Papers by Yuhao Zhang

Soundwave: Less is More for Speech-Text Alignment in LLMs (2025.acl-long)

Challenge:	Existing tabular data synthesis methods fail to account for cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns.
Approach:	They propose a framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator to quantify cross-modal semantic alignment.
Outcome:	The proposed framework outperforms state-of-the-art frameworks in fidelity, diversity, and task utility.

Copied to clipboard

Yuhao Zhang, Zhiheng Liu, Fan Bu, Ruiyu Zhang, Benyou Wang, Haizhou Li

MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs (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

Xiangyu Zhao, Wanghan Xu, Bo Liu, Yuhao Zhou, Fenghua Ling, Ben Fei, Xiaoyu Yue, Lei Bai, Wenlong Zhang, Xiao-Ming Wu

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

Challenge:	Existing datasets often rely on synthetic data or figure-caption pairs, failing to capture the depth and complexity of geoscientific reasoning.
Approach:	They propose a multimodal scientific dataset and benchmark curated from open-access publications.
Outcome:	MSEarth features over 289K figures with captions enriched by contextual discussions and reasoning from original papers.

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.

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

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

Think Wider, Detect Sharper: Reinforced Reference Coverage for Document-Level Self-Contradiction Detection (2025.emnlp-main)

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

Yuhao Chen, Yuanjie Lyu, Shuochen Liu, Chao Zhang, Junhui Lv, Tong Xu

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

Challenge:	Recent approaches to document-level contradiction detection (DSCD) only gain marginal improvement and often introduce inconsistencies across repeated responses.
Approach:	They propose a method that combines supervised fine-tuning and reinforcement learning to enhance document-level contradiction detection (DSCD) they propose to use a task-specific reward function to expand the model’s reasoning scope, boosting both accuracy and consistency.
Outcome:	The proposed method significantly boosts Llama 3.1-8B-Instruct’s accuracy from 38.5% to 51.1%, and consistency from 59.6% to76.2%.

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

Semantic Text Processing

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.

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

Copied to clipboard

Yuhao Zhang, Yongliang Wang

Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation (2021.naacl-main)

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

Yasuhide Miura, Yuhao Zhang, Emily Tsai, Curtis Langlotz, Dan Jurafsky

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

Challenge:	Existing report generation systems suffer from incomplete and inconsistent generation, despite achieving high performance on natural language metrics such as CIDEr and BLEU.
Approach:	They propose two new rewards that encourage the generation of factually complete and consistent radiology reports by using an existing semantic equivalence metric.
Outcome:	The proposed system significantly improves the F1 score of a clinical information extraction performance on two open radiology report 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

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)

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

Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023.findings-emnlp)

Challenge:	Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects.
Approach:	They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt.
Outcome:	The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks.

Copied to clipboard

Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Jia Liu, Tao Gui, Qi Zhang, Xuanjing Huang

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

Challenge:	Existing prompting methods have been used to enhance multistep reasoning capabilities of large language models, but they have overlooked the potential of formulating higher-quality problems.
Approach:	They propose a method that starts from the problem side and refines problems to be more comprehensible and solvable for models.
Outcome:	The proposed method achieves notable and consistent effectiveness on five reasoning benchmarks across different models.

Copied to clipboard

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

Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks (2025.findings-acl)

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

Yuanjie Lyu, Chao Zhang, Yuhao Chen, Yong Chen, Tong Xu

SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning (2026.acl-long)

Challenge:	Recent advances in "Chain of Models" approach increase resource demands as each model must be deployed separately.
Approach:	They propose a prompt-tuning method that enables models to share hidden states . they modify input and attention masks during training to eliminate redundant forward passes .
Outcome:	Empirical results show that FTHSS matches the performance of traditional model chains while improving inference efficiency.

Copied to clipboard

Jinyang Wu, Shuo Yang, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao

Challenge:	Existing methods for training large language models waste computation budget on trivial steps while failing to guarantee sample quality.
Approach:	They propose a framework that selectively branches at critical decision states for resource-efficient exploration.
Outcome:	The proposed framework activates adaptive branching exploration at critical decision states to probe promising trajectories, thereby achieving precise resource allocation that prioritizes sampling quality over blind coverage.

Certified Robustness to Programmable Transformations in LSTMs (2021.emnlp-main)

Copied to clipboard

Yuhao Zhang, Aws Albarghouthi, Loris D’Antoni

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

Challenge:	Existing techniques for certifying robustness of LSTMs and extensions of lsts are prone to adversarial examples.
Approach:	They propose an approach to certify robustness of LSTMs and extensions of lstms . they show that their approach can train models more robust to combinations of string transformations - a key advantage of existing certification approaches .
Outcome:	The proposed approach can show high certification accuracy of the resulting models.

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.

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

Copied to clipboard

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

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals (2024.lrec-main)

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

Rui Zheng, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations (2020.findings-emnlp)

Challenge:	Existing models that extract discrete inputs into fixed-length representations are vulnerable to adversarial attacks that place perturbations on clean inputs to fool DNNs.
Approach:	They propose to inspect the subspaces of sample features through spectral analysis to better understand adversarial attacks.
Outcome:	The proposed strategy enables the model to inherently suppress adversaries, which boosts model robustness and motivates new directions of effective adversarial defense.

Copied to clipboard

Peng Qi, Yuhao Zhang, Christopher D. Manning

Natural Language Interfaces

Challenge:	Existing work on question generation assumes knowledge of what the answer might be . instead, questioner must reason pragmatically about how to acquire new information .
Approach:	They propose a question generation system that generates pragmatically relevant questions in information-asymmetric conversations.
Outcome:	The proposed questioner significantly improves the informativeness and specificity of questions generated over a baseline model as evaluated by metrics as well as humans.

Detecting Adversarial Samples through Sharpness of Loss Landscape (2023.findings-acl)

Copied to clipboard

Rui Zheng, Shihan Dou, Yuhao Zhou, Qin Liu, Tao Gui, Qi Zhang, Zhongyu Wei, Xuanjing Huang, Menghan Zhang

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)

Challenge:	Existing studies have shown that adversarial samples are more vulnerable than normal ones to textual adversarials.
Approach:	They propose a simple and effective sharpness-based detector that can distinguish adversarial samples by maximizing the loss increment within the region where the inference sample is located.
Outcome:	The proposed method outperforms previous detection methods by large margins on three text classification tasks.

Copied to clipboard

Chen Xu, Bojie Hu, Yanyang Li, Yuhao Zhang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

Text Generation

Challenge:	End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it.
Approach:	They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency .
Outcome:	The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks.

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

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.

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

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

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.

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.

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

Semantic Text Processing

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.

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

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

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.

Copied to clipboard

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

ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks (2024.lrec-main)

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

Yuhao Zhou, Wenxiang Chen, Rui Zheng, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

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

Challenge:	Pretrained language models are susceptible to subtle perturbations and require multiple adversarial training during fine-tuning to improve their robustness.
Approach:	They propose a novel adversarial defense method ORTicket that fine-tunes a model for downstream tasks.
Outcome:	The proposed method achieves comparable robustness to other defense methods while maintaining the efficiency of fine-tuning.

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

Learning Architectures from an Extended Search Space for Language Modeling (2020.acl-main)

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

Yinqiao Li, Chi Hu, Yuhao Zhang, Nuo Xu, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li

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

Challenge:	Neural architecture search (NAS) has advanced in recent years but most NAS systems restrict search to learning architectures of a recurrent or convolutional cell.
Approach:	They propose a general approach to learn both intra-cell and inter-cell architectures . they implement their approach in a differentiable architecture search system .
Outcome:	The proposed approach outperforms the baseline on PTB and WikiText data and shows good transferability to other systems.

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

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

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.

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.

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

Copied to clipboard

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

SentiStream: A Co-Training Framework for Adaptive Online Sentiment Analysis in Evolving Data Streams (2023.emnlp-main)

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.

Copied to clipboard

Yuhao Wu, Karthick Sharma, Chun Seah, Shuhao Zhang

Sentiment Analysis

Challenge:	Existing methods for online sentiment analysis rely on pre-existing datasets.
Approach:	They propose a co-training framework specifically designed for efficient sentiment analysis within dynamic data streams.
Outcome:	The proposed framework surpasses existing methods in terms of accuracy and computational efficiency.

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

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

ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning (2026.findings-acl)

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

Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao

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

Challenge:	Existing approaches to optimize large language models with external tools are limited.
Approach:	They propose a dual-path framework for dynamic tool usage in cross-domain complex reasoning . they exploit empirical priors for domain-specific alignment and RL-based multi-step routing .
Outcome:	The proposed framework outperforms closed-source models and existing methods on in-distribution and out-of-distortion tasks.

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

Do Syntax Trees Help Pre-trained Transformers Extract Information? (2021.eacl-main)

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

Devendra Sachan, Yuhao Zhang, Peng Qi, William L. Hamilton

Syntactic Text Processing

Challenge:	Recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models.
Approach:	They propose to incorporate dependency tree information into pre-trained transformers for three tasks . they propose a late fusion approach and a joint fusion technique to infuses syntax structure into attention layers.
Outcome:	The proposed models obtain state-of-the-art results on SRL and relation extraction tasks.

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

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

Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models (2024.emnlp-main)

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.

Copied to clipboard

Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang

Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (D18-1)

Challenge:	Modern language models fail to follow human instructions while being faithful . a trade-off exists between instruction following and faithfulness when training LMs .
Approach:	They propose a method that relies on Reject-sampling by Self-instruct with Continued Fine-tuning to train LMs to follow human instructions while being faithful.
Outcome:	The proposed method outperforms vanilla MTL with high-quality data, but with significantly smaller data.

Copied to clipboard

Yuhao Zhang, Peng Qi, Christopher D. Manning

Information Extraction & Text Mining

Challenge:	Existing dependency-based models neglect crucial information (e.g., negation) by pruning the dependency trees too aggressively.
Approach:	They propose an extension of graph convolutional networks that is tailored for relation extraction by pruning dependency trees too aggressively.
Outcome:	The proposed model outperforms existing sequence and dependency-based models on the large-scale TACRED dataset and has complementary strengths to sequence models.

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

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

Rethinking and Improving Multi-task Learning for End-to-end Speech Translation (2023.emnlp-main)

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

Yuhao Zhang, Chen Xu, Bei Li, Hao Chen, Tong Xiao, Chunliang Zhang, Jingbo Zhu

Stanza: A Python Natural Language Processing Toolkit for Many Human Languages (2020.acl-demos)

Challenge:	auxiliary tasks are highly consistent with end-to-end speech translation (ST) but their effectiveness has not been thoroughly studied.
Approach:	They propose an improved multi-task learning approach for the ST task that bridges the modal gap by mitigating the difference in length and representation.
Outcome:	The proposed approach achieves state-of-the-art on the MuST-C dataset with 20.8% of training time required by the current SOTA method.

Copied to clipboard

Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, Christopher D. Manning

Challenge:	Existing tools that support only a few major languages are under-optimized for accuracy due to a focus on efficiency or use of less powerful models.
Approach:	They introduce a Python natural language processing toolkit that supports 66 languages . they train Stanza on 112 datasets and show it generalizes well on all languages compared to other tools .
Outcome:	The proposed toolkit performs well on 112 datasets and is compatible with the popular Java CoreNLP software.

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

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

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

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

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

Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports (2020.acl-main)

Challenge:	Existing approaches to code generation fail to consider the quality of retrieved examples.
Approach:	They propose a retrieval-augmented generation method that combines existing API examples to improve complexity and readability.
Outcome:	The proposed method achieves up to 22% accuracy improvement over baseline methods.

Copied to clipboard

Yuhao Zhang, Derek Merck, Emily Tsai, Christopher D. Manning, Curtis Langlotz

Text Generation

Challenge:	Existing abstractive summarization models do not guarantee factual correctness of summaries .
Approach:	They propose a framework where models evaluate factual correctness by fact-checking it against its reference using an information extraction module.
Outcome:	The proposed method significantly improves the factual correctness and overall quality of outputs over a competitive neural summarization system, producing radiology summaries that approach the quality of human-authored ones.

Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning (2025.findings-emnlp)

Challenge:	Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging .
Approach:	They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning.
Outcome:	The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets.

Copied to clipboard

Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han