Papers by Yuan Hu

Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models (2025.emnlp-main)

Challenge:	Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach:	They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome:	The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.

Copied to clipboard

Kaiyan Chang, Yonghao Shi, Chenglong Wang, Hang Zhou, Chi Hu, Xiaoqian Liu, Yingfeng Luo, Yuan Ge, Tong Xiao, JingBo Zhu

FISTAPruner: Layer-wise Post-training Pruning for Large Language Models (2025.emnlp-main)

Challenge:	Recent training-based TTS methods, such as continued reinforcement learning, have surged in popularity, while training-free TTS approaches are gradually fading from prominence.
Approach:	They propose a fine-grained sequential scaling method guided by process verification that integrates training-free TTS methods with other classical parallel scaling methods at the step level.
Outcome:	Experiments on five instruction-tuned large language models (LLMs) show that training-free TTS methods can extend reasoning performance boundaries.

Copied to clipboard

Pengxiang Zhao, Hanyu Hu, Ping Li, Yi Zheng, Zhefeng Wang, Xiaoming Yuan

Composable Text Controls in Latent Space with ODEs (2023.emnlp-main)

Challenge:	Existing pruning methods require inefficient retraining for billion-scale LLMs or rely on heuristicically designed metrics to determine pruning masks, leading to performance degradation.
Approach:	They propose a convex optimization model that induces sparsity in large language models by leveraging FISTA.
Outcome:	The proposed method can remove 50% of model parameters while retaining 98.6% and 95.6% of the zero-shot performance.

Copied to clipboard

Guangyi Liu, Zeyu Feng, Yuan Gao, Zichao Yang, Xiaodan Liang, Junwei Bao, Xiaodong He, Shuguang Cui, Zhen Li, Zhiting Hu

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)

Challenge:	Existing approaches to composable text operations often require plug-and-play . a single LM can perform arbitrary text operation composition in the latent space .
Approach:	They propose an efficient approach for composable text operations in the latent space of text . they connect pretrained LMs to the laten space and adapt them to the space .
Outcome:	The proposed approach improves on existing methods in the latent space of text.

Copied to clipboard

Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)

Challenge:	PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks.
Approach:	They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks.
Outcome:	The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning (2025.findings-naacl)

Challenge:	Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach:	They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome:	The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.

Copied to clipboard

Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots (2022.findings-acl)

Challenge:	Existing decoding strategies for chain-of-thought reasoning do not exploit prior information about question difficulty.
Approach:	They propose a decoding strategy called self-consistency to improve reasoning performance by adjusting the number of samples based on the posterior distribution of a set of pre-samples.
Outcome:	The proposed method outperforms baseline methods on arithmetic, commonsense and symbolic reasoning tasks while achieving comparable performance.

Copied to clipboard

Sai Zhang, Yuwei Hu, Yuchuan Wu, Jiaman Wu, Yongbin Li, Jian Sun, Caixia Yuan, Xiaojie Wang

Dialogue Systems & Conversational Agents

Challenge:	Sub-Slot based task-oriented dialogs provide slot values segment by segment over multiple turns.
Approach:	They define a task called Sub-Slot based Task-Oriented Dialog (SSTOD) they build a Chinese dialog dataset SSD for boosting research on SSTOD.
Outcome:	The proposed task is called Sub-Slot based Task-Oriented Dialog (SSTOD) it includes 40K dialogs and 500K utterances from Chinese names, phone numbers, ID numbers and license plate numbers . the dataset is well annotated with sub-slot values, slot values, dialog states and actions .

Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning (2020.coling-main)

Copied to clipboard

Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han, Songlin Hu

R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Challenge:	Existing models for fake news detection are often insufficient or lacking in features . a novel structure-aware multi-head attention network can detect fake news in 4 hours .
Approach:	They propose a structure-aware multi-head attention network to detect fake news in mass news . they use credibility of publishers and users as prior weakly supervised information .
Outcome:	The proposed model can detect fake news in 4 hours with an accuracy of over 91% . the proposed model is faster than the state-of-the-art models .

Copied to clipboard

Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, null Yiwu, Yao Hu, Jun Zhao, Kang Liu

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs (2026.findings-acl)

Challenge:	Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach:	They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome:	The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.

Copied to clipboard

Jinbo Liu, Defu Cao, Yifei Wei, Tianyao Su, Yuan Liang, Yushun Dong, Yan Liu, Yue Zhao, Xiyang Hu

Robustness in NLP

Challenge:	Multi-agent LLMs are rapidly moving from prototype to real-world use . network topology is a first-order security parameter in multi-aggent systems .
Approach:	They propose a framework for comparing topology-conditioned memory leakage in multi-agent LLM systems.
Outcome:	The proposed framework evaluates topology-conditioned memory leakage in multi-agent LLM systems.

Chinese Lexical Substitution: Dataset and Method (2023.emnlp-main)

Copied to clipboard

Jipeng Qiang, Kang Liu, Ying Li, Yun Li, Yi Zhu, Yun-Hao Yuan, Xiaocheng Hu, Xiaoye Ouyang

Low-Resource NLP

Challenge:	Existing benchmarks for lexical substitution (LS) are limited and limited in coverage . despite extensive research on Lexical Substitution in various languages, there is limited evidence for LS in Chinese.
Approach:	They propose to use human and machine collaboration to construct a Chinese LS dataset . they combine four unsupervised LS methods to generate candidate substitutes .
Outcome:	The proposed method outperforms existing benchmarks on the Chinese lexical substitution task.

RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners (2024.lrec-main)

Copied to clipboard

Chi Hu, Yuan Ge, Xiangnan Ma, Hang Cao, Qiang Li, Yonghua Yang, Tong Xiao, Jingbo Zhu

Dialogue Systems & Conversational Agents

Challenge:	Existing solutions to reasoning tasks require extensive human annotations or fail in scenarios with inconsistent responses.
Approach:	They propose a new method that enables LLMs to self-rank their responses without additional resources.
Outcome:	The proposed method improves reasoning performance of ChatGPT and GPT-4 with 13% improvement over existing methods.

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots (D19-1)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Chunyuan Yuan, Wei Zhou, Mingming Li, Shangwen Lv, Fuqing Zhu, Jizhong Han, Songlin Hu

Natural Language Interfaces

Challenge:	Existing studies focus on matching candidate responses with every context utterance, but it also brings noise signals and unnecessary information.
Approach:	They propose a multi-hop selector network to match context with candidate responses . they propose to use a selector to filter the relevant utterances as context .
Outcome:	The proposed model outperforms state-of-the-art methods on three public multi-turn dialogue datasets.

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion (2024.emnlp-main)

Copied to clipboard

Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang, Shaochen Zhong, Jiayi Yuan, Hongye Jin, Zirui Liu, Vipin Chaudhary, Shuai Xu, James Caverlee, Xia Hu

Focused Large Language Models are Stable Many-Shot Learners (2024.emnlp-main)

Challenge:	Existing mechanisms compromise ownership rights or raise data privacy concerns . existing mechanisms compromise security of released large language models .
Approach:	They propose a TaylorMLP to preserve the ownership of large language models by transforming the weights of LLMs into Taylor-series parameters instead of releasing original weights .
Outcome:	The proposed model preserves ownership of large language models and prevents their abuse by adjusting the generation speed and causing low-speed token generation.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

ℛ3: Advertisement Compliance ℛectification via Group-ℛelative Experience Extractor and Curriculum ℛeinforcement (2026.acl-industry)

Challenge:	In-Context Learning (ICL) enables large language models to achieve rapid task adaptation by learning from demonstrations.
Approach:	They propose a training-free method that disperses model attention from the query . they propose 'focus' search strategy that uses model perplexity to ensure sufficient attention .
Outcome:	The proposed method achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations.

Copied to clipboard

Yuan Chen, Zhenyu Hu, Mengge Xue, Cao Te, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang

InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)

Challenge:	Existing methods of content moderation are infeasible due to over-editing and compromise the advertiser’s original semantic intent.
Approach:	They propose a framework to harmonize compliance with original intent preservation that integrates a data-driven framework and a curriculum to enforce compliance while maximizing semantic consistency.
Outcome:	The proposed framework outperforms state-of-the-art baselines on industrial datasets and on online A/B testing on industrial video.

Copied to clipboard

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

Two Streams, One Sarcasm: Orthogonal Expert Tuning for Holistic Multimodal Sarcasm Understanding (2026.acl-long)

Challenge:	Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs.
Approach:	They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time.
Outcome:	The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets.

Copied to clipboard

Diandian Guo, Cong Cao, Fangfang Yuan, Pin Xu, Cheng Hu, Zhicheng Zhang, Yu Liu, Yanbing Liu

Sentiment Analysis

Challenge:	Existing benchmarks for multimodal satirical cognition hinder evaluation of multimodal Sarcasm Understanding . lack of a unified benchmark for holistic satire cognition hampers evaluation of MSU .
Approach:	They propose a framework to decouple experts into orthogonal shared perception and private execution streams to physically block gradient interference between tasks.
Outcome:	The proposed framework achieves superior performance on DocMSU-PLUS.

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation (2024.acl-long)

Copied to clipboard

Xinglin Wang, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations (2025.findings-emnlp)

Challenge:	Existing methods to improve output quality without aggregating input tokens are limited by the complexity of aggregation of responses.
Approach:	They propose to extract and integrate segment-level commonalities from candidate samples to enhance performance of LLMs in open-ended and reasoning tasks.
Outcome:	The proposed method improves performance on reasoning, code generation and mathematical reasoning tasks without requiring additional models and overlooking the knowledge present among the candidates.

Copied to clipboard

Bowen Jiang, Yuan Yuan, Xinyi Bai, Zhuoqun Hao, Alyson Yin, Yaojie Hu, Wenyu Liao, Lyle Ungar, Camillo Jose Taylor

Visual Data in NLP

Challenge:	a new method for visual text rendering requires glyph annotations to be obtained .
Approach:	They propose a model that integrates diffusion with a text segmentation model to achieve multilingual text rendering using just raw images without font label annotations.
Outcome:	The proposed model can achieve font-controllable multilingual text rendering without label annotations.

TCP: a Benchmark for Temporal Constraint-Based Planning (2025.emnlp-main)

Copied to clipboard

Zifeng Ding, Sikuan Yan, Moy Yuan, Xianglong Hu, Fangru Lin, Andreas Vlachos

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks evaluate temporal reasoning and planning in isolation and under limited forms of complexity.
Approach:	They propose a temporal constraint-based planning benchmark that assesses temporal reasoning and planning capabilities in large language models.
Outcome:	The proposed model fails to perform well under limited constraints and lacks temporal grounding.

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Xiaoyun Zhang, Xiaojian Yuan, Di Huang, Wang You, Chen Hu, Jingqing Ruan, Kejiang Chen, Xing Hu

Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval (2024.lrec-main)

Challenge:	Reasoning ability is a defining capability of Large Language Models (LLMs), but RLVR training suffers from policy entropy collapse, hindering exploration and limiting reasoning performance.
Approach:	They propose a framework that dynamically balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.
Outcome:	The proposed framework outperforms baselines on multiple mathematical reasoning benchmarks.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation (2024.emnlp-main)

Challenge:	Existing methods for video-text retrieval capture fine-grained semantic concepts . however, they lack the ability to capture finer-grain concepts such as objects and actions.
Approach:	They propose a dual-encoder architecture for fast video-text retrieval that learns lexicon representations to capture fine-grained semantics.
Outcome:	The proposed framework outperforms existing methods with 4.8% and 8.2% improvement on MSR-VTT and DiDeMo respectively.

Copied to clipboard

Yuan Ge, Yilun Liu, Chi Hu, Weibin Meng, Shimin Tao, Xiaofeng Zhao, Mahong Xia, Zhang Li, Boxing Chen, Hao Yang, Bei Li, Tong Xiao, JingBo Zhu

Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations (2025.findings-emnlp)

Challenge:	Existing methods for instruction data selection have limitations such as relying on fragile external APIs, being affected by biases in GPT models, or reducing the diversity of the selected instruction dataset.
Approach:	They propose an industrial-friendly, expert-aligned and diversity-preserved instruction data selection method: Clustering and Ranking (CaR).
Outcome:	The proposed method outperforms Alpaca's existing methods by 32.1% in GPT-4 evaluations.

Copied to clipboard

Yifan Lu, Ziqi Zhang, Chunfeng Yuan, Jun Gao, Congxuan Zhang, Xiaojuan Qi, Bing Li, Weiming Hu

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)

Challenge:	Existing methods for hallucination mitigation are based on external dependency and require external annotations or auxiliary models for preference data collection.
Approach:	a new method is proposed to help model-generated hallucinations without external dependencies.
Outcome:	a new method that self-injects hallucinations into a generated response improves halluuutations mitigation.

Copied to clipboard

Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)

Challenge:	Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models.
Approach:	They propose a method that conducts customized evaluation tailored to each target model.
Outcome:	The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

TEF: Causality-Aware Taxonomy Expansion via Front-Door Criterion (2025.coling-main)

Challenge:	Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling.
Approach:	They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space.
Outcome:	The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks.

Copied to clipboard

Yuan Meng, Songlin Zhai, Yuxin Zhang, Zhongjian Hu, Guilin Qi

KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)

Challenge:	Existing research still faces spurious query-anchor matching due to unobserved factors.
Approach:	They propose a model that uses the front-door criteria to decompose the expansion process into a parser module and a connector to isolate confounding effects.
Outcome:	Extensive experiments on three benchmarks validate the effectiveness of the proposed model.

Copied to clipboard

Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu

Multi-Task Representation Alignment on Language Understanding: A Mutual Information Perspective (2026.acl-long)

Challenge:	Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts.
Approach:	They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs.
Outcome:	The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks.

Copied to clipboard

Dou Hu, Lingwei Wei, Hongjiang Xiao, Songlin Hu, Yuan Zhang

Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods (2026.acl-long)

Challenge:	Existing approaches to multitask learning fail to address task interference issues . Existing methods focus on task balancing or probabilistic modeling but fail to learn sufficient representations for all target tasks.
Approach:	They propose a multi-task representation alignment framework to achieve task-specific alignment and self-alignment on shared representations from a mutual information perspective.
Outcome:	The proposed framework outperforms 13 representative MTL methods under label-noisy and data-constrained conditions.

Copied to clipboard

Hanzhang Yuan, Mengxuan Hu, Wenhao Zhang, Tianlong Wang, Zhongliang Zhou, Jiasen Lu, Sheng Li

Visual Data in NLP

Challenge:	Large Vision-Language Models (LVLMs) excel at visual understanding but face severe computational bottlenecks when processing high-resolution images and long videos due to massive visual token counts.
Approach:	They propose a taxonomy categorizing methods into vision-side, LLM-side and hybrid paradigms and analyze token selection mechanisms and pruning strategy.
Outcome:	The proposed method selectively removes less informative tokens while maintaining performance.

DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction (2025.findings-emnlp)

Copied to clipboard

Jian Chen, Zhenyan Chen, Xuming Hu, Peilin Zhou, Yining Hua, Han Fang, Cissy Hing Yee Choy, Xinmei Ke, Jingfeng Luo, Zixuan Yuan

Programming Languages in NLP

Challenge:	NL2SQL provides a model-centric paradigm that simplifies database access for non-technical users . challenges such as inaccurate task decomposition and keyword extraction remain major bottlenecks .
Approach:	They propose a RAG-based NL2SQL pipeline that employs three modules for query understanding, entity retrieval, and generation to improve SQL generation accuracy.
Outcome:	The proposed pipeline improves the accuracy of query generation on BIRD and Spider datasets.

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)

Copied to clipboard

Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu

Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains (2026.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability .
Approach:	They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR .
Outcome:	The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks.

Copied to clipboard

Zhonghang Yuan, Zhefan Wang, Fang Hu, Zihong Chen, Jinzhe Li, Gang Li, Jie Ying, Huanjun Kong, Songyang Zhang, Nanqing Dong

CogLM: Tracking Cognitive Development of Large Language Models (2025.naacl-long)

Challenge:	Recent large language models (LLMs) have demonstrated remarkable progress in reasoning, but their applications on knowledge-intensive domains have not been explored due to the scarcity of high-quality verifiable data.
Approach:	They propose a framework that extends reinforcement learning with verifiable rewards (RLVR) to knowledge-intensive domains through automated verififiability data synthesis while enabling verification of the LLM's reasoning process.
Outcome:	Extensive experiments show that the proposed framework enhances the reasoning of large language models in knowledge-intensive domains without significantly compromising the model’s general capabilities.

Copied to clipboard

Xinglin Wang, Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have recently shown remarkable abilities across a wide variety of tasks, but few studies have explored the reasons behind the evolutionary relationship among various abilities.
Approach:	They construct a benchmark CogLM based on Piaget's Theory of Cognitive Development (PTC) which measures the cognitive levels of Large Language Models (LLMs) using 1,220 questions spanning 10 cognitive abilities crafted by more than 20 human experts.
Outcome:	The proposed framework provides a comprehensive testbed for the cognitive levels of LLMs.

Copied to clipboard

Guangze Gao, Zixuan Li, Chunfeng Yuan, Jiawei Li, Wu Jianzhuo, Yuehao Zhang, Xiaolong Jin, Bing Li, Weiming Hu

FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)

Challenge:	Existing approaches to Knowledge Graph Question Answering (KGQA) use Retrieval-Augmented Generation (RAG) but subgraph selection process is non-differentiable, preventing end-to-end training of the retriever and the generator.
Approach:	They propose a Differentiable RAG approach that optimizes the retriever and the generator for KGQA.
Outcome:	The proposed approach outperforms state-of-the-art approaches on WebQSP and CWQ.

Copied to clipboard

Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Shuaiyu Zhang, Shiyang Feng, Xiangchao Yan, Shufei Zhang, Wenlong Zhang, Lei Bai, Bo Zhang

GUICourse: From General Vision Language Model to Versatile GUI Agent (2025.acl-long)

Challenge:	FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Approach:	They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Outcome:	The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download.

Copied to clipboard

Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan Yao, Yankai Lin, Zhiyuan Liu, Maosong Sun

Visual Data in NLP

Challenge:	Graphical User Interfaces (GUIs) are a pivotal medium for human-computer interaction.
Approach:	They propose a series of datasets for training visual-based GUI agents using general VLMs.
Outcome:	The proposed GUICourse datasets show that even a small-sized GUI agent performs better on GUI tasks.

LaMPE: Length-aware Multi-grained Positional Encoding for Adaptive Long-context Scaling Without Training (2026.findings-acl)

Copied to clipboard

Sikui Zhang, Guangze Gao, Ziyun Gan, Chunfeng Yuan, Zefeng Lin, Houwen Peng, Bing Li, Weiming Hu

Challenge:	Large language models (LLMs) experience significant performance degradation when the input exceeds the pretraining context window due to the out-of-distribution (OOD) behavior of Rotary Position Embedding (RoPE).
Approach:	They propose a training-free method that remaps out-of-distribution (OOD) positions into the in-distance range with fixed mapping strategies, ignoring the dynamic relationship between input length and effective context window.
Outcome:	Experiments on three representative LLMs across five mainstream long-context benchmarks show that the proposed method achieves significant performance improvements compared to existing methods.

LegalAgentBench: Evaluating LLM Agents in Legal Domain (2025.acl-long)

Copied to clipboard

Haitao Li, Junjie Chen, Jingli Yang, Qingyao Ai, Wei Jia, Youfeng Liu, Kai Lin, Yueyue Wu, Guozhi Yuan, Yiran Hu, Wuyue Wang, Yiqun Liu, Minlie Huang

Challenge:	Existing general-domain benchmarks do not capture complexity of real-world judicial cognition and decision-making.
Approach:	They propose a benchmark specifically designed to evaluate LLM Agents in the legal domain.
Outcome:	The proposed benchmark includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge.

AMPO: Automatic Multi-Branched Prompt Optimization (2024.emnlp-main)

Copied to clipboard

Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding, Anbang Hu, Yuan Fang, Yunsong Li, Junyan Chen, Linjun Yang

DHP Benchmark: Are LLMs Good NLG Evaluators? (2025.findings-naacl)

Challenge:	Existing prompt engineering techniques are limited to producing single flow instructions, struggling with handling diverse patterns.
Approach:	They propose an automatic prompt optimization method that iteratively develops a multi-branched prompt using failure cases as feedback.
Outcome:	The proposed method achieves the best results across five tasks and demonstrates significant optimization efficiency due to adoption of a minimal search strategy.

Copied to clipboard

Yicheng Wang, Jiayi Yuan, Yu-Neng Chuang, Zhuoer Wang, Yingchi Liu, Mark Cusick, Param Kulkarni, Zhengping Ji, Yasser Ibrahim, Xia Hu

Text Generation

Challenge:	Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks.
Approach:	They propose a framework that measures the discernment of Large Language Models (LLMs) across diverse NLG tasks.
Outcome:	The proposed framework provides quantitative discernment scores for LLMs across four NLG tasks.

TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation (2024.acl-long)

Copied to clipboard

Yikai Zhang, Siyu Yuan, Caiyu Hu, Kyle Richardson, Yanghua Xiao, Jiangjie Chen

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem (2025.findings-emnlp)

Challenge:	e.g., GPT-4 still lag behind humans in effective multitasking, a study finds . current textual simulations do not adequately address the notion of time .
Approach:	They propose a textual simulated environment that incorporates complex temporal dynamics and constraints that better reflect real-life planning scenarios.
Outcome:	The proposed model incorporates complex temporal dynamics and constraints that better reflect real-life planning scenarios.

Copied to clipboard

Hongyi Liu, Shaochen Zhong, Xintong Sun, Minghao Tian, Mohsen Hariri, Zirui Liu, Ruixiang Tang, Zhimeng Jiang, Jiayi Yuan, Yu-Neng Chuang, Li Li, Soo-Hyun Choi, Rui Chen, Vipin Chaudhary, Xia Hu

FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture (2024.emnlp-main)

Challenge:	distributing LLMs without a proven track record like ‘meta-llama‘ or ‘qwen‘ rarely gains community traction.
Approach:	They propose a simple, efficient, yet specific recipe for a backdoor LoRA to be injected into task-enhancing LoRAs and examine the mechanisms of such infections.
Outcome:	The proposed model allows attackers to scale the distribution of compromised LoRAs with minimal effort by leveraging the rich pool of shared LoRA assets.

Copied to clipboard

Wenyan Li, Crystina Zhang, Jiaang Li, Qiwei Peng, Raphael Tang, Li Zhou, Weijia Zhang, Guimin Hu, Yifei Yuan, Anders Søgaard, Daniel Hershcovich, Desmond Elliott

Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Challenge:	FoodieQA is a manually curated, fine-grained image-text dataset capturing the intricate features of food cultures across various regions in China.
Approach:	They evaluate vision–language Models and large language models on unseen food images and corresponding questions.
Outcome:	The proposed dataset evaluates vision–language Models and large language models on unseen food images and corresponding questions.

Copied to clipboard

Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Challenge:	Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach:	They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome:	The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.

Copied to clipboard

Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang

DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models (2024.naacl-demo)

Challenge:	Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach:	They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome:	The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.

Copied to clipboard

Songbo Hu, Xiaobin Wang, Moy Yuan, Anna Korhonen, Ivan Vulić

Natural Language Interfaces

Challenge:	DIALIGHT is a toolkit for developing and evaluating multilingual Task-Oriented Dialogue systems.
Approach:	They propose a toolkit for developing and evaluating multilingual Task-Oriented Dialogue systems which facilitates systematic evaluations and comparisons between ToD systems using pretrained language models and those utilising the zero-shot and in-context learning capabilities of Large Language Models.
Outcome:	The toolkit enables systematic evaluations between ToD systems using pretrained language models and those utilising the zero-shot and in-context learning capabilities of Large Language Models (LLMs).

A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems (2023.emnlp-main)

Copied to clipboard

Songbo Hu, Han Zhou, Moy Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić

Natural Language Interfaces

Challenge:	Existing systems trained for Arabic or Turkish using annotated data fully parallel to English ToD data still exhibit diminished ToD task performance.
Approach:	They define new quantitative measures of absolute and relative equivalence in system performance, capturing disparities across languages and within individual languages.
Outcome:	The proposed measures capture disparities across languages and within individual languages.

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classification (2025.findings-emnlp)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

Yifei Yuan, Jiatong Li, Weijia Zhang, Mohammad Aliannejadi, Evangelos Kanoulas, Renjun Hu

Information Extraction & Text Mining

Challenge:	Recent studies show the promise of large language models for few-shot tabular classification but highlight challenges due to the variability in structured data.
Approach:	They propose a framework that distills data into actionable insights to enable robust and effective classification by large language models.
Outcome:	The proposed framework integrates rule summarization, strategic exemplification, and insight reflection through deep collaboration between LLMs and data modeling techniques.

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)

Copied to clipboard

Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li

Challenge:	Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications.
Approach:	They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis.
Outcome:	The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.

AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)

Copied to clipboard

Feng Luo, Yu-Neng Chuang, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu

Conformal Event Prediction with Temporal Knowledge Graph (2026.findings-acl)

Challenge:	Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions.
Approach:	They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary.
Outcome:	The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy.

Copied to clipboard

Cheng Hu, Cong Cao, Fangfang Yuan, Diandian Guo, Pin Xu, Yu Liu, Yanbing Liu

Knowledge Representation

Challenge:	Current event prediction methods lack rigorous uncertainty quantification, which limits their reliability for decision-making.
Approach:	They propose a conformal prediction framework that applies conformal predictions to event prediction to address this challenge.
Outcome:	The proposed framework guarantees coverage while improving efficiency on three public datasets.

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Copied to clipboard

Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)

Challenge:	Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach:	They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome:	The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.

Copied to clipboard

Xu Huang, Wenhao Zhu, Hanxu Hu, Conghui He, Lei Li, Shujian Huang, Fei Yuan

Can Pretrained Language Models (Yet) Reason Deductively? (2023.eacl-main)

Challenge:	Existing multilingual benchmarks focus primarily on language understanding tasks.
Approach:	They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages.
Outcome:	Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve.

Copied to clipboard

Zhangdie Yuan, Songbo Hu, Ivan Vulić, Anna Korhonen, Zaiqiao Meng

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)

Challenge:	Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted increasing attention, showing promising performance in many knowledge-intensive tasks.
Approach:	They conduct a comprehensive evaluation of the learnable deductive reasoning capability of pretrained language models and compare their performance against simple adversarial surface form edits.
Outcome:	The models are able to generalise learned logic rules and perform inconsistently against simple adversarial surface form edits, but catastrophically forget the previously learnt knowledge.

Copied to clipboard

Peidong Wang, Zhiming Ma, Xin Dai, YongKang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang

SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification (2026.acl-industry)

Challenge:	Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors .
Approach:	They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details.
Outcome:	The proposed method improves accuracy, inference efficiency, and real-time processing capabilities.

Copied to clipboard

Cao Te, Mengge Xue, Zhenyu Hu, Yuan Chen, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang

Label-Specific Dual Graph Neural Network for Multi-Label Text Classification (2021.acl-long)

Challenge:	Existing methods to fix non-compliant images suffer from over-editing, destroying original intent and perceptual similarity.
Approach:	They propose a framework for the minimalist rectification of non-compliant image ads.
Outcome:	The proposed framework outperforms state-of-the-art baselines in both compliance and preservation of visual and commercial consistency.

Copied to clipboard

Qianwen Ma, Chunyuan Yuan, Wei Zhou, Songlin Hu

Information Extraction & Text Mining

Challenge:	Existing studies for multi-label text classification do not explore label-specific semantic components from documents.
Approach:	They propose a label-specific dual graph neural network that incorporates category information to learn label-related components from documents.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark datasets and achieves better performance with respect to tail labels.

Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering (2024.lrec-main)

Copied to clipboard

Yuan Gao, Yiheng Zhu, Yuanbin Cao, Yinzhi Zhou, Zhen Wu, Yujie Chen, Shenglan Wu, Haoyuan Hu, Xinyu Dai

Question Answering

Challenge:	Open Domain Multi-Hop Question Answering (ODMHQA) is one of the most challenging tasks in Natural Language Processing (NLP)
Approach:	They propose a mechanism that leverages the intrinsic capabilities of Large Language Models to judge whether the generated answers are off-topic.
Outcome:	The proposed method reduces the occurrence of off-topic answers by nearly 13%, improving the performance in Exact Match (EM) by nearly 3% compared to the baseline method without the Dr3 mechanism.

CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite (2024.lrec-main)

Copied to clipboard

Yifei Yuan, Chen Shi, Wang Runze, Liyi Chen, Renjun Hu, Zengming Zhang, Feijun Jiang, Wai Lam

TeCES: Collaborative Geometric Knowledge Representation Framework under Evolving Fact Snapshots (2026.acl-long)

Challenge:	Recent advances in conversational IR systems have seen a resurgent interest in conversation . generative query rewrite generates reconstructed query based on the conversation history .
Approach:	They propose to use unlabeled data to make further improvements using contrastive co-training paradigm.
Outcome:	The proposed model is robust to noise and language style shift under few-shot and zero-shot scenarios.

Copied to clipboard

Jiujiang Guo, Zhengliang Guo, Kai Wang, Meiyang Wang, Dehua Peng, Shaozu Yuan, Chengyin Hu, Shuan Ai, Yiwei Wei

PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models (2024.acl-long)

Challenge:	Existing knowledge graphs represent static facts but lack collaborative modeling of both . e.g., existing knowledge graph models lack a framework for integrating snapshots into knowledge graph.
Approach:	They propose a framework for high-fidelity modeling of evolving snapshots using concept of snapshots.
Outcome:	The proposed framework outperforms existing models on six benchmarks.

Copied to clipboard

Haoran Li, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, Yuan Yao, Yangqiu Song

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Challenge:	generative large language models (LLMs) exhibit surprising capability and integrate previous tasks into a unified text generation formulation.
Approach:	They propose a privacy evaluation benchmark to quantify the privacy leakage of language models.
Outcome:	The proposed benchmark compares PPLMs with different privacy implementations to find out how privacy leakage is handled.

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworks (2025.findings-acl)

Copied to clipboard

Jiamu Zhang, Jiayi Yuan, Andrew Wen, Hoang Anh Duy Le, Yu-Neng Chuang, Soo-Hyun Choi, Rui Chen, Xia Hu

Poor-Supervised Evaluation for SuperLLM via Mutual Consistency (2024.findings-acl)

Challenge:	Large Language Models (LLMs) are increasingly adopted across real-world applications . traditional evaluations rely on expensive, domain-specific ground-truth labels . obtaining labeled data is expensive, time-consuming, and often requires domain expertise .
Approach:	They propose a ground-truth-free evaluation framework focused on reasoning consistency and instruction following.
Outcome:	The proposed framework outperforms existing label-free methods, including majority voting, triplet ranking, and peer-review approaches.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Explaining Length Bias in LLM-Based Preference Evaluations (2025.findings-emnlp)

Challenge:	evaluating superLLMs is especially difficult because of their intelligence-intensive nature.
Approach:	They propose an evaluation benchmark with accurate labels for SuperLLMs whose capabilities surpass those of humans . they first prove that consistency between model under evaluation and reference model can equalize the true capabilities of the model to be evaluated .
Outcome:	The proposed evaluation benchmarks can assess the true capabilities of the model to be evaluated without accurate labels.

Copied to clipboard

Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong