Papers by Wenhao Liu

Controllable Abstractive Dialogue Summarization with Sketch Supervision (2021.findings-acl)

Challenge:	Existing studies on text summarization factual consistency are divided into two categories . entailment-based and question answering-based metrics are the most efficient .
Approach:	They propose an optimized QA-based metric that improves factual consistency by 14% . they compare entailment-based and QA metrics to find the best fit .
Outcome:	The proposed metric outperforms the best performing entailment-based metric on the SummaC factual consistency benchmark.

Copied to clipboard

Chien-Sheng Wu, Linqing Liu, Wenhao Liu, Pontus Stenetorp, Caiming Xiong

Dialogue Systems & Conversational Agents

Challenge:	Using a model to generate summary sketches, we improve abstractive dialogue summarization quality and enable granularity control.
Approach:	They propose a model that generates a preliminary summary sketch and a strategy to control granularity.
Outcome:	The proposed model achieves state-of-the-art on the largest dialogue summarization corpus with as high as 50.79 in ROUGE-L score.

CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction (2025.acl-long)

Copied to clipboard

Jingheng Ye, Zishan Xu, Yinghui Li, Linlin Song, Qingyu Zhou, Hai-Tao Zheng, Ying Shen, Wenhao Jiang, Hong-Gee Kim, Ruitong Liu, Xin Su, Zifei Shan

Syntactic Text Processing

Challenge:	Existing studies have focused on the interpretability of Grammatical Error Correction (GEC) evaluation metrics, but the interpretabilty of these metrics has been neglected.
Approach:	They propose a reference-based metric that describes four aspects of GEC systems: hit-correction, wrong-corrections, under-correcties, and over-corrects.
Outcome:	The proposed metric reveals critical qualities and locates drawbacks of GEC systems.

MixQG: Neural Question Generation with Mixed Answer Types (2022.findings-naacl)

Copied to clipboard

Lidiya Murakhovs’ka, Chien-Sheng Wu, Philippe Laban, Tong Niu, Wenhao Liu, Caiming Xiong

Question Generation

Challenge:	Existing neural question generation approaches focus on short factoid type of answers.
Approach:	They propose a neural question generator that trains a single generative model by combining multiple question types with different answer types.
Outcome:	The proposed model outperforms existing models in both seen and unseen domains and can generate questions with different cognitive levels when conditioned on different answer types.

WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning (2023.acl-long)

Copied to clipboard

Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Sujian Li, Yajuan Lyu

Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting (2023.acl-short)

Challenge:	Existing factual consistency metrics are often uncontrollably generating text that is factually inconsistent with inputs.
Approach:	They propose a weakly supervised framework that is directly trained on actual generated samples from language models with weakly annotated labels.
Outcome:	The proposed framework improves on the TRUE benchmark by 3.3% over existing methods with 435M parameters.

Copied to clipboard

Zahra Fatemi, Chen Xing, Wenhao Liu, Caimming Xiong

PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment (2025.acl-long)

Challenge:	Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training with such data.
Approach:	They propose a method to improve gender fairness of pre-trained models with less forgetting by evaluating them with general NLP tasks in GLUE.
Outcome:	The proposed method improves gender fairness of pre-trained models with less forgetting and performs better on GLUE by a large margin.

Copied to clipboard

Zekun Moore Wang, Shenzhi Wang, King Zhu, Jiaheng Liu, Ke Xu, Jie Fu, Wangchunshu Zhou, Wenhao Huang

Challenge:	Typical approaches to training large language models rely on limited contrasting patterns . contrasting data is limited and models are susceptible to harmful response tendencies .
Approach:	They propose a framework that integrates contrasting patterns across the prompt, model, and pipeline levels.
Outcome:	The proposed framework outperforms existing methods in the comparison of RQ1 and RQ2 . the proposed framework significantly outperformed existing methods, leading to more comprehensive alignment.

DialFact: A Benchmark for Fact-Checking in Dialogue (2022.acl-long)

Copied to clipboard

Prakhar Gupta, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong

Natural Language Interfaces

Challenge:	Existing fact-checking models trained on non-dialogue data fail to perform well on this task.
Approach:	They propose a task of fact-checking in dialogue to improve fact- checking performance . they propose to use an annotated conversational claim and Wikipedia snippets as evidence .
Outcome:	The proposed task improves fact-checking performance in dialogue.

Aligning Large Language Models with Human Preferences through Representation Engineering (2024.acl-long)

Copied to clipboard

Wenhao Liu, Xiaohua Wang, Muling Wu, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

Harmonizing the Past, Present, and Future: A Null-Space Constrained Region-Specific Method for Continual Learning in LLMs (2026.acl-long)

Challenge:	Existing methods for achieving this alignment involve employing reinforcement learning from human feedback (RLHF) Existing approaches involve using RLHF to fine-tune LLMs based on human labels . however, RLRF is susceptible to instability during fine- tuning and presents challenges in implementation.
Approach:	They propose to use reinforcement learning from human feedback to fine-tune large language models with human preferences to achieve precise control of model behavior.
Outcome:	Experiments show that RAHF can be used to capture and manipulate representations to align with a broad spectrum of human preferences or values rather than being confined to a single concept or function.

Copied to clipboard

Jinhui Chen, Shizhu He, Xingchang Yang, Huanxuan Liao, Yequan Wang, Xiangwen Liao, Wenhao Teng, Kang Liu, Jun Zhao

Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts (2023.findings-emnlp)

Challenge:	Existing continual learning paradigms prioritize instant performance through dense updates, leading to catastrophic forgetting and rapid exhaustion of model capacity.
Approach:	They propose a method that preserves previously acquired knowledge and acquires new task-specific skills while preserving sufficient parameter capacity for subsequent adaptation.
Outcome:	The proposed method is based on the brain's functional partitioning and can be used to map tasks between specialized and generalist neurons.

Copied to clipboard

Muling Wu, Wenhao Liu, Jianhan Xu, Changze Lv, Zixuan Ling, Tianlong Li, Longtao Huang, Xiaoqing Zheng, Xuanjing Huang

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)

Challenge:	Prompt tuning has been proven to be successful on various tasks by incorporating a small number of trainable parameters while freezing large pre-trained language models.
Approach:	They propose a token-wise prompt tuning method that uses a bank of finer-grained soft prompt tokens to generate an instance-dependent prompt.
Outcome:	The proposed method performs far better than full parameter fine-tuned models and achieves state-of-the-art by tuning only 0.035% parameters on 14 datasets.

Copied to clipboard

Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression (2025.findings-emnlp)

Challenge:	Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation.
Approach:	They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset.
Outcome:	The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations.

Copied to clipboard

Jiebin Zhang, Dawei Zhu, Yifan Song, Wenhao Wu, Chuqiao Kuang, Xiaoguang Li, Lifeng Shang, Qun Liu, Sujian Li

Challenge:	storing more tokens in the KV cache at lower precision can enhance the long-context performance of large language models.
Approach:	They propose a token-precision trade-off strategy to optimize KV cache compression . they also propose storing more tokens in the KV at lower precision .
Outcome:	The proposed method achieves an optimal point within the Information Bottleneck compared to standalone KV pruning or KV quantization.

Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging (2020.emnlp-main)

Copied to clipboard

Semih Yavuz, Kazuma Hashimoto, Wenhao Liu, Nitish Shirish Keskar, Richard Socher, Caiming Xiong

Low-Resource NLP

Challenge:	Existing studies on DA tagging focus on human-human social conversations, which is less applicable for task-oriented setting.
Approach:	They propose a controllable mechanism that augments text input by leveraging the pre-trained Mask token from BERT model.
Outcome:	The proposed mechanism augments text input by leveraging the pre-trained Mask token from BERT model.

Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.findings-acl)

Copied to clipboard

Wenhao Liu, Siyu An, Junru Lu, Muling Wu, Tianlong Li, Xiaohua Wang, Changze Lv, Xiaoqing Zheng, Di Yin, Xing Sun, Xuanjing Huang

Representation Learning

Challenge:	Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge.
Approach:	They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy.
Outcome:	The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities.

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)

Copied to clipboard

Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Gong Yifan, Sheng Zhang

MAPO: Advancing Multilingual Reasoning through Multilingual-Alignment-as-Preference Optimization (2024.acl-long)

Challenge:	Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting.
Approach:	They propose a representation-aware model merging framework for continual learning without access to historical data.
Outcome:	The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios.

Copied to clipboard

Shuaijie She, Wei Zou, Shujian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, Jiajun Chen

FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness (2022.findings-emnlp)

Challenge:	Existing models exhibit inconsistent reasoning abilities across different languages . existing models lack consistency across languages due to imbalance of training data .
Approach:	They propose a multilingual alignment-as-preference optimization framework to align reasoning processes in other languages with the dominant language.
Outcome:	The proposed framework improves multilingual reasoning across languages on three benchmarks.

Copied to clipboard

Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Ziqiang Cao, Sujian Li, Hua Wu

Robustness in NLP

Challenge:	Existing models of abstractive summarization are able to generate fluent and coherent summaries, but they still suffer from the unfaithful generation problem.
Approach:	They propose to improve the faithfulness of existing models by enhancing their factual robustness by using a novel training strategy, namely FRSUM, which teaches the model to defend against both explicit adversarial samples and implicit factual adversarials.
Outcome:	The proposed training strategy improves faithfulness of various models, such as T5, BART, and T5 .

Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory (2026.findings-acl)

Copied to clipboard

Sirui Liang, Pengfei Cao, Jian Zhao, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

Challenge:	Existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift.
Approach:	They propose a Meta-Cognitive Memory Abstraction method which decouples task execution from memory management by combining a frozen task model with a learned memory copilot.
Outcome:	Experiments on ALFWorld, ScienceWorld, and BabyAI show that the proposed method improves performance, out-of-distribution generalization, and cross-task transfer over several baselines.

MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response (2024.findings-naacl)

Copied to clipboard

Zihao Deng, Yinghao Ma, Yudong Liu, Rongchen Guo, Ge Zhang, Wenhu Chen, Wenhao Huang, Emmanouil Benetos

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation (2025.findings-emnlp)

Challenge:	Large Language Models have shown immense potential in multimodal applications, but convergence between textual and musical domains remains unexplored.
Approach:	They propose a system that aligns music representations with a frozen LLM . they train the system on an extensive music caption dataset and fine-tune it with instructional data .
Outcome:	The proposed system bridges the gap between music audio and textual contexts by combining music captions with a frozen model . it performs well in generating music caption and composing music-related Q&A pairs . the proposed system is available for free download at http://www.musilingo.com/ .

Copied to clipboard

Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Longxiang Liu, Kaiyuan Zhang, Jianpeng Jiao, Ge Zhang, Wenhao Huang, Nenghai Yu

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models (LLMs) have been widely adopted in real-world dialogue applications, but their robustness is criticized all along.
Approach:	They propose to use play-by-play text commentary to build a multi-turn athletic real-world scenario dialogue benchmark to evaluate three critical aspects of multi-turned conversations: ultra multi- turn, interactive multi-twist, and cross-turn tasks.
Outcome:	The proposed benchmarks outperform open-source LLMs on three critical aspects of multi-turn conversations: ultra multi-turned, interactive multi- turn, and cross-turn tasks.

Quiz Design Task: Helping Teachers Create Quizzes with Automated Question Generation (2022.findings-naacl)

Copied to clipboard

Philippe Laban, Chien-Sheng Wu, Lidiya Murakhovs’ka, Wenhao Liu, Caiming Xiong

Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models (2024.findings-emnlp)

Challenge:	Question generation models are often evaluated with standardized NLG metrics that are based on n-gram overlap.
Approach:	They propose to use QGen to help teachers automate the generation of reading comprehension quizzes by comparing n-gram overlap with BLEU to compare system-generated questions with heldout human-written references.
Outcome:	The best model had only 68.4% of its questions accepted by the ten teachers who participated in the study.

Copied to clipboard

Wenhao Shi, Zhiqiang Hu, Yi Bin, Junhua Liu, Yang Yang, See-Kiong Ng, Lidong Bing, Roy Lee

Revisiting the Negative Data of Distantly Supervised Relation Extraction (2021.acl-long)

Challenge:	Existing image instruction fine-tuning datasets do not fully exploit visual information to enhance multimodal reasoning capabilities of Large language models (LLMs).
Approach:	They propose a LLaVA-based model fine-tuned with MathV360K to bridge this gap by collecting 40K high-quality images with question-answer pairs from 24 existing datasets and synthesizing 320K new pairs.
Outcome:	The proposed model improves the multimodal reasoning capabilities of LLaVA-1.5 and demonstrates enhanced generalizability on the MMMU benchmark.

Copied to clipboard

Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang, Wenhao Huang, Yanghua Xiao

Multilingual Contrastive Decoding via Language-Agnostic Layers Skipping (2024.findings-emnlp)

Challenge:	Existing methods for relation extraction with distant supervision generate plenty of training samples but noisy labels and imbalanced training data cause problems.
Approach:	They propose a method that automatically labels a sentence with relational triples from a knowledge base.
Outcome:	The proposed method outperforms existing methods even with false positive samples.

Copied to clipboard

Wenhao Zhu, Sizhe Liu, Shujian Huang, Shuaijie She, Chris Wendler, Jiajun Chen

Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation (2022.emnlp-main)

Challenge:	Decoding by contrasting layers (DoLa) is designed to improve the generation quality of large language models (LLMs) however, this approach does not work well on non-English tasks.
Approach:	They propose a contrastive decoding algorithm that uses amateur logits to contrast with the output of an expert model's early exit logits.
Outcome:	The proposed method outperforms baselines and significantly improves chain-of-thought reasoning accuracy across 11 languages.

Copied to clipboard

Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Sujian Li, Yajuan Lyu

Robustness in NLP

Challenge:	Existing models for text generation are weak enough to handle perturbations in inputs, leading to degeneration in faithfulness and informativeness.
Approach:	They propose a framework for improving faithfulness and informativeness of Seq2Seq models by perturbing word representations and word swapping.
Outcome:	The proposed framework improves faithfulness and informativeness of Seq2Seq models under automatic and human evaluation settings.

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization (2026.acl-long)

Copied to clipboard

Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, Luming Li, Minghao Liu, Yihang Xia, Jiawei Shen, Yuchen Wu, Yixin Cao, Zhaoxiang Zhang, Wenhao Huang, Jiaheng Liu, Ge Zhang

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Existing approaches to formalizing mathematical statements face limitations in accuracy, especially in the context of complex, highlevel problems that involve sophisticated mathematical reasoning.
Approach:	They propose a CriticLean framework that elevates the role of the critic from a passive validator to an active learning component and introduce a benchmark to measure models’ ability to distinguish semantically correct from incorrect formalizations.
Outcome:	The proposed framework outperforms open- and closed-source benchmarks and shows that it significantly outperformed existing models.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

kNN-BOX: A Unified Framework for Nearest Neighbor Generation (2024.eacl-demo)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Wenhao Zhu, Qianfeng Zhao, Yunzhe Lv, Shujian Huang, Siheng Zhao, Sizhe Liu, Jiajun Chen

Token Level Routing Inference System for Edge Devices (2025.acl-demo)

Challenge:	kNN-BOX enables quick development and visualization for novel generation paradigm . Currently, knn-BOx has provided implementation of seven popular kN-MT variants .
Approach:	They propose a framework which decomposes the datastore-augmentation approach into three modules . they apply kNN-BOX to machine translation and three other tasks .
Outcome:	The proposed framework decomposes the datastore-augmentation approach into three modules . it provides implementation of seven popular kNN-MT variants, covering research from performance enhancement to efficiency optimization.

Copied to clipboard

Jianshu She, Wenhao Zheng, Zhengzhong Liu, Hongyi Wang, Eric P. Xing, Huaxiu Yao, Qirong Ho

InstructEval: Instruction-Tuned Text Evaluator from Human Preference (2024.findings-acl)

Challenge:	Large language models (LLMs) have been gaining in performance but deployment in edge devices faces significant hurdles due to their high computational complexity.
Approach:	They propose a collaborative decoding system that allows small models to perform on-device inference while selectively consulting a cloud-based large model for critical token generation.
Outcome:	The proposed system achieves 60% performance gain on CommonsenseQA using a 0.5B model on an M1 MacBook, with under 7% of tokens generation uploaded to the large model in the cloud.

Copied to clipboard

Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Sujian Li

Conformal Predictor for Improving Zero-Shot Text Classification Efficiency (2022.emnlp-main)

Challenge:	InstructEval is a general text evaluator based on open-source Large Language Models (LLMs).
Approach:	They propose to build a general multi-aspect text evaluator based on open-source Large Language Models (LLMs) they use extensive open Human Preference Modeling datasets and a small set of multi-spect annotated data to overcome the shortage of annotation resources for multi-task evaluations.
Outcome:	The proposed model performs comparable or superior to commercial LLMs like ChatGPT or GPT-4 in terms of both overall and multi-aspect evaluation tasks.

Copied to clipboard

Prafulla Kumar Choubey, Yu Bai, Chien-Sheng Wu, Wenhao Liu, Nazneen Rajani

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification.
Approach:	They propose to limit the number of likely labels using a fast base classifier-based conformal predictor calibrated on samples labeled by the 0shot model.
Outcome:	The proposed models reduce the average inference time for NLI- and NSP-based models by 25.6% and 22.2% without dropping performance below the predefined error rate of 1%.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

Knowledge-Guided Cross-Topic Visual Question Generation (2024.lrec-main)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Hongfei Liu, Guohua Wang, Jiayuan Xie, Jiali Chen, Wenhao Fang, Yi Cai

Visual Data in NLP

Challenge:	Existing methods for visual question generation use answers or question types as constraints to generate questions.
Approach:	They propose a knowledge-guided cross-topic visual question generation task to generate unseen topics in cross-section scenarios.
Outcome:	The proposed model outperforms baselines and can generate unseen topic-related questions in cross-topic scenarios.

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

QAConv: Question Answering on Informative Conversations (2022.acl-long)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Chien-Sheng Wu, Andrea Madotto, Wenhao Liu, Pascale Fung, Caiming Xiong

Natural Language Interfaces

Challenge:	Experimental results show that state-of-the-art pretrained QA systems have limited zero-shot performance and tend to predict our questions as unanswerable.
Approach:	They propose a question-answering dataset that uses conversations as a knowledge source.
Outcome:	The proposed dataset provides a training and evaluation testbed to facilitate QA on conversations research.

ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement (2026.acl-long)

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao, Zhitong Wang, Yingli Shen, Wenhao Li, Zhu Liu, Yufeng Han, Jiayi Wu, Cunliang Kong, Maosong Sun

SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning (2025.findings-emnlp)

Challenge:	Existing supervised neural methods for coreference resolution are underexplored . current methods rely on small language models, but their potential is underexploited .
Approach:	They propose a framework that integrates an enhanced supervised model with LLM-based reasoning.
Outcome:	The proposed method surpasses existing state-of-the-art methods in coreference resolution.

Copied to clipboard

Mingsheng Cai, Jiuming Jiang, Wenhao Huang, Che Liu, Rossella Arcucci

A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis (2022.findings-naacl)

Challenge:	Recent ECG Self-Supervised Learning methods mitigate this by learning features without extensive labels but fail to capture fine-grained clinical semantics and require extensive task-specific fine-tuning.
Approach:	They propose a supervised pre-training framework for Multimodal ECG representation learning that combines structured diagnostic labels with large language models to help denoise, standardize cardiac concepts and improve clinical representation learning.
Outcome:	The proposed framework improves on six downstream datasets covering 106 cardiac conditions and achieves a zero-shot AUC performance of 77.20% over state-of-the-art eSSLs.

Copied to clipboard

Ehsan Hosseini-Asl, Wenhao Liu, Caiming Xiong

MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)

Challenge:	Pre-trained language models are often used to achieve state-of-the-art results . eval paper shows that generative language model can handle joint and multi-task settings .
Approach:	They propose to reformulate extraction and prediction tasks into a sequence generation task . they propose a generative language model with unidirectional attention that learns to accomplish the tasks via language generation .
Outcome:	The proposed model outperforms the state-of-the-art in few-shot and full-shot settings.

Copied to clipboard

Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jessie Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)

Challenge:	Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences.
Approach:	They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Outcome:	The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner.

Copied to clipboard

Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li

Multilinguality

Challenge:	Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored.
Approach:	They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation.
Outcome:	The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs.

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models (2023.findings-emnlp)

Copied to clipboard

Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

Exploring Neural Models for Query-Focused Summarization (2022.findings-naacl)

Challenge:	Large language models can perform a wide range of tasks by following natural language instructions without task-specific fine-tuning.
Approach:	They propose a method to automatically improve the quality of LLM instructions . they leverage the generative ability of LMS to generate diverse candidate instructions based on a scoring model trained on 575 existing NLP tasks.
Outcome:	The proposed method surpasses human-written and LLM-generated instructions on 118 out-of-domain tasks.

Copied to clipboard

Jesse Vig, Alexander Fabbri, Wojciech Kryscinski, Chien-Sheng Wu, Wenhao Liu

ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQL (2026.acl-long)

Challenge:	Recent work in Query-focused summarization lacks a comprehensive study of the broad space of applicable modeling methods.
Approach:	They propose to explore two general classes of methods for Query-focused summarization: extractive-abstractive solutions and end-to-end models.
Outcome:	The proposed models achieve state-of-the-art on the QMSum dataset, with a margin of 3.38 ROUGE-1, 3.72 ROUGe2 and 3.28 ROUGEL-L.

Copied to clipboard

Yaxun Dai, Wenxuan Xie, Xialie Zhuang, Tianyu Yang, Ziyi Liu, Haiqin Yang, Yiying Yang, Yuhang Zhao, Pingfu Chao, Wenhao Jiang

Programming Languages in NLP

Challenge:	Current Text-to-SQL reasoning models lack integrated execution feedback during generation.
Approach:	They propose a text-to-SQL framework that interacts with the SQL execution engine during decoding and dynamically adjusts reasoning based on execution feedback.
Outcome:	The proposed framework achieves 89.1% accuracy on Spider and 65.3% on BIRD at the 7B scale.

UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation (2025.findings-emnlp)

Copied to clipboard

Tianlong Li, Wenhao Liu, Muling Wu, Shihan Dou, Zhenghua Wang, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang

Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference (2020.emnlp-main)

Challenge:	Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs).
Approach:	They propose a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM’s personality traits.
Outcome:	The proposed method can modulate the personality expression of large language models by dynamically altering their predicted probability of upcoming words in a pluggable fashion.

Copied to clipboard

Jianguo Zhang, Kazuma Hashimoto, Wenhao Liu, Chien-Sheng Wu, Yao Wan, Philip Yu, Richard Socher, Caiming Xiong

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Existing work on few-shot intent classification without OOS has focused on the few-shot intent classification with out-of-scope intents.
Approach:	They propose to use BERT-style pairwise encoding to train a binary classifier that estimates the best matched training example for a user input.
Outcome:	The proposed approach achieves more stable and accurate in-domain and OOS detection accuracy than RoBERTa-based classifiers and embedding-based nearest neighbor approaches.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

Advancing Parameter Efficiency in Fine-tuning via Representation Editing (2024.acl-long)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang

On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning (2026.acl-long)

Challenge:	Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters.
Approach:	They propose a new approach to fine-tuning neural models that scales and biases the representation produced at each layer.
Outcome:	The proposed approach reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning and by . 32 compared with LoRA.

Copied to clipboard

Changyu Liu, Yiyang Liu, Taowen Wang, Qiao Zhuang, James Chenhao Liang, Wenhao Yang, Renjing Xu, Qifan Wang, Dongfang Liu, Cheng Han

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2024.findings-acl)

Challenge:	Existing vision-language-action models are unsuitable for simulated or physical-world deployments . current methods fail when confronted with inherent real-world dynamic variability.
Approach:	They propose a test-time reinforcement learning framework that enables on-the-fly policy adaptation during inference.
Outcome:	Empirical results show that the proposed framework improves adaptability, stability and task success in dynamic, previously unseen scenarios.

Copied to clipboard

Noah Wang, Z.y. Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhao Huang, Jie Fu, Junran Peng

Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have paved the way for complex tasks such as role-playing.
Approach:	They propose a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models.
Outcome:	The proposed framework improves role-playing abilities with 168,093 samples.

Copied to clipboard

Wenhao Yu, Zhicong Lu, Bo Lv, Fangyin Ma, Kaiwen Wei, Shihao Yang, Nayu Liu

HydraSum: Disentangling Style Features in Text Summarization with Multi-Decoder Models (2022.emnlp-main)

Challenge:	Existing knowledge editing methods suffer from performance degradation in batch knowledge editing.
Approach:	They propose an orthogonal representation editing method which decouples semantic entanglement from edit vectors and enforcing orthogonals on edit vector.
Outcome:	The proposed method outperforms existing methods and achieves superior performance in cross-lingual knowledge editing scenarios.

Copied to clipboard

Tanya Goyal, Nazneen Rajani, Wenhao Liu, Wojciech Kryscinski

Summarization

Challenge:	Abstractive summarization systems implicitly encode “decisions” about summary properties, but these are not enforced.
Approach:	They propose a new summarization architecture that extends existing models to a mixture-of-experts version with multiple decoders.
Outcome:	The proposed architecture outperforms baseline models in obtaining stylistically-diverse summaries by sampling from individual decoders or their mixtures.

DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models (2025.acl-long)

Copied to clipboard

Ruizhe Chen, Wenhao Chai, Zhifei Yang, Xiaotian Zhang, Ziyang Wang, Tony Quek, Joey Tianyi Zhou, Soujanya Poria, Zuozhu Liu

BASS: Boosting Abstractive Summarization with Unified Semantic Graph (2021.acl-long)

Challenge:	Inference-time alignment approaches still face limitations due to policy-specific value functions and latency during the inference phase.
Approach:	They propose an efficient and policy-agnostic preference optimization method that avoids time latency associated with token generation.
Outcome:	The proposed method achieves a favorable trade-off between alignment quality and inference-time latency.

Copied to clipboard

Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Ziqiang Cao, Sujian Li, Hua Wu, Haifeng Wang

MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)

Challenge:	Abstractive summarization for long-document or multi-document remains challenging for Seq2Seq as it does not analyze long-distance relations in text.
Approach:	They propose a framework for Boosting Abstractive Summarization based on a unified Semantic graph which aggregates co-referent phrases distributing across a long range of context and conveys rich relations between phrases.
Outcome:	The proposed framework improves document representation and summary generation process by leveraging the graph structure.

Copied to clipboard

Siwei Wu, King Zhu, Yu Bai, Yiming Liang, Yizhi Li, Haoning Wu, Jiaheng Liu, Ruibo Liu, Xingwei Qu, Xuxin Cheng, Ge Zhang, Wenhao Huang, Chenghua Lin

Trust Within? Seek Beyond? Knowledge Boundary Aware Policy Optimization for Agentic Search (2026.acl-long)

Challenge:	Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images.
Approach:	They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs.
Outcome:	The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks.

Copied to clipboard

Tao Feng, Xinke Jiang, Xinyan Hu, Yonggang Zhang, Zhen Tao, Wentao Zhang, Boyang Liu, Wenhao Jiang, Chao Wu

Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)

Challenge:	Existing approaches to augment large language models with external knowledge suffer from a lack of calibration regarding the model’s knowledge boundary.
Approach:	They propose a reinforcement learning framework that explicitly aligns retrieval decisions with quantified knowledge states.
Outcome:	The proposed framework outperforms strong baselines while exhibiting reduced hallucination rates.

Copied to clipboard

Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang

Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection (2026.acl-long)

Challenge:	Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted.
Approach:	They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space.
Outcome:	The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns.

Copied to clipboard

Yuwei Zhang, Wenhao Yu, Shangbin Feng, Yifan Zhu, Letian Peng, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang

CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization (2023.findings-acl)

Challenge:	Existing knowledge injection benchmarks for large language models lack standardized testing grounds.
Approach:	They propose a knowledge injection benchmark that leverages recently-added and expert-curated facts from Wikipedia’s “Did You Know...” entries.
Outcome:	The proposed framework improves reliability accuracy by 29.1%.

Copied to clipboard

Prafulla Kumar Choubey, Alex Fabbri, Jesse Vig, Chien-Sheng Wu, Wenhao Liu, Nazneen Rajani

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

Challenge:	Existing work suggests that the degree of hallucination depends on factual errors in training data.
Approach:	They propose a method to use training data to reduce hallucination by ensembling parameter variations in training data.
Outcome:	The proposed method improves on XSUM and CNN/DM datasets on human evaluations and factual metrics.

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

Task Compass: Scaling Multi-task Pre-training with Task Prefix (2022.findings-emnlp)

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

Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng

CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs (2026.findings-acl)

Challenge:	Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks.
Approach:	They propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks.
Outcome:	The proposed model can be used as a foundation backbone for a wide range of tasks and as augmentation tool for data augmentation with complementary tasks.

Copied to clipboard

Siyi Li, Jiajun Shi, Shiwen Ni, Ge Zhang, Shuaimin Li, Shijian Wang, Zhoufutu Wen, Yizhi LI, Hamid Alinejad-Rokny, Jiaheng Liu, Min Yang, Wenhao Huang

Green & Sustainable NLP

Challenge:	Existing evaluations emphasize final accuracy or coarse token counts, and lack automated tools to separate essential logic from structural redundancy.
Approach:	They propose a graph-driven framework that quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path needed to reach a correct solution.
Outcome:	Evaluating 21 LRMs, the proposed framework quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path (SEP) needed to reach a correct solution.

LANTERN in the Event Stream: Training-Free Temporal Knowledge Graph Forecasting by Balancing Inertia and Shifts (2026.findings-acl)

Copied to clipboard

Chengyuan Jin, Ao Chang, Daojian Zeng, Wenhao Teng, Xiangwen Liao, Kang Liu, Jun Zhao, Yubo Chen

SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters (2026.acl-long)

Challenge:	Temporal knowledge graph forecasting (TKGF) uses long-window strengthscores and short-windowed novelty scores to predict missing entities in future queries.
Approach:	They propose a training-freeprompting framework that uses two perspectives of history to predict missing entities in future queries.
Outcome:	The proposed framework outperforms the state-of-the-art baselineAnRe framework in ICEWS14, ICEW05-15, and GDELT.

Copied to clipboard

Wenhao Gao, Tianlong Wang, Wei Jia, Linhao Zhang, Aiwei Liu, Miao Fan, Zhou Xiao

LIME: Less Is More for MLLM Evaluation (2025.findings-acl)

Challenge:	Prompt-based in-context learning and parameter fine-tuning are dominant paradigms for incorporating external information into large language models, but they incur high inference costs or require expensive retraining.
Approach:	They propose to convert prompts into temporary adapter weights to bridge this gap by converting prompts to temporary adapters.
Outcome:	The proposed model outperforms baselines on long-context language modeling and downstream NLU and summarization benchmarks while significantly reducing memory footprint and latency.

Copied to clipboard

King Zhu, Qianbo Zang, Shian Jia, Siwei Wu, Feiteng Fang, Yizhi Li, Shuyue Guo, Tianyu Zheng, Jiawei Guo, Bo Li, Haoning Wu, Xingwei Qu, Jian Yang, Ruibo Liu, Xiang Yue, Jiaheng Liu, Chenghua Lin, Hamid Alinejad-Rokny, Min Yang, Shiwen Ni, Wenhao Huang, Ge Zhang

Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs (2026.acl-long)

Challenge:	Existing MLLM benchmarks and unified evaluation frameworks cannot accurately and efficiently reflect the ability of MLMLs.
Approach:	They propose a semi-automated benchmark curated using a pipeline that filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding.
Outcome:	The proposed benchmark reduces the number of samples by 76% and evaluation time by 77% while it can more effectively distinguish different models’ abilities.

Copied to clipboard

Huanxuan Liao, Shizhu He, Yupu Hao, Yequan Wang, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

Green & Sustainable NLP

Challenge:	Continual Learning (CL) for Large Language Models faces a fundamental Stability-Plasticity Dilemma . Rank-Blindness enforces a single rank constraint across diverse tasks, leading to catastrophic forgetting of earlier tasks and underfitting on complex new ones.
Approach:	They propose a rank-spectrum-based rehearsal-free framework that explicitly disentangles knowledge into two orthogonal subspaces.
Outcome:	The proposed framework achieves a superior stability-plasticity balance compared to single-rank baselines.

Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets (2022.emnlp-main)

Copied to clipboard

Philippe Laban, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong

Promoting Data and Model Privacy in Federated Learning through Quantized LoRA (2024.findings-emnlp)

Challenge:	Existing methods for evaluating progress in natural language generation tasks are expensive, difficult to reproduce, and non-reusable.
Approach:	They propose a new automatic evaluation method for NLG called Near-Negative Distinction that repurposes prior human annotations into NND tests.
Outcome:	The proposed method achieves higher correlation with human judgments than standard NLG evaluation metrics.

Copied to clipboard

Zhu JianHao, Changze Lv, Xiaohua Wang, Muling Wu, Wenhao Liu, Tianlong Li, Zixuan Ling, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang