Papers by Guanhua Chen

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models (2026.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly integrated into our daily lives, raising ethical concerns, especially about perpetuating stereotypes.
Approach:	They propose a method that incorporates a neutral word semantics-based loss function to alleviate the deterioration of the LMS during debiasing.
Outcome:	The proposed method alleviates the deterioration of the Language Modeling Score (LMS) by incorporating a neutral word semantics-based loss function.

Copied to clipboard

Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen

Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders (2021.emnlp-main)

Challenge:	Existing adapter-based transfer methods treat instruction-tuned models as passive targets . direct fine-tuning can disrupt this delicate balance and lead to instability or performance degradation.
Approach:	They propose a framework that incorporates instruction-level guidance into task adaptation.
Outcome:	The proposed framework outperforms direct fine-tuning and representative transfer-based baselines while maintaining robust generalization and favorable test-time scaling behavior.

Copied to clipboard

Guanhua Chen, Shuming Ma, Yun Chen, Li Dong, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei

MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning (2025.naacl-long)

Challenge:	Existing work on improving cross-lingual transferability of NMT model is under-explored.
Approach:	They propose a model that leverages a multilingual pretrained encoder to improve cross-lingual transferability.
Outcome:	The proposed model outperforms mBART and m2m-100 on a zero-shot cross-lingual transfer task.

Copied to clipboard

Hanqing Wang, Yixia Li, Shuo Wang, Guanhua Chen, Yun Chen

Tag-Instruct: Controlled Instruction Complexity Enhancement through Structure-based Augmentation (2025.findings-acl)

Challenge:	Efficient finetuning of large language models (LLMs) aims to adapt the LLMs with reduced computational and memory costs.
Approach:	They propose a simple yet effective method that initializes low-rank matrices with Gaussian distribution and zero values while keeping the original weight matrics frozen.
Outcome:	The proposed approach only updates the minor components of the weight matrix while keeping the principal singular components frozen.

Copied to clipboard

He Zhu, Zhiwen Ruan, Junyou Su, Xingwei He, Yun Chen, Wenjia Zhang, Guanhua Chen

Challenge:	High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity.
Approach:	They propose a framework that compresses instructions into a compact tag space and enhances complexity through RL-guided tag expansion.
Outcome:	The proposed framework outperforms existing methods in the evaluation of instruction complexity augmentation and semantic compression of text into a compact tag space.

mCLIP: Multilingual CLIP via Cross-lingual Transfer (2023.acl-long)

Copied to clipboard

Guanhua Chen, Lu Hou, Yun Chen, Wenliang Dai, Lifeng Shang, Xin Jiang, Qun Liu, Jia Pan, Wenping Wang

Distract Large Language Models for Automatic Jailbreak Attack (2024.emnlp-main)

Challenge:	Existing multilingual vision-language pretrained models are biased towards English due to the lack of sufficient non-English image-text pairs.
Approach:	They propose to train a retrieval-efficient dual-stream multilingual VLP model by aligning CLIP model and a multilingual text encoder through a novel Triangle Cross-modal Knowledge Distillation method.
Outcome:	Empirical results show that mCLIP achieves new state-of-the-art performance for both zero-shot and finetuned multilingual image-text retrieval tasks.

Copied to clipboard

Zeguan Xiao, Yan Yang, Guanhua Chen, Yun Chen

G2: Guided Generation for Enhanced Output Diversity in LLMs (2025.emnlp-main)

Challenge:	Commercial large language models (LLMs) have made great progress in various NLP tasks.
Approach:	They propose a black-box jailbreak framework for automated red teaming of Large language models using an iterative optimization algorithm to conceal malicious content and memory reframing.
Outcome:	The proposed framework outperforms existing jailbreak defense methods and highlights the need to develop more effective and practical defense strategies.

Copied to clipboard

Zhiwen Ruan, Yixia Li, Yefeng Liu, Yun Chen, Weihua Luo, Peng Li, Yang Liu, Guanhua Chen

Challenge:	Existing approaches to enhance output diversity but compromise quality of outputs.
Approach:	They propose a training-free plug-and-play method that enhances output diversity while preserving generation quality.
Outcome:	The proposed method enhances output diversity while maintaining an optimal balance between diversity and quality.

An Iteratively Parallel Generation Method with the Pre-Filling Strategy for Document-level Event Extraction (2023.emnlp-main)

Copied to clipboard

Guanhua Huang, Runxin Xu, Ying Zeng, Jiaze Chen, Zhouwang Yang, Weinan E

Information Extraction & Text Mining

Challenge:	Existing methods to generate event roles require a given generation order . parallel methods suffer from inadequate training and manifest zero accuracies on some event roles.
Approach:	They propose an iteratively parallel generation method with the Pre-Filling strategy to generate event roles in parallel to avoid order selection.
Outcome:	The proposed method outperforms other entity-enhanced models and achieves state-of-the-art performance on two public datasets.

LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Yuxuan Li, Xinwei Guo, Jiashi Gao, Guanhua Chen, Xiangyu Zhao, Jiaxin Zhang, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei

Information Retrieval

Challenge:	Large language models (LLMs) generate outputs that stray from user input or contravene established knowledge.
Approach:	They propose a new phenomenon, Authority Bias, where LLMs favor one knowledge source over the other . they propose atomic information that generates conflicts and a Conflict Detection Enhanced Query framework .
Outcome:	The proposed framework reduces Authority bias in large language models . it detects conflicts, performs credibility assessment on conflicting paragraphs, and detects perturbed text .

From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)

Copied to clipboard

Yixia Li, Hongru Wang, Jiahao Qiu, Zhenfei Yin, Dongdong Zhang, Cheng Qian, Zeping Li, Xiaoteng Ma, Guanhua Chen, Heng Ji

ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs (2025.acl-long)

Challenge:	Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time.
Approach:	They propose a framework that reframes language modeling as next-state prediction under interaction.
Outcome:	The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics .

Copied to clipboard

Yan Yang, Yixia Li, Hongru Wang, Xuetao Wei, James Jianqiao Yu, Yun Chen, Guanhua Chen

SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026.acl-long)

Challenge:	Recent approaches to reduce resource requirements for task-specific large language models have been developed.
Approach:	They propose a delta compression approach that optimizes for importance of a model . they use SVD to dynamically adjust the sparsity ratios of different vectors based on their importance .
Outcome:	The proposed approach achieves state-of-the-art in retaining task-specific knowledge even at high sparsity ratios.

Copied to clipboard

Tianyi Wang, Yixia Li, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen

Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms (2026.findings-acl)

Challenge:	Proximal Policy Optimization (PPO) is central to aligning Large Language Models with verifiable rewards.
Approach:	They propose a scalable algorithm that harmonizes sample efficiency with stability of outcome-based updates.
Outcome:	The proposed algorithm outperforms standard PPO and matches the performance of computation-heavy group-based methods.

Copied to clipboard

Zeguan Xiao, Yun Chen, Jian Yang, Guanhua Chen, Ke Tang

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, including instruction following, mathematical problem solving, and coding generation.
Approach:	They propose a method that truncates both preferred and dispreferred responses to match the shorter one’s length.
Outcome:	The proposed approach improves over standard implementations and achieves 11.8 points in AlpacaEval 2 and overall improvements across downstream tasks.

Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents (2026.acl-long)

Copied to clipboard

Zeping Li, Hongru Wang, Yiwen Zhao, Guanhua Chen, Yixia Li, Keyang Chen, Yixin Cao, Guangnan Ye, Hongfeng Chai, Zhenfei Yin

From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG (2026.findings-acl)

Challenge:	Large language models excel in mathematical reasoning and multi-hop question answering tasks, but in long trajectories, agents often invoke tools excessively or inappropriately, increasing computation cost and derailing the reasoning process.
Approach:	They propose to use entropy reduction as a supervisory signal to reduce tool calls . they propose to design two reward strategies to address the needs of optimizing tool-use behavior.
Outcome:	The proposed reward strategies reduce tool calls by 72.07% and improve performance by 22.27%.

Copied to clipboard

Guanhua Chen, Chuyue Huang, Yutong Yao, Shudong Liu, Xueqing Song, Lidia S. Chao, Derek F. Wong

Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification (2025.emnlp-main)

Challenge:	Existing multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities, making failures unverifiable.
Approach:	They propose a multimodal benchmark that features real-world landmarks with annotations across multiple viewpoints and a framework that treats visual elements as first-class retrieval units through three stages: element-level detection and classification, multi-granularity cross-modal alignment for evidence retrieval, and attribution-constrained generation.
Outcome:	The proposed framework achieves up to 29.2% improvement over six strong baselines for this task.

Copied to clipboard

Maya Kruse, Majid Afshar, Saksham Khatwani, Anoop Mayampurath, Guanhua Chen, Yanjun Gao

Evaluating Memory Capability in Continuous Lifelog Scenario (2026.findings-acl)

Challenge:	Prior work on calibration and uncertainty quantification focuses on individual models, overlooking the potential of model diversity.
Approach:	They propose a method that uses Jensen-Shannon Divergence to identify and aggregate well-calibrated subsets of large language models (LLMs) to improve calibration.
Outcome:	The proposed method improves accuracy on binary prediction tasks compared to single-model and naive ensemble baselines.

Copied to clipboard

Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng

Challenge:	Existing benchmarks focus on online one-on-one chatting or human-AI interactions, neglecting real-world scenarios.
Approach:	They propose a framework to curate a lifelog benchmark that combines two subsets of audio data to address temporal leakage in offline settings.
Outcome:	The proposed framework outperforms existing benchmarks on live chats and AI interactions.

PlanGPT: Enhancing Urban Planning with a Tailored Agent Framework (2025.acl-industry)

Copied to clipboard

He Zhu, Guanhua Chen, Wenjia Zhang

Accurate Word Alignment Induction from Neural Machine Translation (2020.emnlp-main)

Challenge:	Empirical tests demonstrate that PlanGPT framework has achieved advanced performance, providing comprehensive support that significantly enhances professional planning efficiency.
Approach:	They propose a specialized AI agent framework tailored for urban and spatial planning that integrates a customized local database retrieval system and domain-specific knowledge activation capabilities.
Outcome:	Empirical tests show that PlanGPT framework significantly improves planning efficiency . it integrates a customized database retrieval system, domain-specific knowledge activation capabilities, and advanced tool orchestration mechanisms.

Copied to clipboard

Yun Chen, Yang Liu, Guanhua Chen, Xin Jiang, Qun Liu

Can LLMs Hear the Dogwhistle? (2026.findings-acl)

Challenge:	Prior work suggests that Transformer captures poor word alignments through its attention mechanism.
Approach:	They propose two new word alignment induction methods that use attention weights to capture accurate word alignments.
Outcome:	The proposed methods outperform baselines on three publicly available datasets and are significantly better than GIZA++.

Copied to clipboard

Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)

Challenge:	Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach:	They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome:	The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.

Copied to clipboard

Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu

Challenge:	Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves.
Approach:	They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop.
Outcome:	The proposed framework yields more stable training and higher long-horizon task success across open-world environments.

VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation (2026.acl-long)

Copied to clipboard

Yixia Li, Yaqing Shi, Zhiwen Ruan, Dongdong Zhang, Lingjie Jiang, Shaohan Huang, Yun Chen, Guanhua Chen, Furu Wei

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization (2026.findings-acl)

Challenge:	Multimodal large language models have advanced rapidly, yet most remain English-centric . scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of non-English image–text supervision.
Approach:	They propose a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over a shared LLM backbone.
Outcome:	The proposed framework achieves competitive performance with a fully multimodally trained model using less than 2% of the text data.

Copied to clipboard

Yuxiang Ji, Yong Wang, Ziyu Ma, Yiming Hu, Hailang Huang, Xuecai Hu, Guanhua Chen, Liaoni Wu, Xiangxiang Chu

Visual Data in NLP

Challenge:	Existing large vision-language model (LVLM) approaches overlook a common strategy used by humans — using maps.
Approach:	They propose a method to equip a vision-language model with the ability to think with maps and optimize it using agentic reinforcement learning and parallel test-time scaling.
Outcome:	The proposed method outperforms open- and closed-source models on most metrics.

FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios (2026.findings-acl)

Copied to clipboard

Yutao Hou, Yihan Jiang, Yuhan Xie, Jian Yang, Liwen Zhang, Hailiang Huang, Guanhua Chen, Yun Chen

A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU (2024.lrec-main)

Challenge:	Existing large language models (LLMs) are prone to misuse and misinformation, posing serious compliance risks.
Approach:	They propose a bilingual red-teaming benchmark to test an LLM’s refusal of requests that violate financial compliance.
Outcome:	The proposed benchmark is based on real-world financial crime cases and ethical violations and includes 14 subcategories covering financial crimes and ethical breaches.

Copied to clipboard

Guanhua Chen, Yutong Yao, Derek F. Wong, Lidia S. Chao

Toward Automated Robustness Evaluation of Mathematical Reasoning (2026.findings-acl)

Challenge:	Multi-intent natural language understanding (NLU) models lack the rich information between the shared intents, especially in low-data scenarios.
Approach:	They propose a two-stage framework for multi-intent natural language understanding to harness shared intent information by word-level pre-training and prediction-aware contrastive fine-tuning.
Outcome:	The proposed framework surpasses baselines on low-data and full-data scenarios.

Copied to clipboard

Yutao Hou, Zeguan Xiao, Fei Yu, Yihan Jiang, Ma Shuguang, Zhaoqian Dai, Hailiang Huang, Yun Chen, Guanhua Chen

Reasoning

Challenge:	Existing robustness evaluations rely on hand-crafted templates or a limited set of perturbation rules, resulting in model failure.
Approach:	They propose a framework inspired by software stress testing that generates adversarial variants via a multi-round rewrite-verify loop, ensuring semantic consistency while successfully inducing model failure.
Outcome:	The proposed framework generates adversarial variants dynamically for each LLM, minimizing the risk of data contamination.

Multilingual Sentence Transformer as A Multilingual Word Aligner (2022.findings-emnlp)

Copied to clipboard

Weikang Wang, Guanhua Chen, Hanqing Wang, Yue Han, Yun Chen

CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models (2026.acl-long)

Challenge:	Multilingual pretrained language models (mPLMs) have shown their effectiveness in multilingual word alignment induction, but these methods usually start from mBERT or XLM-R.
Approach:	They propose to fine tune multilingual sentence Transformer LaBSE for alignment induction using parallel corpus and a parallel corpora model.
Outcome:	The proposed model outperforms existing models on seven language pairs and achieves new state-of-the-art on zero-shot language pairs.

Copied to clipboard

Shengli Zhou, Xiangchen Wang, Guanhua Chen, Feng Zheng

Reasoning

Challenge:	Existing pruning methods rely on spatial proximity and remove relevant relations, thereby undermining reliable spatial reasoning.
Approach:	They propose a scene graph pruning model that integrates fuzzy semantic relevance with spatial proximity to estimate the importance of relations.
Outcome:	Experiments show that CAPruner outperforms proximity-based pruning with negligible cost savings.

Representation-Guided Parameter-Efficient LLM Unlearning (2026.findings-acl)

Copied to clipboard

Zeguan Xiao, Lang Mo, Yun Chen, Lei Yang, Jiehui Zhao, Lili Yang, Guanhua Chen

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)

Challenge:	Existing methods to unlearning large language models often memorize sensitive or harmful information, but they struggle with the forget-retain trade-off due to the polysemantic nature of LLMs parameters.
Approach:	They propose a representation-guided low-rank unlearning approach that leverages the geometric properties of representation spaces to achieve robust and precise unlearning.
Outcome:	The proposed approach outperforms state-of-the-art models on TOFU and WMDP benchmarks while maintaining higher model utility.

Copied to clipboard

Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding (2024.acl-long)

Challenge:	Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks.
Approach:	They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically.
Outcome:	The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios.

Copied to clipboard

Huang Lei, Jiaming Guo, Guanhua He, Xishan Zhang, Rui Zhang, Shaohui Peng, Shaoli Liu, Tianshi Chen

Challenge:	Generating long-term texts using artificial intelligence has always been a challenge . however, the generated novels exhibit poor logical coherence and appeal in their plots and deficiencies in character and event depiction, ultimately compromising the overall narrative quality.
Approach:	They propose a method for extracting excelsior and expanding from novel data to generate arbitrarily long novels using large language models.
Outcome:	The proposed method produces high-quality long-form novels with a high level of logical coherence and appeal despite the use of large language models.

InstructDiff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning (2026.acl-long)

Copied to clipboard

Junyou Su, He Zhu, Xiao Luo, Liyu Zhang, Hong-Yu Zhou, Yun Chen, Peng Li, Yang Liu, Guanhua Chen

Self-DC: When to Reason and When to Act? Self Divide-and-Conquer for Compositional Unknown Questions (2025.naacl-long)

Challenge:	Existing data selection methods suffer from severe domain specificity . existing methods for general instruction-following fail on reasoning tasks .
Approach:	They propose a framework that operationalizes contrastive entropy as a domain-adaptive selection criterion through warmup calibration, bi-directional NLL filtering, and entropic-based ranking.
Outcome:	Experiments show that InstructDiff outperforms baseline training on reasoning tasks while using only 10% of the data.

Copied to clipboard

Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang, Cunxiang Wang, Huimin Wang, Guanhua Chen, Kam-Fai Wong

PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models (2025.emnlp-industry)

Challenge:	Existing studies focus on leveraging internal knowledge of Large Language Models (LLMs) to answer known questions.
Approach:	They propose a framework that allows LLMs to choose between internal and external knowledge . they use a dataset to analyze compositional questions that are composed of unknown sub-questions .
Outcome:	The proposed framework can achieve comparable or even better performance with much fewer external calls compared with several strong baselines.

Copied to clipboard

He Zhu, Junyou Su, Minxin Chen, Wen Wang, Yijie Deng, Guanhua Chen, Wenjia Zhang

Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation (2022.acl-long)

Challenge:	Existing Vision-Language Models (VLMs) fail to analyze planning maps . specialized visual representations of land use zones, transportation networks, and development policies are needed to interpret complex planning maps.
Approach:	They propose a domain-specific VLM tailored for urban planning maps that employs three innovations: PlanAnno-V framework for high-quality VQA data synthesis, Critical Point Thinking (CPT) and PlanBench-V benchmark for systematic evaluation.
Outcome:	The new model outperforms general-purpose VLMs on planning map interpretation tasks.

Copied to clipboard

Guanhua Chen, Shuming Ma, Yun Chen, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei

SGIC: A Self-Guided Iterative Calibration Framework for RAG (2025.acl-long)

Challenge:	Existing unsupervised neural machine translation systems can degrade when labeled data is limited.
Approach:	They propose a multilingual pretraining and multilingual fine-tuning for facilitating cross-lingual transfer in zero-shot translation using a parallel dataset.
Outcome:	The proposed model outperforms state-of-the-art models on many-to-English translation by over 7.2 and 5.0 BLEU.

Copied to clipboard

Guanhua Chen, Yutong Yao, Lidia S. Chao, Xuebo Liu, Derek F. Wong

Information Retrieval

Challenge:	Existing studies on retrieval-augmented generation (RAG) focus on extracting relevant documents or refinement of specialized instructions.
Approach:	They propose a framework that provides LLMs with specific cues to improve their calibration efficacy . they propose an iterative self-calibration training set that harnesses uncertainty scores .
Outcome:	The proposed framework significantly improves performance on both closed-source and open-source LLMs.

FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only (2025.findings-acl)

Copied to clipboard

He Zhu, Yifan Ding, Yicheng Tao, Zhiwen Ruan, Yixia Li, Wenjia Zhang, Yun Chen, Guanhua Chen

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning (2024.findings-acl)

Challenge:	Recent studies explore approaches to synthesize instruction data with open-sourced LLMs but require high-quality human-crafted seed data.
Approach:	They propose an end-to-end framework to synthesize high-quality instruction data with open-sourced LLMs and sampled unlabeled documents, eliminating the need for seed data.
Outcome:	The proposed framework synthesizes high-quality instruction data with open-sourced LLMs and sampled unlabeled documents, eliminating the need for seed data.

Copied to clipboard

Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen

Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA (2026.findings-acl)

Challenge:	In-context instruction tuning is a method that fine tunes with supervised instruction data to enhance the instruction following ability of large language models.
Approach:	They propose an in-context instruction tuning method that incorporates positive and negative examples into the prompt for better performance.
Outcome:	The proposed method outperforms baseline instruction tuning methods on in-domain and out-domain tasks up to 9.16 and 3.14 average ROUGE-L scores.

Copied to clipboard

Guanhua Chen, Yutong Yao, Shenghe Sun, Ci-jun Gao, Shudong Liu, Lidia S. Chao, Feng Wan, Derek F. Wong

Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem (2026.acl-long)

Challenge:	Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their capability in visual procedure question answering (VP-QA) remains largely unexplored.
Approach:	They propose a multimodal benchmark specifically designed for visual procedural reasoning that synergizes cross-modal procedure retrieval, context-aware step decomposition, and the next step prediction.
Outcome:	The proposed framework significantly outperforms baselines on visual procedure question answering (VP-QA) Experiments on six VLMs show that it performs better than baselines.

Copied to clipboard

Zeguan Xiao, Siqing Li, Yong Wang, Xuetao Wei, Jian Yang, Yun Chen, Guanhua Chen

Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL (2026.findings-acl)

Challenge:	Large language models (LLMs) are inherently dual-use and can be leveraged for both beneficial and harmful purposes.
Approach:	They propose a retention-prioritized gradient synthesis framework that decouples task-specific gradient extraction from conflict-aware combination.
Outcome:	The proposed method achieves tighter alignment on WMDP Bio and RWKU benchmarks.

Copied to clipboard

Hanqing Wang, Yongdong Chi, Jian Yang, Lei Yang, Jiehui Zhao, Yun Chen, Guanhua Chen

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) have been successful in Text-to-SQL tasks, but their deployment in real-world environments is hindered by latent reliability issues.
Approach:	They propose a framework to autonomously uncover latent failure patterns in LLM-based Text-to-SQL generation.
Outcome:	The proposed framework uncovers a substantial number of failure cases on state-of-the-art open-source LLMs.

StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation (2023.findings-emnlp)

Copied to clipboard

Hanqing Wang, Yajing Luo, Boya Xiong, Guanhua Chen, Yun Chen

LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy (2025.findings-naacl)

Challenge:	Existing studies on unsupervised headline generation focus on a standard dataset and mono-style corpora.
Approach:	They propose an unsupervised approach for stylistic headline generation using a pretrained BART model decorated with adapters responsible for different styles.
Outcome:	The proposed method separates the task of style learning and headline generation, allowing for the generation of diverse headlines with diverse styles.

Copied to clipboard

Zhiwen Ruan, Yixia Li, He Zhu, Longyue Wang, Weihua Luo, Kaifu Zhang, Yun Chen, Guanhua Chen

XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation (2022.emnlp-main)

Challenge:	Large language models (LLMs) are pretrained on multilingual corpora but exhibit suboptimal performance on low-resource languages.
Approach:	They propose a framework that integrates representations from all encoder layers and an adaptive fusion-enhanced attention mechanism to enable layer-wise interaction between the LLM and the multilingual encoder.
Outcome:	Experiments on multilingual reasoning tasks show that the proposed framework outperforms baselines.

Copied to clipboard

Yong Wang, Shilin He, Guanhua Chen, Yun Chen, Daxin Jiang