Papers by Liang Chang

Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis (2024.findings-emnlp)

Challenge:	Existing methods for knowledge distillation use a two-stage paradigm: general distillation with a task-agnostic general corpus and task-specific distillation using augmented task- specific corpus.
Approach:	They propose a contextualized corpus that contextualizes task corpus with large-scale general corpus through relevance-based text retrieval to improve student learning.
Outcome:	The proposed model improves on the GLUE benchmark and shows that it is better than generalized corpus and augmented task-specific corpus.

Copied to clipboard

Xinyu Feng, Yuming Lin, Lihua He, You Li, Liang Chang, Ya Zhou

Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability (2026.acl-long)

Challenge:	Existing methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modal may become dominant.
Approach:	They propose a Knowledge-Guided Dynamic Modality Attention Fusion Framework (KuDA) that uses sentiment knowledge to guide the model dynamically selecting the dominant modality and adjusting the contributions of each modality.
Outcome:	The proposed model can be used to highlight the contribution of dominant modality through the correlation evaluation loss.

Copied to clipboard

Xiao Liang, Zhong-Zhi Li, Zhenghao Lin, Eric Hanchen Jiang, Hengyuan Zhang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Yeyun Gong, Weizhu Chen

Reasoning

Challenge:	Large language models have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning, but their strictly sequential nature constrains test-time scalability.
Approach:	They propose an end-to-end reinforcement learning framework to enhance LLMs' DAC-style reasoning capacity by decomposing a problem into subproblems and solving them sequentially.
Outcome:	The proposed model surpasses CoT by 8.6% and 6.3% on competition-level benchmarks and is available at the [github.com/MasterVito/DAC-RL].

Looking Beyond Text: Reducing Language Bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance (2025.emnlp-main)

Copied to clipboard

Haozhe Zhao, Shuzheng Si, Liang Chen, Yichi Zhang, Maosong Sun, Baobao Chang, Minjia Zhang

Visual Data in NLP

Challenge:	Large vision-language models (LVLMs) have been criticized for their language bias.
Approach:	They propose to use a dual-attention mechanism to construct separate attention for visual and text inputs to enhance integration of visual inputs across models.
Outcome:	Experiments show that the proposed model debiases LVLMs from their language bias, enhancing visual comprehension and reducing hallucinations without additional resources.

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data (2026.acl-long)

Copied to clipboard

Shiping Yang, Jie Wu, Wenbiao Ding, Ning Wu, Shining Liang, Ming Gong, Hongzhi Li, Hengyuan Zhang, Angel X. Chang, Dongmei Zhang

Hierarchical Curriculum Learning for AMR Parsing (2022.acl-short)

Challenge:	Existing studies on robustness to explicit noise (e.g., document semantics) but overlook implicit noise (spurious features).
Approach:	They propose a framework to quantify the robustness of RAGs against spurious features by integrating a data synthesis pipeline and a taxonomy.
Outcome:	The proposed framework quantifies the robustness of RALMs against spurious features.

Copied to clipboard

Peiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui

From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities (2025.findings-acl)

Challenge:	Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, but there is a gap between their flat training objective and the hierarchic structure, which limits the model generalization.
Approach:	They propose a Hierarchical Curriculum Learning framework with Structure-level (SC) and Instance-level curricula (IC) that aims to translate sentences to semantic representation with a hierarchical structure.
Outcome:	Experiments on AMR2.0, AMR3.0, structure-complex and out-of-distribution situations confirm the effectiveness of the proposed framework.

Copied to clipboard

Shixin Jiang, Jiafeng Liang, Jiyuan Wang, Xuan Dong, Heng Chang, Weijiang Yu, Jinhua Du, Ming Liu, Bing Qin

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets (P19-1)

Challenge:	MLLMs are able to integrate multiple modalities into a single model to tackle complex tasks in real-world scenarios.
Approach:	They propose a comprehensive survey of Omni-MLLMs to address the challenges and opportunities of multimodal modeling.
Outcome:	The proposed model can integrate multiple modalities into a single model and provide novel perspectives.

Copied to clipboard

Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao

C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs (2026.findings-acl)

Challenge:	Natural Language Sentence Matching (NLSM) is a popular NLP task.
Approach:	They propose to use QuoraQP to train and evaluate NLSM models using a selection bias framework.
Outcome:	The proposed framework can improve generalization ability of trained models and give more trustworthy evaluation results for real-world adoptions.

Copied to clipboard

Xuan Feng, Bo An, Tianlong Gu, Liang Chang, Fengrui Hao, Peipeng Yu, Shuai Zhao

Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models (2026.acl-long)

Challenge:	Existing approaches to solve large language models address stereotypical and structural biases in isolation . however, prior paradigms address these in isolation, often at the expense of exacerbating the other .
Approach:	They propose a framework to tackle latent spurious feature correlations within input that drive erroneous reasoning shortcuts.
Outcome:	The proposed framework mitigates stereotypical and structural biases while preserving robust general reasoning capabilities.

Copied to clipboard

Eric Hanchen Jiang, Levina Li, Frank Wan, Xiao Liang, Sophia Yin, Yuchen Wu, Xinfeng Li, Yizhou Sun, Wei Wang, Kai-Wei Chang, Ying Nian Wu

Green & Sustainable NLP

Challenge:	Existing frameworks rely on static or rule-based topologies that fail to adapt to task requirements.
Approach:	They propose a generative framework that generates highly task-adaptive topologies . they validated the framework on multiple benchmarks and validated it on multiple platforms .
Outcome:	The proposed framework outperforms existing frameworks in task-adaptive communication topologies.

Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning (2023.findings-emnlp)

Copied to clipboard

Chang Liu, Chongyang Tao, Jianxin Liang, Jiazhan Feng, Tao Shen, Quzhe Huang, Dongyan Zhao

ChemAmp: Amplified Chemistry Tools via Composable Agents (2026.findings-acl)

Challenge:	Existing methods to accelerate inference speed are model compression and dynamic computation (e.g., dynamic token pruning).
Approach:	They propose a two-stage knowledge distillation framework that produces a customized small language model for dynamic token pruning.
Outcome:	The proposed framework can make the small language model more customized for dynamic token pruning and achieve better speed-performance trade-off.

Copied to clipboard

Zhucong Li, Powei Chang, Jin Xiao, Zhijian Zhou, Qianyu He, Jiaqing Liang, Fenglei Cao, Xu Yinghui, Yuan Qi

Challenge:	LLM-based agents are powerful tools for automating complex scientific workflows, especially in chemistry, but their single-task performance is limited by tool constraints.
Approach:	They propose a framework that optimizes the collective capabilities of specialized tools by dynamic coordination within individual tasks.
Outcome:	The proposed framework outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration.

On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, Baobao Chang

Multilinguality

Challenge:	Despite its success, multilingual neural machine translation suffers from the off-target issue, where the translation is in the wrong language.
Approach:	They propose a language-aware vocabulary sharing algorithm that can be used to increase the lexical distance between languages by isolating the vocab of different languages in the decoder.
Outcome:	The proposed algorithm reduces off-target rate for 90 translation tasks from 29% to 8%, while improving overall BLEU score by an average of 1.9 points without extra training cost or sacrificing the supervised directions’ performance.

A Survey of Deep Learning for Mathematical Reasoning (2023.acl-long)

Copied to clipboard

Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, Kai-Wei Chang

Reasoning

Challenge:	a survey of deep learning for mathematical reasoning examines the field . a comprehensive reading list is provided to assist readers interested in the field.
Approach:	They present a survey of deep learning for mathematical reasoning over the past decade . they outline directions for future research and highlight potential for further exploration .
Outcome:	The proposed framework is based on the results of a decade-long survey of deep learning for mathematical reasoning.

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System (2026.acl-long)

Copied to clipboard

Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, Charith Peris

Robustness in NLP

Challenge:	Existing red-teaming approaches focus on policy-level weaknesses, but they overlook systemic weaknesses . aRES exploits dual-targeting weaknesses in both the core LLM and the RM simultaneously.
Approach:	a new framework uncovers weaknesses in both the core and the reward models simultaneously . a "Safety Mentor" generates semantically coherent adversarial prompts .
Outcome:	ARES uncovers weaknesses in both the core LLM and the RM simultaneously . it fine-tunes the LM to detect harmful content, then optimizes the core model .

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following (2026.acl-long)

Copied to clipboard

Qingyu Ren, Qianyu He, Powei Chang, Jie Zeng, Zeye Sun, Fei Yu, Jiaqing Liang, Yanghua Xiao

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation (2024.naacl-long)

Challenge:	Existing reinforcement learning approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks.
Approach:	They propose a self-supervised reinforcement learning framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training.
Outcome:	The proposed framework achieves strong improvements across 3 in-domain and 5 out-of-domain datasets while maintaining computational efficiency.

Copied to clipboard

Haozhe Zhao, Zefan Cai, Shuzheng Si, Liang Chen, Yufeng He, Kaikai An, Baobao Chang

Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation (2022.acl-short)

Challenge:	Large-scale multilingual pretrained language models (mPLMs) yield impressive performance on cross-language tasks, yet significant performance disparities exist across different languages within the same mPLm.
Approach:	They propose to leverage the learned knowledge from well-performing languages to guide under-performing ones within the same mPLM.
Outcome:	The proposed model shows that it can guide under-performing languages while minimizing language-level performance disparities across different mPLMs.

Copied to clipboard

Liang Chen, Runxin Xu, Baobao Chang

Machine Translation

Challenge:	Label smoothing and vocabulary sharing are widely used in neural machine translation models, but they can be conflicting and lead to suboptimal performance.
Approach:	They propose a mechanism that masks the soft label probability of source-side words to zero and integrates label smoothing with vocabulary sharing to improve translation quality.
Outcome:	The proposed mechanism improves translation quality and model calibration on bilingual and multilingual datasets, while retaining the original smoothing method.

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs (2022.findings-naacl)

Copied to clipboard

Liang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain (2024.findings-acl)

Challenge:	Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations.
Approach:	They propose to use auxiliary tasks which are semantically or formally related to enhance AMR parsing.
Outcome:	The proposed method achieves state-of-the-art performance on benchmarks especially in topology-related scores.

Copied to clipboard

Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu, Baobao Chang

Guiding AMR Parsing with Reverse Graph Linearization (2023.findings-emnlp)

Challenge:	a new multimodal decision-making benchmark evaluates the integrated capabilities of multimodal large language models.
Approach:	They propose a multimodal decision-making benchmark for evaluating MLLMs . they propose an automatic evaluation protocol to assess 10 prevalent ML models .
Outcome:	The proposed benchmark improves performance of multimodal large language models in three scenarios . the model is required to integrate multiple capabilities to make accurate decisions .

Copied to clipboard

Bofei Gao, Liang Chen, Peiyi Wang, Zhifang Sui, Baobao Chang

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions (2026.acl-long)

Challenge:	Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a sentence.
Approach:	They propose a new framework that allows for reversed linearization of AMR graphs . they propose to combine sequence-to-sequence approaches with a linearized graph .
Outcome:	The proposed framework outperforms the best AMR parser by 0.8 and 0.5 Smatch scores on the AMR 2.0 and AMR 3.0 datasets.

Copied to clipboard

Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong

Green & Sustainable NLP

Challenge:	Existing methods for geometry theorem proving in Euclidean geometry are challenging and require a neural network to perform.
Approach:	They propose a method for adding auxiliary points in geometry that runs on CPUs without relying on neural network-based inference.
Outcome:	The proposed method achieves silver-medal-level human performance on IMO-30 benchmark.

What Makes an Ideal Quote? Recommending “Unexpected yet Rational” Quotations via Novelty (2026.acl-long)

Copied to clipboard

Powei Chang, Jin Xiao, Guanglei Yue, Qianyu He, Yanghua Xiao, Deqing Yang, Jiaqing Liang

Challenge:	Prior systems focus on topical relevance and overlook what makes quotes memorable.
Approach:	They propose a system that maps quotations and contexts into deep-meaning labels for label-enhanced retrieval.
Outcome:	The proposed system can recommend quotations that are contextually novel while semantically coherent.

Quantification of Large Language Model Distillation (2025.acl-long)

Copied to clipboard

Sunbowen Lee, Junting Zhou, Chang Ao, Kaige Li, Xeron Du, Sirui He, Haihong Wu, Tianci Liu, Jiaheng Liu, Hamid Alinejad-Rokny, Min Yang, Yitao Liang, Zhoufutu Wen, Shiwen Ni

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026.acl-long)

Challenge:	Existing studies have revealed the robustness degra-dation caused by data distillation.
Approach:	They propose a framework to evaluate and quantify model distillation . they aim to identify identity cognition contradictions and analyse multi-granularity response similarities across models to measure the extent of homogenization.
Outcome:	The proposed framework addresses two key aspects: (1) Identifying identity cognition contradictions to assess discrepancies in how models perceive and represent identity-related information; (2) Analyzing multi-granularity response similarities across models to measure the extent of homogenization.

Copied to clipboard

Hengyuan Zhang, Shiping Yang, Xiao Liang, Chenming Shang, Yuxuan Jiang, Chaofan Tao, Jing Xiong, Hayden Kwok-Hay So, Ruobing Xie, Angel X. Chang, Ngai Wong

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Challenge:	Existing studies show that stronger models are not always optimal teachers, suggesting a mismatch between the teacher’s output and the student’s learning ability.
Approach:	They propose a method that routes each prompt to its optimal teacher via a query-level router that jointly considers the student models’ learnability and teacher models’ response quality.
Outcome:	The proposed method outperforms baselines on six benchmarks including instruct tuning and math reasoning settings.

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen

Challenge:	a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach:	They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome:	The proposed benchmarks show that the current models perform worse than the human ceiling.

Attend, Select and Eliminate: Accelerating Multi-turn Response Selection with Dual-attention-based Content Elimination (2023.findings-acl)

Copied to clipboard

Jianxin Liang, Chang Liu, Chongyang Tao, Jiazhan Feng, Dongyan Zhao

MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation (2025.naacl-long)

Challenge:	Pre-trained language models can be used to perform multi-turn response selection, but they can be expensive.
Approach:	They propose a framework and a strategy that progressively selects and eliminates unimportant content under context-response dual-attention.
Outcome:	The proposed method can effectively speed-up SOTA models without much performance degradation and shows a better trade-off between speed and performance than previous methods.

Copied to clipboard

Jinsheng Huang, Liang Chen, Taian Guo, Fu Zeng, Yusheng Zhao, Bohan Wu, Ye Yuan, Haozhe Zhao, Zhihui Guo, Yichi Zhang, Jingyang Yuan, Wei Ju, Luchen Liu, Tianyu Liu, Baobao Chang, Ming Zhang

Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision (2026.acl-long)

Challenge:	Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, but many benchmarks suffer from systematic biases.
Approach:	They propose a benchmark to avoid Type-I errors by creating one perception question and one knowledge anchor question through a meticulous annotation process.
Outcome:	The proposed benchmark avoids Type-I errors while maintaining reliability of MCQ evaluations.

Copied to clipboard

Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang, Yuhao Shang, Huiwen Zheng, Hongli Ma, Yan Liang, Yuanchun Li, Yunxin Liu