Papers by Yuhao Wang

S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)

Challenge:	Existing end-to-end speech large language models rely on large-scale annotated data for training, while data-efficient training has not been discussed in depth.
Approach:	They propose a training strategy and a novel architecture to address representation space gap and sequence length inconsistency in speech and text.
Outcome:	The proposed model outperforms other advanced speech LLMs in speech translation and AIR-Bench speech tasks with only a fraction of the training data.

Copied to clipboard

Feng Jiang, Zhiyu Lin, Yiyang Liu, Liumeng Xue, Fan Bu, Yuhao Du, Xiangying Chen, Benyou Wang, Haizhou Li

Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation (2025.findings-acl)

Challenge:	Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits.
Approach:	They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression.
Outcome:	The proposed system enables more natural, robust, and human-aligned speech agents.

Copied to clipboard

Yuhao Zhang, Xiangnan Ma, Kaiqi Kou, Peizhuo Liu, Weiqiao Shan, Benyou Wang, Tong Xiao, Yuxin Huang, Zhengtao Yu, JingBo Zhu

Multilinguality

Challenge:	Existing textless speech-to-speech translation models have two main challenges: 1) learning cross-modal features and 2) learning alignment of difference languages in long sequences.
Approach:	They propose a unit language to overcome two main modeling challenges . they propose task prompt modeling to utilize the unit language in guiding the modeling process.
Outcome:	The proposed language improves over a strong baseline and achieves comparable performance to models trained with text.

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions (2025.naacl-industry)

Copied to clipboard

Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

Challenge:	Streaming automatic speech recognition models use high power consumption to improve usability and accuracy.
Approach:	They propose to optimize on-device speech recognition models by adjusting component energy sensitivities based on their specific energy sensitities to reduce power consumption.
Outcome:	The proposed approach achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.

Copied to clipboard

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry (2026.acl-long)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Han Zhang, Zihan Gu, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu, Xinyan Zhang, Yuhao Wei, Cheng Hua

Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, but it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns.
Approach:	They propose a benchmark that combines a constructionist Out-of-Sample dataset with reverse understanding probes to evaluate large-scale large-format models.
Outcome:	The proposed model performs well on classical Chinese poetry benchmarks, but a performance gap persists . the model can complete famous couplets and can be used to understand a variety of texts.

Copied to clipboard

Lu Chen, Rui Zheng, Binghai Wang, Senjie Jin, Caishuang Huang, Junjie Ye, Zhihao Zhang, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

A Query-Parallel Machine Reading Comprehension Framework for Low-resource NER (2023.findings-emnlp)

Challenge:	Current methods rely on ranking losses to teach reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions.
Approach:	They propose a method that incorporates contrastive learning into the reward modeling process to enhance generalization and stabilize the reinforcement learning training process.
Outcome:	The proposed method enhances generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences.

Copied to clipboard

Yuhao Zhang, Yongliang Wang

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Named entity recognition (NER) is a fundamental task in natural language processing.
Approach:	They propose a query-parallel MRC-based approach to named entity recognition . the model is trained with parameter-efficient tuning technique, making it more data-efficient .
Outcome:	The proposed model performs competitively against strong baseline methods in resource-rich settings and achieves state-of-the-art results in low-resource settings.

Copied to clipboard

Pengyue Jia, Derong Xu, Xiaopeng Li, Zhaocheng Du, Xiangyang Li, Yichao Wang, Yuhao Wang, Qidong Liu, Maolin Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations (2025.coling-main)

Challenge:	Existing approaches to rerank and align documents based on reasoning capabilities of large language models (LLMs) . prior work shows that LLMs have exceptional reasoning and text generation capabilities .
Approach:	They propose a rationale extraction method that leverages reasoning capabilities of large language models to extract the rationales necessary for answering a query.
Outcome:	The proposed method is compared with baseline methods on two tasks across three datasets.

Copied to clipboard

Wenlin Zhang, Chuhan Wu, Xiangyang Li, Yuhao Wang, Kuicai Dong, Yichao Wang, Xinyi Dai, Xiangyu Zhao, Huifeng Guo, Ruiming Tang

Miner: Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models (2026.acl-long)

Challenge:	Lack of training data leads to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations.
Approach:	They propose a tree-based LLM recommendation framework which structures all items into an item tree to improve the efficiency of LLM’s item retrieval.
Outcome:	The proposed framework outperforms the baseline model in the A/B test on Huawei industrial system.

Copied to clipboard

Shuyang Jiang, Yuhao Wang, Ya Zhang, Yanfeng Wang, Yu Wang

SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning (2026.findings-acl)

Challenge:	Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts.
Approach:	They propose a method that repurposes the policy’s intrinsic uncertainty as a self-supervised reward signal, with no external supervision, auxiliary models, or additional inference cost.
Outcome:	Evaluated across six reasoning benchmarks on Qwen3-4B and Qwend3-8B base models, the proposed method achieves state-of-the-art performance among the other four methods.

Copied to clipboard

Kehua Feng, Keyan Ding, Yuhao Wang, Menghan Li, Fanjunduo Wei, Xinda Wang, Huajun Chen

Bridging the Granularity Gap for Acoustic Modeling (2023.findings-acl)

Challenge:	Existing alignment methods struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks.
Approach:	They propose a framework for 'Safety' alignment via eFficient' Ex-Ante-R**easoning that instantiates structured Ex-Ance reasoning and embeds predefined safety rules.
Outcome:	The proposed framework enhances safety performance while maintaining usefulness and efficiency.

Copied to clipboard

Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu, Chi Hu, Xin Zeng, Tong Xiao, Anxiang Ma, Huizhen Wang, Jingbo Zhu

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Challenge:	Despite the success of speech recognition, how to encode the speech features effectively remains an open problem.
Approach:	They propose a Progressive Down-Sampling technique which compresses acoustic features into coarser-grained units containing more complete semantic information, like text-level representation.
Outcome:	The proposed method yields comparable or better results on the speech recognition task and inference speedups ranging from 1.20x to 1.47x.

Copied to clipboard

Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach:	They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome:	The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu

Machine Translation

Challenge:	End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach:	They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome:	The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.

Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)

Copied to clipboard

Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu

Challenge:	Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols.
Approach:	They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations.
Outcome:	The proposed method reveals local knowledge conflicts invisible to existing benchmarks.

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward (2026.findings-acl)

Copied to clipboard

Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou

RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)

Challenge:	Recent studies show that RLVR training is slow and results plateau as policy entropy collapses . low-probability regularization (Lp-Reg) reduces the number of low-quality exploratory tokens induced by RL training .
Approach:	They propose a method to reduce RLVR over-penalization by eliminating low-probability exploratory tokens . they propose 'Low-provability Regularization' to reduce the gradual elimination of low-quality exploratory entropy tokens.
Outcome:	The proposed method eliminates low-probability exploratory tokens and prevents suppression of potentially valuable low-property candidates.

Copied to clipboard

Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth

Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Challenge:	Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains.
Approach:	They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control .
Outcome:	The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control.

Copied to clipboard

Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach:	They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome:	The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.

Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)

Copied to clipboard

Zhihao Zhan, Yuhao Chen, Jiaying Zhou, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang

Visual Data in NLP

Challenge:	Existing vision-Language-Action models are notoriously brittle to linguistic perturbations.
Approach:	They propose a probabilistic framework that disentangles physical affordance from semantic execution.
Outcome:	The proposed framework disentangles physical affordance from semantic execution.

DSQG-Syn: Synthesizing High-quality Data for Text-to-SQL Parsing by Domain Specific Question Generation (2025.findings-naacl)

Copied to clipboard

Shaoming Duan, Youxuan Wu, Chuanyi Liu, Yuhao Zhang, Zirui Wang, Peiyi Han, Shengyuan Yu, Liang Yan, Yingwei Liang

Programming Languages in NLP

Challenge:	Existing methods for generating SQL queries using natural language questions produce inconsistent NLQ-SQL pairs.
Approach:	They propose a text-to-SQL data synthesis framework that generates domain-relevant questions . they synthesize NLQ-SqL pairs that are domain-specific and intent-consistent .
Outcome:	The proposed method outperforms closed-source LLMs on the Text-to-SQL task.

Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization (2025.acl-long)

Copied to clipboard

Yuhao Wang, Keyan Ding, Kehua Feng, Zeyuan Wang, Ming Qin, Xiaotong Li, Qiang Zhang, Huajun Chen

Structured Data in NLP

Challenge:	Protein language models pose significant risks of generating harmful sequences, e.g., viral transmissibility, drug resistance, environmental imbalances, public health crises, etc.
Approach:	They propose a protein-based model that integrates prior knowledge via a Protein Safety Knowledge Graph to minimize the risk of generating harmful sequences.
Outcome:	The proposed framework reduces the likelihood of producing hazardous sequences while maintaining high functionality.

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism (2026.acl-long)

Copied to clipboard

Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Huan Li, Cong Wang

Information Retrieval

Challenge:	Parallel Speculative Decoding (PSD) has limitations due to speedup limits and high computational waste . a novel synchronous mechanism solves the Retrieval Precision-Efficiency Dilemma .
Approach:	They propose a framework that combines a draft-verification-based approach with a synchronous mechanism to solve the Retrieval Precision-Efficiency Dilemma.
Outcome:	The proposed framework breaks speedup limits for Speculative Decoding by overlapping draft generation with verification.

Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction (2021.naacl-main)

Copied to clipboard

Yuhao Feng, Yanghui Rao, Yuyao Tang, Ninghua Wang, He Liu

Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs (2026.acl-long)

Challenge:	Recent studies on ABSA focus on Target-oriented Opinion Words (or Terms) Extraction . Experimental results indicate that TSMSA outperforms the benchmark methods on TOWE significantly .
Approach:	They propose to use a pre-trained language model with multi-head self-attention to integrate TOWE with AOPE to extract aspects and opinion terms in pairs.
Outcome:	The proposed structure outperforms the benchmark methods on TOWE significantly . the proposed structure is similar or even better than state-of-the-art AOPE models .

Copied to clipboard

Hongcheng Liu, Yuhao Wang, Zhe Chen, Pingjie Wang, Zhiyuan Zhu, Yixuan Hou, Yanfeng Wang, Yu Wang

Information Extraction & Text Mining

Challenge:	Experiments on 13 Omni-LLMs reveal systematic weaknesses in cross-modal coreference . cross-module coreference is a crucial missing piece for advancing robust omni-modal reasoning.
Approach:	They propose a cross-modal coreference problem to evaluate and enhance Omni-LLMs' reasoning capabilities.
Outcome:	Experiments on 13 Omni-LLMs show they lack coreference-aware thinking patterns . the CROSSOMNI dataset yields significant performance gains and generalizes well to collaborative reasoning tasks.

A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple-wise Perspective in Angular Space (2022.acl-long)

Copied to clipboard

Yuhao Zhang, Hongji Zhu, Yongliang Wang, Nan Xu, Xiaobo Li, Binqiang Zhao

Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing methods for learning sentence representations focus on constitution of positive and negative representation pairs and do not focus on training objective.
Approach:	They propose a new method to learn sentence representations using BERT-like pre-trained models . they use a pairwise discriminating power and a model to model the entailment relation of triplet sentences .
Outcome:	The proposed method outperforms the previous state-of-the-art on diverse sentence related tasks.

Copied to clipboard

Yuhao Wang, Ruiyang Ren, Yucheng Wang, Xin Zhao, Jing Liu, Hua Wu, Haifeng Wang

Information Retrieval

Challenge:	Existing reinforcement learning systems lack verifiable reward mechanisms for long-form question answering . current systems lack reliable long-term answers due to lack of factual content .
Approach:	They propose a framework for reinforced verifiable informativeness optimization . it defines informativeness as measurable and externally verifier objective for RL .
Outcome:	Experiments show that RioRAG achieves higher factual recall and faithfulness . the proposed framework is based on a framework that uses nugget-centric verification with cross-source checks .

Robust Lottery Tickets for Pre-trained Language Models (2022.acl-long)

Copied to clipboard

Rui Zheng, Bao Rong, Yuhao Zhou, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang, Xuanjing Huang

Robustness in NLP

Challenge:	Recent studies have shown that pre-trained language models contain smaller matching subnetworks that are not robust to adversarial examples.
Approach:	They propose a method to find robust tickets hidden in pre-trained language models by learning binary weight masks and an adversarial loss objective to guide the search.
Outcome:	The proposed method improves on previous work on adversarial robustness evaluation.

Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations (2023.findings-acl)

Copied to clipboard

Jifan Chen, Yuhao Zhang, Lan Liu, Rui Dong, Xinchi Chen, Patrick Ng, William Yang Wang, Zhiheng Huang

EvolveBench: A Comprehensive Benchmark for Assessing Temporal Awareness in LLMs on Evolving Knowledge (2025.acl-long)

Challenge:	Existing methods for multitask learning typically use a dataset name as input prefix, which limits the effectiveness of multitask training.
Approach:	They propose compositional task configurations, a set of prompts prepended to the encoder to improve cross-task generalization of unified models.
Outcome:	The proposed model outperforms the UnifiedSKG baseline by noticeable margins in both in-domain and zero-shot settings.

Copied to clipboard

Zhiyuan Zhu, Yusheng Liao, Zhe Chen, Yuhao Wang, Yunfeng Guan, Yanfeng Wang, Yu Wang

Challenge:	Existing studies have explored how LLMs perceive time, but they often overlook the critical aspect of knowledge utilization.
Approach:	They propose a benchmark that evaluates temporal competence along five key dimensions: Cognition, Awareness, Trustworthiness and reasoning.
Outcome:	EvolveBench measures temporal competence along five key dimensions: Cognition, Awareness, Trustworthiness, Understanding and reasoning.

Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation (2025.coling-main)

Copied to clipboard

Ruiyang Ren, Yuhao Wang, Yingqi Qu, Wayne Xin Zhao, Jing Liu, Hua Wu, Ji-Rong Wen, Haifeng Wang

VocalNet: Speech LLMs with Multi-Token Prediction for Faster and High-Quality Generation (2025.emnlp-main)

Challenge:	Large language models (LLMs) have shown impressive prowess in solving a wide range of tasks with world knowledge, but it remains unclear how well they perceive their factual knowledge boundaries.
Approach:	They propose to use a retrieval augmentation approach to enhance LLMs' awareness of factual knowledge boundaries to analyze factual and factual information in open-domain question answering (QA)
Outcome:	The proposed method improves LLMs’ QA and judgemental capabilities by integrating supporting documents with the questions.

Copied to clipboard

Yuhao Wang, Heyang Liu, Ziyang Cheng, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang

CodeFort: Robust Training for Code Generation Models (2024.findings-emnlp)

Challenge:	Experimental results show VocalNet outperforms existing open-source speech LLMs despite limited training data.
Approach:	They propose a scalable and model-agnostic training framework and a novel multi-token prediction paradigm for speech generation.
Outcome:	The proposed model outperforms open-source speech LLMs while outperforming existing open-sourced models.

Copied to clipboard

Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, Anoop Deoras

Programming Languages in NLP

Challenge:	Existing research efforts to improve code generation models are inadequate . code generation model performance is degraded under small perturbations .
Approach:	They propose a framework to improve the robustness of code generation models by generalizing code perturbations to enrich training data and enabling various robust training strategies.
Outcome:	The proposed framework increases pass rates and robustness drop rate against code-syntax perturbations.

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang

Visual Data in NLP

Challenge:	Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach:	They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome:	The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.

SPO: Self Preference Optimization with Self Regularization (2025.findings-emnlp)

Copied to clipboard

Yuhao Sun, Yifan Zhang, Quandong Wang, Qinzhuo Wu, Wei Liu, Jian Luan

Machine Translation

Challenge:	Existing reference-free preference optimization methods exhibit higher training efficiency but are prone to overoptimization, leading to performance degradation.
Approach:	They propose a reference-free preference optimization method that replaces the logsigmoid loss function with a SiLU function to improve the model's performance.
Outcome:	The proposed method achieves 7% improvement over SimPO on AlpacaEval 2 and MT-Bench.

HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing (2026.findings-acl)

Copied to clipboard

Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding, Pengyu Zhao, Yanghua Xiao

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering (2024.emnlp-main)

Challenge:	Existing models for LLM role-playing lack high-quality datasets with explicit reasoning traces and reliable reward signals aligned with human preferences.
Approach:	They propose a unified framework for cognitive-level persona simulation that strictly distinguishes characters’ first-person thinking processes from LLMs’ third-person reasoning.
Outcome:	The proposed framework outperforms the Qwen3-32B baseline model and achieves a 30.26% and 14.97% performance on the minimax benchmarks.

Copied to clipboard

Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

Robustness in NLP

Challenge:	Existing datasets for question answering based on retrieval augmented generation (RAG-QA) are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization.
Approach:	They propose a dataset that integrates short extractive answers from multiple documents into a single coherent narrative.
Outcome:	The proposed dataset integrates short extractive answers from multiple documents into a single coherent narrative, covering 26K queries and large corpora across seven different domains.

REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering (2024.emnlp-main)

Copied to clipboard

Yuhao Wang, Ruiyang Ren, Junyi Li, Xin Zhao, Jing Liu, Ji-Rong Wen

DORA: A Dual-Objective Reinforcement Learning Framework for Effective and Efficient Multimodal Agentic Search (2026.acl-long)

Challenge:	Existing methods to extend knowledge scope of large language models (LLMs) lack internal parametric knowledge, resulting in misusing external knowledge.
Approach:	They propose a retrieval-augmented approach that provides LLMs with potentially relevant documents through a module.
Outcome:	The proposed approach outperforms existing methods on four open-domain QA tasks.

Copied to clipboard

Guangming Qin, Yuhao Deng, Yukun Zhao, Zhenyang Li, Junfeng Wang, Dawei Yin, Ye Yuan, Guoren Wang, Yizhou Yan, Chengliang Chai, Lei Cao

MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception (2024.acl-long)

Challenge:	Existing methods to train large language models overlook quality of intermediate search results . existing methods often invoke search calls during reasoning, making inference inefficient .
Approach:	They propose a dual-objective reinforcement learning framework to improve search strategies of MLLMs . DORA outperforms state-of-the-art methods, achieving up to 8.4% higher accuracy .
Outcome:	The proposed model outperforms state-of-the-art methods while reducing search calls by 9.7%.

Copied to clipboard

Yuhao Wang, Yusheng Liao, Heyang Liu, Hongcheng Liu, Yanfeng Wang, Yu Wang

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning (2025.emnlp-main)

Challenge:	Recent advances in multimodal large language models (MLLMs) have demonstrated exceptional capabilities in visual perception and understanding, but they also suffer from hallucinations, which limit their reliability as AI systems.
Approach:	They propose a benchmark to evaluate self-awareness in perception for multimodal large language models (MLLMs) by integrating image information with knowledge quadrants, and propose MM-SAP to evaluate this capability.
Outcome:	The proposed benchmark offers detailed analysis of MLLMs with self-awareness in perception.

Copied to clipboard

Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang

A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Challenge:	Existing work focuses on enabling models to generate natural language chain-of-thought rationales or leverage executable and verifiable code, such as Python.
Approach:	They propose a novel training pipeline that integrates sequential P-CoT and N-Co T generation and a subtask hybrid training strategy to facilitate natural language transferability.
Outcome:	The proposed training pipeline improves both N-CoT and P-Co T performance over the RL baseline.

Copied to clipboard

Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Challenge:	Inductive reasoning is an important task for large language models (LLMs).
Approach:	They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome:	The proposed method improves inductive reasoning in large language models.

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Programming Languages in NLP

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs (2026.acl-long)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Hongcheng Liu, Pingjie Wang, Yuhao Wang, Siqu Ou, Yanfeng Wang, Yu Wang

Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks (2023.findings-emnlp)

Challenge:	Existing evaluations of multimodal large language models focus on passive inference, where seeing is not enough.
Approach:	They propose a benchmark to evaluate active reasoning in multimodal large language models . they propose to acquire missing evidence and iteratively refine decisions under incomplete information .
Outcome:	The proposed model performs better on active reasoning than on passive inference settings.

Copied to clipboard

Kaiser Sun, Peng Qi, Yuhao Zhang, Lan Liu, William Wang, Zhiheng Huang

Question Answering

Challenge:	Pretrained sequence-to-sequence (seq2sequ) models have been widely used to solve extractive tasks, where parts of the input are extracted to form the desired output.
Approach:	They propose a simple fix to tokenization inconsistency that damages extractive nature of generative models by causing performance drop and hallucination.
Outcome:	The proposed model performs better in both in-domain and out-of-domain datasets with a notable average of +1.7 F1 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets.

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025.findings-emnlp)

Copied to clipboard

Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge (2023.findings-acl)

Challenge:	Existing approaches to deep search training lack high-quality training trajectories, prohibitive computational costs and lack of high-fidelity training data.
Approach:	They propose a framework that synthesizes high-quality training data by simulating real user interactions in live web search environments.
Outcome:	The proposed framework synthesizes high-quality training data by simulating user interactions in live web search environments.

Copied to clipboard

Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

SEARCH-R: Structured Entity-Aware Retrieval with Chain-of-Reasoning Navigator for Multi-hop Question Answering (2026.findings-acl)

Challenge:	Open-ended Visual Question Answering (VQA) requires models to reason over visual and natural language inputs using world knowledge.
Approach:	They propose a new VQA pipeline that deploys a generate-then-select strategy guided by world knowledge for the first time.
Outcome:	The proposed pipeline expands the knowledge coverage from in-domain training data by 4.1% on OK-VQA, without additional computation cost.

Copied to clipboard

FU Yuqing, Yimin Deng, Wanyu Wang, Yuhao Wang, Yejing Wang, Hongshi Liu, Yiqi Wang, Xiao Han, Maolin Wang, Guoshuai Zhao, Yi Chang, Xiangyu Zhao

Information Retrieval

Challenge:	Existing approaches to multi-hop question answering lack effective control over reasoning paths, leading to astray results.
Approach:	They propose a framework for multi-hop question answering that trains an end-to-end reasoning path navigator to provide a powerful sub-question decomposer by fine-tuning the Llama3.1-8B model.
Outcome:	The proposed framework trains an end-to-end reasoning path navigator . it is able to provide a powerful sub-question decomposer by fine-tuning the Llama3.1-8B model .

Aria-UI: Visual Grounding for GUI Instructions (2025.findings-acl)

Copied to clipboard

Yuhao Yang, Yue Wang, Dongxu Li, Ziyang Luo, Bei Chen, Chao Huang, Junnan Li

Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming (2026.acl-long)

Challenge:	Using a multimodal model, GUI agents can ground from language instructions to target elements . relying on HTML or AXTree inputs is a challenge for GUI agents .
Approach:	They propose a large multimodal model specifically designed for GUI grounding that adopts a pure vision approach instead of auxiliary inputs.
Outcome:	The proposed model outperforms vision-only and AXTree-reliant models on offline and online agents.

Copied to clipboard

Yuhao Li, Haifeng Sun, Xuesong Zhang, Shu Yao, Haoyu Zheng, Yvchuan Wang, Huazheng Wang, Zirui Zhuang, Qi Qi, Jianxin Liao, Jingyu Wang