encode semantic information, but their quality is not consistent across the vocabulary due to the long-tail distribution of word frequency. |
| Approach: | They propose a reliability-aware name tagging model that uses word frequency to indicate word quality . they propose to use word frequency-based reliability signals to dynamically select and compose features . |
| Outcome: | The proposed model outperforms the baseline model on OntoNotes 5.0 and up to 5% gain on cross-genre data sets. |
FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows (2022.emnlp-main)
Copied to clipboard
| Challenge: | Despite recent progress in dialogue evaluation, how to develop automatic metrics remains an open problem. |
| Approach: | They propose a consensus-based framework for dialog evaluation using segment act flows . they propose to crowdsource a large-scale dataset for it to be evaluated . |
| Outcome: | The proposed framework can reach the best or comparable correlation with human evaluation. |
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP) Existing cost analyses regulate only the number of sampling passes, ignoring the substantial disparities in sampling costs. |
| Approach: | They propose to integrate two complementary methods into a unified EconRL pipeline to increase pass rates under constrained sampling passes. |
| Outcome: | The proposed method reduces token usage and sample passes while maintaining the original performance. |
Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety defenses typically intervene internally within the generative model, but suffer from severe concept entanglement, leading to degradation of benign generation quality. |
| Approach: | They propose a structurally isolated safety module that performs external, interpretable rectification without modifying the base model. |
| Outcome: | The proposed module performs external, interpretable rectification without modifying the base model. |
Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective (2026.acl-long)
Copied to clipboard
Zhezheng Hao, Hong Wang, Haoyang Liu, Jian Luo, Jiarui Yu, Hande Dong, Qiang Lin, Can Wang, Jiawei Chen
| Challenge: | Large Language Models (LLMs) have remarkable reasoning capabilities in complex tasks such as mathematics and coding. |
| Approach: | They propose an entropy-modulation method that adaptively reweighs tokens based on theoretically-estimated entropic variations. |
| Outcome: | The proposed method outperforms state-of-the-art methods in six mathematical reasoning and three coding benchmarks. |
DA3: A Distribution-Aware Adversarial Attack against Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent attacks have shown that adversarial examples have a different data distribution than the original examples, reducing their effectiveness under detection methods. |
| Approach: | They propose a distribution-aware adversarial attack method that considers the distribution shifts of adversarials to improve attacks’ effectiveness under detection methods. |
| Outcome: | The proposed method improves the effectiveness of adversarial examples under detection methods and integrates both ASR and detectability. |
Salience Allocation as Guidance for Abstractive Summarization (2022.emnlp-main)
Copied to clipboard
Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu
| Challenge: | Abstractive summarization models implicitly learn to capture the salient information from scratch. |
| Approach: | They propose a method that uses salience expectation to guide abstractive summarization by averaging salient content to a fixed threshold. |
| Outcome: | The proposed method can be easily adapted to documents with various abstractiveness and achieves high performance. |
End-to-End Chinese Speaker Identification (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for speaker identification in texts are incomplete and introduce errors that propagate and seriously affect the final output. |
| Approach: | They propose to use speaker identification (SI) in texts to identify the speaker(s) for each utterance in texts. |
| Outcome: | The proposed model can achieve comparable or better than previous state-of-the-art methods on all public SI datasets for Chinese. |
Importance-based Neuron Allocation for Multilingual Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multilingual neural machine translation tend to preserve general knowledge, but ignore language-specific knowledge. |
| Approach: | They propose to divide model neurons into general and language-specific parts based on their importance across languages. |
| Outcome: | The proposed model can preserve general knowledge but ignore language-specific knowledge on several languages, and is universal and cost-effective. |
LEPO: Latent Reasoning Policy Optimization for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing latent reasoning methods that use chain of thought (CoT) are limited to selecting one discrete token at each reasoning step, which potentially induces information loss. |
| Approach: | They propose a framework that injects controllable stochasticity into latent reasoning via Gumbel-Softmax, restoring LLMs' exploratory capacity and enhancing their compatibility with Reinforcement Learning (RL). |
| Outcome: | The proposed framework preserves richer information for more comprehensive reasoning and is compatible with Reinforcement Learning (RL). |
Towards Robust Temporal Activity Localization Learning with Noisy Labels (2024.lrec-main)
Copied to clipboard
Daizong Liu, Xiaoye Qu, Xiang Fang, Jianfeng Dong, Pan Zhou, Guoshun Nan, Keke Tang, Wanlong Fang, Yu Cheng
| Challenge: | Existing methods for temporal activity localization are expensive and difficult to satisfy due to subjective labeling. |
| Approach: | They propose a new TAL setting where a TAL model should be robust to mixed training data with noisy moment boundaries. |
| Outcome: | The proposed method is significantly more robust to noisy training data than existing methods. |
AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on basic abilities using nonverbal methods, such as yes-no and multiple-choice questions. |
| Approach: | They propose a benchmark that provides more nuanced evaluations of alignment capabilities for large Vision-Language Models (VLMs) they use a rule-calibrated evaluator that exceeds GPT-4's evaluation ability and a “alignment score” to assess the robustness and stability of models across diverse prompts. |
| Outcome: | The proposed benchmark covers 13 tasks across three categories and includes both single-turn and multi-turn dialogue scenarios. |
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for dialogue rewriting suffer from the robustness issue, i.e., performances drop dramatically when testing on a different dataset. |
| Approach: | They propose a sequence-tagging-based approach that reduces the search space while preserving the core of the task. |
| Outcome: | The proposed model significantly reduces the search space while still covering the core of the task. |
ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT (2020.acl-main)
Copied to clipboard
| Challenge: | Zero pronoun recovery and resolution aim at recovering the dropped pronounce and pointing out its anaphoric mentions. |
| Approach: | They propose to solve two tasks together to recover the dropped pronoun and point out its anaphoric mentions. |
| Outcome: | The proposed model outperforms previous state of the arts benchmarks on two benchmarks. |
Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are generalist agents capable of operating within complex environments. |
| Approach: | They propose a class of tools that can serve as a middleware layer shielding LLMs from environmental complexity. |
| Outcome: | The proposed tool can shield the LLM from environmental complexity in two representative complex environments. |
Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts (2025.naacl-long)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) models are constrained by their fixed model capacities when the number of tasks grows in instruction tuning. |
| Approach: | They propose to combine all training tasks and apply fixed sampling weights without considering the importance of different tasks as the model training state changes. |
| Outcome: | The proposed method can be used on knowledge & reasoning tasks and open-ended queries with limited training budget. |
Skills-in-Context: Unlocking Compositionality in Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | eliciting compositional generalization capabilities in large language models is challenging for advanced LLMs because they lack foundational skills and compositional examples in the same prompt context. |
| Approach: | They propose to use compositional generalization capabilities in large language models to elicit compositional skills in a prompt context. |
| Outcome: | The proposed structure enables LLMs to tackle more challenging problems with as few as two exemplars and unlocks their latent potential. |
Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification (2026.findings-acl)
Copied to clipboard
Yuxuan Wan, Tianqing Fang, Zaitang LI, Yintong Huo, Wenxuan Wang, Haitao Mi, Dong Yu, Michael R. Lyu
| Challenge: | Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving. |
| Approach: | They propose an inference-time scaling of verification wherein an agent self-improves at test time by evaluating its generated answers. |
| Outcome: | The proposed model outperforms vanilla agent-as-judge and LLM judge baselines by 12%–48% in meta-evaluation F1 score. |
RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game (2026.findings-acl)
Copied to clipboard
| Challenge: | despite the adoption of Large Language Models (LLMs), contract revision remains impeded because generic models treat strict legal constraints as mere suggestions. |
| Approach: | They propose a risk-constrained bilevel Stackelberg framework that models high-stakes revision as a strategic interaction rather than an open-ended conversation. |
| Outcome: | The proposed framework achieves state-of-the-art performance with an average RRR of 84.21% and enhanced token efficiency. |
Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity (2023.acl-short)
Copied to clipboard
| Challenge: | Semantic Textual Similarity (STS) measures the degree to which the underlying semantics of paired sentences are equivalent. |
| Approach: | They propose a token-level matching inference algorithm which can be applied on top of any language model to improve its performance on STS task. |
| Outcome: | The proposed method improves the performance of almost all language models, with up to 12.7% gain in Spearman’s correlation. |
Capturing Conversational Interaction for Question Answering via Global History Reasoning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have studied history-dependent reasoning for question answering . utilizing global conversation history for enhancement is gaining interest . |
| Approach: | They propose to establish long-distance dependency among global utterances in multi-turn conversation. |
| Outcome: | The proposed method improves on QuAC by 1%, yielding the F1 score of 73.7%. |
A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression (2025.acl-long)
Copied to clipboard
| Challenge: | gist-based context compression methods can achieve only slight performance loss on tasks like retrieval-augmented generation and long-document QA, but it faces challenges in tasks like synthetic recall. |
| Approach: | They propose two strategies to improve gist-based context compression in large language models. |
| Outcome: | The proposed methods can achieve only slight performance loss on retrieval-augmented generation and long-document QA tasks, but they face challenges in tasks like synthetic recall. |
Variational Graph Autoencoding as Cheap Supervision for AMR Coreference Resolution (2022.acl-long)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a way to preserve the semantic meaning of a sentence in a graph. |
| Approach: | They propose a general pretraining method that leverages any general AMR corpus and even automatically parses AMR data to achieve performance gains of up to 6% absolute F1 points. |
| Outcome: | The proposed model significantly improves on the previous state-of-the-art model by up to 11% F1. |
MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning (2024.naacl-long)
Copied to clipboard
Fuxiao Liu, Xiaoyang Wang, Wenlin Yao, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Yaser Yacoob, Dong Yu
| Challenge: | Existing large language models have limited ability to perform tasks effectively. |
| Approach: | They propose a large-scale multimodal chart instruction dataset with 600k instances supporting diverse tasks and chart types. |
| Outcome: | The proposed LMM achieves state-of-the-art performance on existing chart QA benchmarks. |
Enhancing Multimodal Continual Instruction Tuning with BranchLoRA (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to fine tune Multimodal Large Language Models (MLLMs) are prone to Catastrophic Forgetting (CF) existing approaches rely on the Mixture-of-Experts (MoE) LoRA framework to preserve previous instruction alignments. |
| Approach: | They propose an asymmetric tuning-freezing mechanism to mitigate parameter inefficiency . branch-specific routers are introduced to ensure optimal branch distribution over time . |
| Outcome: | The proposed framework outperforms existing frameworks on the latest MCIT benchmarks. |
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. |
Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to retrieval-augmented generation still face problems with low context utilization and frequent hallucinations. |
| Approach: | They propose a framework that reformulates retrieval and generation as constrained optimization and path planning. |
| Outcome: | The proposed framework significantly improves reasoning accuracy on complex queries while reducing hallucinations. |
Injecting Entity Types into Entity-Guided Text Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in deep generative modeling have led to significant advances in natural language generation (NLG). |
| Approach: | They propose to model the entity type carefully in the decoding phase to generate contextual words accurately. |
| Outcome: | The proposed model produces a target sequence based on a given list of entities. |
Toward Unifying Text Segmentation and Long Document Summarization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive strategies produce more condensed summaries, but they suffer from hallucinations and factual errors, which pose a more difficult generation challenge. |
| Approach: | They propose a method that learns robust sentence representations by performing summarization and segmentation simultaneously, which is further enhanced by an optimization-based regularizer to promote selection of diverse summary sentences. |
| Outcome: | The proposed model achieves state-of-the-art performance on publicly available benchmarks and better cross-genre transferability when equipped with text segmentation. |
GenProve: Learning to Generate Text with Fine-Grained Provenance (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large language models (LLMs) are coarse-grained and fail to distinguish between direct quotes and complex reasoning. |
| Approach: | They propose a framework that combines supervised fine-tuning and group relative policy optimization to generate fluent answers while simultaneously producing sentence-level provenance triples. |
| Outcome: | The proposed framework outperforms 14 strong large language models in joint evaluation. |
Event Detection from Social Media for Epidemic Prediction (2024.naacl-long)
Copied to clipboard
Tanmay Parekh, Anh Mac, Jiarui Yu, Yuxuan Dong, Syed Shahriar, Bonnie Liu, Eric Yang, Kuan-Hao Huang, Wei Wang, Nanyun Peng, Kai-Wei Chang
| Challenge: | Social media is an easy-to-access platform providing timely updates about societal trends and events. |
| Approach: | They propose a framework to extract epidemic-related events from social media posts to provide early warnings. |
| Outcome: | The proposed framework can detect epidemic events for three unseen epidemics of Monkeypox, Zika, and Dengue while existing models fail miserably. |
Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on *broadening* the training set with data augmentation techniques to maximize such benefits. |
| Approach: | They propose a method that embeds problem reflection into each training instance. |
| Outcome: | The proposed method enhances performance in standard and complex scenarios that require reflective thinking. |
Dense X Retrieval: What Retrieval Granularity Should We Use? (2024.emnlp-main)
Copied to clipboard
| Challenge: | a learned dense retrieval model is often overlooked when using a corpus for inference, resulting in a design choice of retrieval unit . granularity of retrievals is important for both retrieval and downstream tasks . |
| Approach: | They propose a retrieval unit for dense retrieval that uses propositions to index corpus . propositions are defined as atomic expressions within text, each encapsulating a distinct factoid . |
| Outcome: | The proposed retrieval unit outperforms passage-level units on retrieval and downstream tasks. |
Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to machine reading comprehension (MRC) on long texts typically chunk text into equally-spaced segments without considering information from other segments. |
| Approach: | They propose to let a model learn to chunk in a more flexible way via reinforcement learning. |
| Outcome: | The proposed model extracts a text span from document and query as answer . previous models can only take a fixed-length (e.g., 512) text as input . |
Token-level Adaptive Training for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural machine translation (NMT). |
| Approach: | They propose to assign tokens with different frequencies to target tokens during training to encourage the model to pay more attention to low-frequency tokens. |
| Outcome: | The proposed model yields consistent improvements on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens. |
AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on factual correctness, semantic grounding, visual reasoning, or multimodal large language models. |
| Approach: | They propose a benchmark to assess AICA, which integrates perception, reasoning, and generation into a unified framework. |
| Outcome: | The proposed framework corrects intensity errors and significantly enhances descriptive depth. |
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training (2024.emnlp-main)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) has gained increasing popularity as a framework for scaling up large language models. |
| Approach: | They investigate how to build Mixture-of-Experts (MoE) models from existing large language models . they use expert construction, Continual pre-training and data sampling strategies . |
| Outcome: | The proposed model outperforms existing models with similar parameters on a wide range of tasks. |
Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization (2026.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that KV cache compression can increase hallucination scores in LLMs . modern LLM models support extremely long sequences, but their impact on model hallucinosity remains underexplored. |
| Approach: | They propose a decoding-phase strategy that selectively removes generated KV pairs from retrieval heads responsible for retrieving critical information from source context. |
| Outcome: | The proposed method reduces hallucination across multiple models and datasets while preserving computational efficiency. |
Knowledge-aware Pronoun Coreference Resolution (P19-1)
Copied to clipboard
| Challenge: | Existing models for pronoun coreference resolution only use triplets, the most common format for knowledge graphs. |
| Approach: | They propose a model that leverages different types of knowledge to resolve pronoun coreference with a neural model. |
| Outcome: | The proposed model outperforms state-of-the-art baselines on two datasets from different domains. |
Video-aided Unsupervised Grammar Induction (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods of multi-modal grammar induction focus on grammar inducing from text-image pairs, but videos provide even richer information, such as static objects and actions. |
| Approach: | They propose a video-aided grammar induction model which learns a constituency parser from unlabeled text and its corresponding video. |
| Outcome: | The proposed model outperforms existing systems on three benchmarks. |
MM-LLMs: Recent Advances in MultiModal Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | MultiModal Large Language Models (MM-LLMs) have undergone significant advances in the past year . traditional MM models incur substantial computational costs, especially when trained from scratch . |
| Approach: | They propose a taxonomy encompassing 126 MM-LLMs and summarize key training recipes to enhance their potency. |
| Outcome: | The proposed models preserve the reasoning and decision-making capabilities of LLMs and empower diverse range of MM tasks. |
Router-Tuning: A Simple and Effective Approach for Dynamic Depth (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve computational efficiency are under-explored and face several critical challenges. |
| Approach: | They propose a method that selectively activates only a subset of the model's layers, skipping those deemed less important. |
| Outcome: | The proposed method significantly improves performance on Attention layers and MoE layers while reducing redundant computation and memory usage. |
Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to fine tune a large language model in low-resource settings are limited in their expressiveness or rely on task-independent knowledge. |
| Approach: | They propose a framework where all parameters are finetuned with task-dependent information from the training data only. |
| Outcome: | The proposed framework outperforms baseline models on several classification datasets in low-resource scenarios. |
PIVOINE: Instruction Tuning for Open-world Entity Profiling (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for information extraction focus on a closed-world setting, but PIVOINE is a promising solution to tackle the open-world problem of entity profiling. |
| Approach: | They propose to develop an LLM that performs Open-world Entity Profiling with instruction tuning to extract desirable entity profiles . they construct INSTRUCTOPENWIKI, a substantial instruction-tuning dataset for Open-World Entity Profiles . |
| Outcome: | The proposed model outperforms existing methods and ChatGPT-based baselines on unseen and out-of-ontology cases. |
Improving Machine Reading Comprehension with Contextualized Commonsense Knowledge (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve machine reading comprehension (MRC) tasks require unstated knowledge to perform well. |
| Approach: | They propose to extract a new kind of structured knowledge from scripts and use it to improve machine reading comprehension (MRC) They propose a teacher-student paradigm to facilitate the transfer of knowledge in weakly-labeled MRC data. |
| Outcome: | The proposed method outperforms methods that use weakly-labeled data and improves a state-of-the-art baseline by 4.3% in accuracy on a Chinese multiple-choice MRC dataset C3. |
Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension (2020.tacl-1)
Copied to clipboard
| Challenge: | ''Language is, at best, a means of directing others to construct similar-thoughts from their own prior knowledge,'' says K. S. Adams and Bruce. |
| Approach: | They present a free-form multiple-choice Chinese machine reading Comprehension dataset (C3) containing 13,369 documents and their associated 19,577 multiple-CHOice free- form questions. |
| Outcome: | The proposed model outperforms human models on linguistic, domain-specific, and general world knowledge problems. |
Continual Named Entity Recognition without Catastrophic Forgetting (2023.emnlp-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (CNER) is a burgeoning area of research . a new paradigm has ushered NER into a non-entity type at the current step t . |
| Approach: | They propose a pooled feature distillation loss that skillfully navigates the trade-off between retaining knowledge of old entity types and acquiring new ones. |
| Outcome: | The proposed method outperforms state-of-the-art approaches on ten CNER settings using three datasets. |
Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning general-purpose audio representations are limited in scope and coverage of audio attributes. |
| Approach: | They propose to use a 10.7M caption dataset to compare ALP with captioning . they find that contrastive learning yields competitive, transferable representations . |
| Outcome: | The proposed model yields competitive, transferable representations, while captioning exhibits better scalability. |
Improving Machine Reading Comprehension with General Reading Strategies (N19-1)
Copied to clipboard
| Challenge: | Recent studies have shown that reading strategies improve comprehension levels for readers lacking adequate prior knowledge. |
| Approach: | They propose three general strategies to improve machine reading comprehension (MRC) by fine-tuning a pre-trained model with strategies and a target task. |
| Outcome: | The proposed models improve non-extractive machine reading comprehension (MRC) on the largest general domain multiple-choice dataset RACE. |
Abstraction-of-Thought Makes Language Models Better Reasoners (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Abstract reasoning is a key to generalization in human reasoning, but eliciting language models to perform reasoning with abstraction remains unexplored. |
| Approach: | They propose a new structured reasoning format called Abstraction-of-Thought (AoT) this approach elicits language models to first contemplate on the abstract level before incorporating concrete details . |
| Outcome: | The proposed model outperforms the prevailing Chain-of-Thought (CoT) reasoning on 23 unseen tasks. |
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to cross-lingual knowledge graph (KG) alignment rely on entity embeddings derived from monolingual KG structural information. |
| Approach: | They propose a topic entity graph to represent entities with contextual information in KGs. |
| Outcome: | The proposed model outperforms state-of-the-art methods by a large margin. |
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Standard RALMs often neglect their intrinsic knowledge due to the interference from retrieved information. |
| Approach: | They propose a new approach to improve robustness of RALMs by generating sequential reading notes for each retrieved document. |
| Outcome: | The proposed approach outperforms standard RALMs on four open-domain QA benchmarks. |
Multi-Fact Correction in Abstractive Text Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing abstractive summarization systems generate incorrect facts with respect to the source text. |
| Approach: | They propose a suite of two factual correction models that leverages question-answering knowledge to make corrections in system-generated summaries via span selection. |
| Outcome: | The proposed model improves factuality of news summarization without sacrificing summary quality. |
SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | SALAD-Bench is a safety benchmark specifically designed for LLMs . it provides a robust source for evaluating both attack and defense algorithms . |
| Approach: | They propose a hierarchical safety benchmark specifically designed for LLMs . it uses a taxonomy of questions spanning three levels and a robust taxonomies based on a QA pair . |
| Outcome: | The proposed safety benchmark shows that LLMs are resilient against emerging threats and the effectiveness of contemporary defense methods. |
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)
Copied to clipboard
Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang
| Challenge: | Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows . |
| Approach: | They propose a repository-level evaluation benchmark to assess security of AI-generated code. |
| Outcome: | The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation. |
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)
Copied to clipboard
Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong
| Challenge: | Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. |
| Approach: | They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs. |
| Outcome: | The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks. |
Polarity Calibration for Opinion Summarization (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing opinions summarization models emphasize the majority opinions while ignoring the minority opinions. |
| Approach: | They propose a method to align output summary and input text to achieve polarity calibration. |
| Outcome: | The proposed model can mitigate the polarity mismatch between output summary and input text, and maintain the content semantic and language quality. |
Generating Diverse Story Continuations with Controllable Semantics (D19-56)
Copied to clipboard
| Challenge: | a new framework for controllable story continuation generation is proposed . we use frames to generate story continuations based on sentence attributes . |
| Approach: | They propose a framework for controlled generation of multiple, diverse outputs . they use sentiment, length, predicates, frames, and automatically-induced clusters as controllable dimensions . |
| Outcome: | The proposed model produces outputs that match target attributes, the authors show . it also yields higher metric scores than previous models, they show ." |
MetaLogic: Logical Reasoning Explanations with Fine-Grained Structure (2022.emnlp-main)
Copied to clipboard
| Challenge: | Current explanation datasets often employ synthetic data with simple reasoning structures. |
| Approach: | They propose a comprehensive logical reasoning explanation form that incorporates three main components to better fit the human cognitive process. |
| Outcome: | The proposed model performs better than existing models on real-life scenarios, but is more challenging for the current models. |
CLGC: A Corpus for Chinese Literary Grace Evaluation (2022.lrec-1)
Copied to clipboard
| Challenge: | Literature grace is a key element of the style and quality of articles in China. |
| Approach: | They propose to annotate a Chinese literary grace corpus with 10,000 texts and 1.85 million tokens and build a literary grace evaluation task to assess the literary grace level. |
| Outcome: | The proposed model achieves 79.71% on the weighted average F1-score. |
BLCU-NLP at COIN-Shared Task1: Stagewise Fine-tuning BERT for Commonsense Inference in Everyday Narrations (D19-60)
Copied to clipboard
| Challenge: | Experimental results show that our system achieves significant improvements over the baseline systems with 84.2% accuracy on the official test dataset. |
| Approach: | They propose a system to inject more external knowledge into everyday narrations . they use a pre-trained BERT model to fine-tune on a machine reading comprehension dataset . |
| Outcome: | The proposed system achieves significant improvements over baseline systems with 84.2% accuracy on the official test dataset. |
Inverse Reinforcement Learning for Text Summarization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that inverse reinforcement learning (RL) training has certain disadvantages such as object mismatch and exposure bias. |
| Approach: | They propose inverse reinforcement learning (IRL) as an effective paradigm for training abstractive summarization models. |
| Outcome: | The proposed model outperforms MLE and RL baselines on ROUGE, coverage, novelty, compression ratio, factuality, and human evaluations. |
When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables (2026.acl-long)
Copied to clipboard
Shenghao Ye, Yu Guo, Dong Jin, Yuxiang Wang, Yikai Shen, Yunpeng Hou, Shuangwu Chen, null Jianyang, Xiaofeng Jiang
| Challenge: | Extensive research shows that noisy data significantly degrades the performance of table reasoning in real-world applications. |
| Approach: | They propose a dual denoising framework for complex questions and large-scale tables that uses Tree-guided table pruning to remove irrelevant data step by step. |
| Outcome: | The proposed framework achieves outstanding performance on TableQA tasks with complex questions and large-scale tables. |
Prosody-TTS: Improving Prosody with Masked Autoencoder and Conditional Diffusion Model For Expressive Text-to-Speech (2023.findings-acl)
Copied to clipboard
| Challenge: | Expressive text-to-speech aims to generate high-quality samples with rich prosody . prosodic attributes in highly dynamic voices are difficult to capture and model without intonation . |
| Approach: | They propose a pipeline that enhances prosody modeling and sampling by introducing a self-supervised masked autoencoder and a diffusion model to sample diverse prosodic patterns within the latent space. |
| Outcome: | The proposed pipeline achieves new state-of-the-art in text-to-speech with natural and expressive synthesis. |