Papers by Hua Huang

Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models (2026.acl-long)

Challenge:	Existing pipelined task-oriented dialogue systems have difficulties adapting to unseen domains . end-to-end systems are plagued by large-scale knowledge bases in practice .
Approach:	They propose a query-driven task-oriented dialogue system that extracts dialogue context information into a natural language query.
Outcome:	The proposed system outperforms strong baselines and establishes a new state-of-the-art performance on three publicly available task-oriented dialogue datasets.

Copied to clipboard

Shaoning Sun, Mingzhu Cai, Huang He, Bingjin Chen, Siqi Bao, Yujiu Yang, Hua Wu, Haifeng Wang

MMAG: Multimodal Learning for Mucus Anomaly Grading in Nasal Endoscopy via Semantic Attribute Prompting (2025.emnlp-main)

Challenge:	RL-friendly models exhibit intra-class compactness and inter-class separation in probability assignments . under identical training, Qwen models achieve substantial gains, while others like Llama yield limited improvements.
Approach:	They propose a method to quantify distributional clarity in probability space . they show distributional clearness is a trainable property underlying RL-Friendliness .
Outcome:	The proposed model families achieve substantial gains under identical training, while others like Llama yield limited improvements.

Copied to clipboard

Xinpan Yuan, Mingzhu Huang, Liujie Hua, Jianuo Ju, Xu Zhang

Planning-Guided Tutoring with Assessment-Driven Memory for Pedagogical LLM Tutors (2026.acl-long)

Challenge:	Accurate grading of rhinitis severity relies heavily on the characterization of key secretions, notably clear nasal discharge (CND) and purulent nasal secretion (PUS).
Approach:	They propose a framework that integrates structured prompts with rank-aware vision-language modeling for joint detection and grading.
Outcome:	The proposed model improves AUC and F1 scores on CND and PUS datasets by 6.31% and 4.79%.

Copied to clipboard

Zechen Li, Qiannan Zhu, Mei Wang, Jia Li, Hua Huang

STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)

Challenge:	Existing approaches to simulate tutor behaviors or preferences fail to sustain high-quality pedagogical conversations that provide explicit stepwise scaffolding and adapt to learners’ evolving cognitive states.
Approach:	They propose a planning-guided tutoring framework with an assessment-driven memory for multi-turn math dialogue tutoring.
Outcome:	Experiments on multi-turn math tutoring benchmarks show that ScaffoldLM significantly improves pedagogical tutoring quality over strong baselines.

Copied to clipboard

Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang

Multilinguality

Challenge:	Simultaneous translation is notoriously dif- ficult due to word-order differences.
Approach:	They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model.
Outcome:	The proposed framework achieves low latency and reasonable qual- ity on 4 directions.

PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation (2022.findings-aacl)

Copied to clipboard

Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhihua Wu, Zhen Guo, Hua Lu, Xinxian Huang, Xin Tian, Xinchao Xu, Yingzhan Lin, Zheng-Yu Niu

QDMR-based Planning-and-Solving Prompting for Complex Reasoning Tasks (2024.lrec-main)

Challenge:	Experimental results show PLATO-XL achieves state-of-the-art results across multiple conversational tasks.
Approach:	They propose to train PLATO-XL models with up to 11 billion parameters, trained on Chinese and English social media conversations.
Outcome:	The proposed model achieves state-of-the-art on multiple conversational tasks, verifying its potential as a foundation model of conversational AI.

Copied to clipboard

Jinfeng Huang, Qiaoqiao She, Wenbin Jiang, Hua Wu, Yang Hao, Tong Xu, Feng Wu

Reasoning

Challenge:	Existing Plan-and-Solve prompting methods are difficult to implement for complex questions.
Approach:	They propose a plan-and-solve prompting method based on Question Decomposition Meaning Representation (QDMR) it allows LLM to generate a QDMR graph to represent problem-solving logic .
Outcome:	The proposed method can represent and execute the problem-solving logic of complex questions more accurately than existing methods.

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs (2026.findings-acl)

Copied to clipboard

Yue Huang, Haomin Zhuang, Jiayi Ye, Han Bao, Yanbo Wang, Hang Hua, Siyuan Wu, Pin-Yu Chen, Xiangliang Zhang

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)

Challenge:	prevailing taxonomies neglect robustness and honesty, yielding safer-on-paper but less useful systems.
Approach:	They propose a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference.
Outcome:	The proposed model maintains safety while reducing over-refusal.

Copied to clipboard

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain? (2026.acl-long)

Challenge:	Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood.
Approach:	They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction .
Outcome:	The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones .

Copied to clipboard

Peiyu Li, Xiaobao Huang, Ting Hua, Nitesh V Chawla

Multimodality

Challenge:	Existing multimodal large language models cannot generate executable procedures . authors propose a new benchmark to assess procedural competence in multimodal models .
Approach:	They propose a new benchmark to assess procedural competence in multimodal large language models . they use a CrochetPARADE DSL representation to enable structural validation and functional evaluation .
Outcome:	The proposed model enables structural validation and functional evaluation via execution.

CDConv: A Benchmark for Contradiction Detection in Chinese Conversations (2022.emnlp-main)

Copied to clipboard

Chujie Zheng, Jinfeng Zhou, Yinhe Zheng, Libiao Peng, Zhen Guo, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Minlie Huang

Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for detecting dialogue contradictions are difficult due to contextualization nature of conversations.
Approach:	They propose a benchmark for Contradiction Detection in Chinese Conversations . they use automatic conversation generation to simulate common user behaviors .
Outcome:	The proposed benchmark simulated the user behaviors that trigger chatbots to make contradictions . the results show that the current state-of-the-art chatbot can be easily goaded into making contradictions.

Copied to clipboard

Mo Zhiqiang, Yang Hua, Jiahui Li, Yuan Liu, Shawn Wong, Jianmin Huang

A Survey on LLM-powered Agents for Recommender Systems (2025.findings-emnlp)

Challenge:	Existing approaches to integrating graph and language models face two key limitations: achieving robust semantic alignment and ensuring interpretability in outputs.
Approach:	They propose a framework to integrate graph and language modalities while enhancing transparency.
Outcome:	Extensive experiments on three benchmark datasets show that the proposed framework surpasses existing methods in efficiency and generates outputs that are significantly more interpretable.

Copied to clipboard

Qiyao Peng, Hongtao Liu, Hua Huang, Jian Yang, Qing Yang, Minglai Shao

Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling (2026.acl-long)

Challenge:	Large Language Models have demonstrated remarkable capabilities in natural language understanding, reasoning, and generation.
Approach:	They present a comprehensive synthesis of large language models and their applications . they dissect a four-module agent architecture and review representative designs .
Outcome:	The proposed models address fundamental challenges in traditional recommender systems . they include limited comprehension of complex user intents, insufficient interaction capabilities .

Copied to clipboard

Qiyuan Chen, Hongsen Huang, Jiahe Chen, Qian Shao, Jintai Chen, Hongxia Xu, Renjie Hua, Ren Chuan, Jian Wu

PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation (2022.acl-long)

Challenge:	Existing multimodal reward models are interpretable but slow, while discriminative ones are opaque "black boxes."
Approach:	They propose a framework that dynamically decomposes evaluation into granular, interpretable dimensions.
Outcome:	The proposed framework outperforms open-source reward models on benchmarks like VL-RewardBench.

Copied to clipboard

Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, Lifu Huang

Towards Boosting the Open-Domain Chatbot with Human Feedback (2023.acl-long)

Challenge:	Existing methods for text generation still suffer from incoherence problems . Neural sequence-to-sequence (seq2sequ) models generate fluent results .
Approach:	They propose a novel generation framework that leverages autoregressive self-attention mechanism to conduct content planning and surface realization dynamically.
Outcome:	The proposed framework outperforms baseline models and generates more coherent texts with richer contents.

Copied to clipboard

Hua Lu, Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang

CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering (2024.emnlp-main)

Challenge:	Existing frameworks for pre-training open-domain dialogue models with social media comments generate coherent replies but have difficulties producing engaging responses.
Approach:	They propose a framework to boost the open-domain chatbot by leveraging human feedback and annotating the model's candidate responses.
Outcome:	The proposed framework boosts the open-domain chatbot by leveraging human demonstrated responses and leveraging the implicit preference in the data collection process.

Copied to clipboard

Yike Wu, Yi Huang, Nan Hu, Yuncheng Hua, Guilin Qi, Jiaoyan Chen, Jeff Pan

Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction (2024.findings-emnlp)

Challenge:	Existing knowledge rewriting methods may include irrelevant information, omit crucial details, or fail to align with the question’s semantics.
Approach:	They propose a new rewriting method CoTKR for generating reasoning traces and corresponding knowledge in an interleaved manner, thereby mitigating the limitations of single-step knowledge rewrite.
Outcome:	The proposed method mitigates the limitations of single-step knowledge rewriting and bridges the preference gap between the knowledge reactor and the question answering (QA) model.

Copied to clipboard

Yuncheng Hua, Yujin Huang, Shuo Huang, Tao Feng, Lizhen Qu, Christopher Bain, Richard Bassed, Reza Haf

Low-Resource NLP

Challenge:	Emotion-cause pair extraction is a task that aims to extract emotions and the events causing such emotions.
Approach:	They propose a deep latent model which captures the underlying latent structures of data and utilizes the easily transferable knowledge of emotions as the bridge to link the distributions of events in different domains.
Outcome:	The proposed model outperforms the strongest baseline by approximately 11.05% on a Chinese benchmark and 2.45% on an English benchmark in terms of weighted-average F1 score.

Are Shortest Rationales the Best Explanations for Human Understanding? (2022.acl-short)

Copied to clipboard

Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao Huang

Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning (2025.findings-acl)

Challenge:	Existing models favor extracting the shortest possible rationales to explain model predictions . however, this assumption has yet to be validated .
Approach:	They propose a model that extracts rationales at any target length from text inputs . they show that rationale lengths too short do not help humans predict labels better .
Outcome:	The proposed model achieves compatible end-task performance and human-annotated rationale agreement compared to baseline models .

Copied to clipboard

Xuetao Ma, Wenbin Jiang, Hua Huang

Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning (2026.acl-long)

Challenge:	In-context learning (ICL) can enhance the complex reasoning capabilities of large language models.
Approach:	They propose a curriculum ICL strategy guided by problem-solving logic to select demonstration examples based on curriculum learning.
Outcome:	The proposed strategy outperforms existing methods on multiple benchmarks.

Copied to clipboard

Jiacheng Hua, Yishu Yin, Yuhang Wu, Tai Wang, Yifei Huang, Miao Liu

Icon2: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation (2025.emnlp-main)

Challenge:	Existing Multimodal Large Language Models struggle with 3D spatial reasoning as they fail to construct structured abstractions of the 3D environment depicted in video inputs.
Approach:	They propose a prompting method that induces MLLMs to generate 3D representations as reasoning traces for more accurate spatial question answering.
Outcome:	Extensive experiments on VSI-Bench and OST-Bech show that TRACE improves over prior prompting strategies across a diverse range of MLLM backbones.

Copied to clipboard

Qiyuan Chen, Hongsen Huang, Qian Shao, Jiahe Chen, Jintai Chen, Hongxia Xu, Renjie Hua, Ren Chuan, Jian Wu

Min Peng, Qianqian Xie, Yanchun Zhang, Hua Wang, Xiuzhen Zhang, Jimin Huang, Gang Tian

Challenge:	Large Language Models (LLMs) require high quality preference datasets to align with human preferences.
Approach:	They propose a framework that leverages inherent regulation of LLMs’ representation space for efficient and tailored preference dataset construction, named Icon2.
Outcome:	The proposed framework improves performance on benchmarks like AlpacaEval 2.0 and Arena-Hard while reducing computational costs by up to 48.1%.

Neural Sparse Topical Coding (P18-1)

Copied to clipboard

Topic Modeling

Challenge:	Topic models with sparsity enhancement are effective at learning discriminative and coherent latent topics of short texts.
Approach:	They propose a novel sparsity-enhanced topic model with back propagation that replaces the inference process with the back propagations, making it easy to explore extensions.
Outcome:	The proposed model outperforms existing methods on Web Snippet and 20Newsgroups datasets.

DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training (2022.findings-acl)

Copied to clipboard

Luyang Huang, Guocheng Niu, Jiachen Liu, Xinyan Xiao, Hua Wu

Multimodality

Challenge:	Existing vision-and-language generation models cannot utilize pair-wise images and text through bi-directional generation due to the limitations of the model structure and pre-training objectives.
Approach:	They propose a framework which unifies vision-and-language generation as sequence generation problems.
Outcome:	The proposed framework achieves better performance than variants trained with uni-directional generation objectives or the variant without the commitment loss on image captioning and text-to-image generation datasets.

Watermarking PLMs on Classification Tasks by Combining Contrastive Learning with Weight Perturbation (2023.findings-emnlp)

Copied to clipboard

Chenxi Gu, Xiaoqing Zheng, Jianhan Xu, Muling Wu, Cenyuan Zhang, Chengsong Huang, Hua Cai, Xuanjing Huang

PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable (2020.acl-main)

Challenge:	Large pre-trained language models (PLMs) are highly valuable intellectual property due to their expensive training costs.
Approach:	They propose to embed backdoors that can be triggered by specific inputs into models by model watermarking.
Outcome:	The proposed method can be used to protect the intellectual property of large pre-trained language models without knowledge about downstream tasks.

Copied to clipboard

Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang

Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment (P19-1)

Challenge:	Existing pre-training models for dialogue generation have been proven effective for a wide range of tasks.
Approach:	They propose a dialogue generation pre-training framework that leverages bi-directional context and uni-directional characteristic of language generation.
Outcome:	The proposed framework is superior to existing models on three publicly available datasets.

Copied to clipboard

Siqi Bao, Huang He, Fan Wang, Rongzhong Lian, Hua Wu

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)

Challenge:	Existing approaches to generate informative responses based on external knowledge are limited to singleround settings.
Approach:	They propose a framework for multi-turn conversations with two dialogue agents . they propose to evaluate dialogues on informativeness and coherence .
Outcome:	The proposed framework outperforms state-of-the-art approaches significantly on the publicly available dataset.

Copied to clipboard

Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Process-Supervised Reinforcement Learning for Code Generation (2025.emnlp-main)

Challenge:	Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness .
Approach:	They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image.
Outcome:	The proposed model outperforms existing models on key downstream tasks.

Copied to clipboard

Yufan Ye, Ting Zhang, Wenbin Jiang, Hua Huang

Programming Languages in NLP

Challenge:	Existing reinforcement learning strategies based on outcome supervision have shown effectiveness in code generation tasks, but their effectiveness in the field of code generation remains limited.
Approach:	They propose a method that uses a teacher model to mutate and refactor statements and a compiler to automatically label them.
Outcome:	The proposed method improves performance in complex code generation tasks.

Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling (2023.acl-long)

Copied to clipboard

Mingzhu Cai, Siqi Bao, Xin Tian, Huang He, Fan Wang, Hua Wu

PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning (2021.findings-acl)

Challenge:	Existing methods to retrieve knowledge-intensive conversations are based on external resources such as Wikipedia databases or search engine results.
Approach:	They propose an unsupervised query enhanced approach for knowledge-intensive conversations . they conduct experiments on three knowledge- intensive conversation datasets .
Outcome:	The proposed approach performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods.

Copied to clipboard

Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhen Guo, Zhibin Liu, Xinchao Xu

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)

Challenge:	PLATO-2 is a high-quality open-domain chatbot that can generate one-to-many mappings and improve response quality.
Approach:	They propose a curriculum learning process to build a high-quality open-domain chatbot . they use a coarse-grained generation model and latent variables to train a generative model .
Outcome:	The proposed model improves on Chinese and English data and can generate diverse responses and select the best response.

Copied to clipboard

Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen