Papers by Meng Fang

Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting (2023.findings-emnlp)

Challenge:	Named entity recognition (NER) is an important step in most natural language processing (NLP) applications.
Approach:	They propose a dual-adversarial neural transfer method for addressing low-resource Named Entity Recognition (NER) they propose 'Generalized Resource-Adversarial Discriminator' and 'accidental training'
Outcome:	The proposed method improves on low-resource Named Entity Recognition (NER) with two variants, i.e., DATNet-F and DATNET-P, and adversarial training is adopted to boost model generalization.

Copied to clipboard

Fanghua Ye, Meng Fang, Shenghui Li, Emine Yilmaz

Generalization in Text-based Games via Hierarchical Reinforcement Learning (2021.findings-emnlp)

Challenge:	Existing approaches to rewrite context-dependent queries lack sufficient information for optimal retrieval performance.
Approach:	They propose to use large language models (LLMs) as query rewriters to generate informative queries through well-designed instructions.
Outcome:	The proposed approach improves performance on the QReCC dataset compared to human rewrites .

Copied to clipboard

Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Chengqi Zhang

Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding (2020.emnlp-main)

Challenge:	Reinforcement Learning (RL) based agents are promising for text-based games, but their generalization remains a challenge.
Approach:	They propose a hierarchical framework for reinforcement learning based on knowledge graphs . they propose to decompose the game into subtasks and execute a sub-policy in the low level to conduct goal-conditioned reinforcement learning.
Outcome:	The proposed framework enjoys favorable generalizability on a set of difficulty levels and is able to handle complex training tasks.

Copied to clipboard

Jiaxin Huang, Yu Meng, Fang Guo, Heng Ji, Jiawei Han

DOSE: Data Selection for Multi-Modal LLMs via Off-the-Shelf Models (2026.findings-acl)

Challenge:	Existing methods for aspect-based sentiment analysis of review text use only a few keywords describing each aspect/sentiment without using any labeled examples.
Approach:	They propose a weakly-supervised approach for aspect-based sentiment analysis which uses only a few keywords describing each aspect/sentiment without using any labeled examples.
Outcome:	The proposed method generates quality joint topics and outperforms baselines significantly on benchmark datasets.

Copied to clipboard

Biao Wu, Yiwu Zhong, Meng Fang, Ling Chen

Spiral of Silence in Large Language Model Agents (2025.findings-emnlp)

Challenge:	Existing data filtering methods are expensive because they are trained on the same data they are meant to screen.
Approach:	They propose to use off-the-shelf pretrained models that have never seen the target data to select training samples for larger and stronger multimodal models without task-specific training.
Outcome:	The proposed method can achieve comparable or even better results than those trained on the full dataset in standard VQA and math benchmarks.

Copied to clipboard

Mingze Zhong, Meng Fang, Zijing Shi, Yuxuan Huang, Shunfeng Zheng, Yali Du, Ling Chen, Jun Wang

SpatialWebAgent: Leveraging Large Language Models for Automated Spatial Information Extraction and Map Grounding (2025.acl-demo)

Challenge:	Existing theories of Spiral of Silence do not apply to large language models .
Approach:	They propose an evaluation framework for examining SoS in large language models . they consider four controlled conditions that vary the availability of "History" and "Persona" signals .
Outcome:	The proposed framework examines the SoS-like dynamics in large language models . it shows that history and persona together produce strong majority dominance .

Copied to clipboard

Shunfeng Zheng, Meng Fang, Ling Chen

TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation (2024.findings-emnlp)

Challenge:	Understanding and extracting spatial information from text is vital for a wide range of applications, says nielsen . inherent complexity of geographic expressions in natural language presents significant hurdles for traditional extraction methods.
Approach:	They propose a system that leverages large language models to extract spatial information from natural language.
Outcome:	SpatialWebAgent is designed to extract, standardize, and ground spatial information from natural language text directly onto maps.

Copied to clipboard

Jinyuan Fang, Zaiqiao Meng, Craig MacDonald

Natural Language Interfaces

Challenge:	Existing retrievers are not perfect and often include irrelevant documents in the retrieved set.
Approach:	They propose to construct knowledge-grounded reasoning chains from retrieved documents to integrate supporting evidence into RAG models.
Outcome:	The proposed model achieves an average performance improvement of 14.03% on three multi-hop QA datasets.

Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset (2026.findings-acl)

Copied to clipboard

Baode Wang, Biao Wu, Weizhen Li, Meng Fang, Zuming Huang, Jun Huang, Yanjie Liang, Haozhe Wang, Ling Chen, Wei Chu, Yuan Qi

Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving (2025.findings-emnlp)

Challenge:	Existing supervised fine-tuning methods struggle to generalize across document types, leading to poor performance.
Approach:	They propose layoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation.
Outcome:	The proposed model outperforms specialized document parsing systems and general-purpose vision-language models on a broad range of document types, languages, and structural complexities.

Copied to clipboard

Shunfeng Zheng, Yudi Zhang, Meng Fang, Zihan Zhang, Zhitan Wu, Mykola Pechenizkiy, Ling Chen

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack (2022.emnlp-main)

Challenge:	a new study examines the potential of retrieval-augmented generation (RAG) with foundation models to enhance expert-level reasoning.
Approach:	They introduce PhoPile, a high-quality multimodal dataset specifically designed for Olympiad-level physics.
Outcome:	The proposed model can be used to solve Olympiad-level physics problems.

Copied to clipboard

Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, Dacheng Tao

Robustness in NLP

Challenge:	Existing adversarial models rely on keyword matching and ignore relevant contextual relations for answer prediction.
Approach:	They propose to use keyword matching to attack model with two biases that rely on a perturbed answer sentence and a distracting answer sentence to misguide model.
Outcome:	The proposed method produces fluent and grammatical adversarial contexts while maintaining gold answers.

Revisiting Catastrophic Forgetting in Large Language Model Tuning (2024.findings-emnlp)

Copied to clipboard

Hongyu Li, Liang Ding, Meng Fang, Dacheng Tao

How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances (2023.emnlp-main)

Challenge:	Catastrophic Forgetting (CF) compromises the effectiveness of large language models during fine-tuning, yet the underlying causes of CF remain largely unexplored.
Approach:	They propose a method to flatten the model loss landscape to mitigate CF by flattening the loss landscape.
Outcome:	The proposed method complements existing anti-forgetting strategies, further enhancing the resistance of LLMs to CF.

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad, Jun Wang

Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation (2026.findings-acl)

Challenge:	Large language models (LLMs) are impressive in solving tasks, but they can quickly be outdated after deployment.
Approach:	They provide a review of recent advances in aligning deployed large language models with the ever-changing world knowledge.
Outcome:	The proposed models can be used to perform various tasks directly through in-context learning or for further fine-tuning for domain-specific uses.

Copied to clipboard

Wenpeng Xing, Moran Fang, Guangtai Wang, Changting Lin, Meng Han

Representation Learning

Challenge:	Existing strategies to circumvent safety constraints face significant trade-offs between effectiveness and efficiency.
Approach:	They propose a framework that allows to infer model refusal behaviors without expensive parameter updates or training.
Outcome:	The proposed framework outperforms baselines in multiple safety-aligned open-source LLMs.

CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models (2023.acl-long)

Copied to clipboard

Jiaxu Zhao, Meng Fang, Zijing Shi, Yitong Li, Ling Chen, Mykola Pechenizkiy

ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection (2021.findings-emnlp)

Challenge:	Existing studies on social biases in language models have focused on only English.
Approach:	They propose to use a Chinese dataset for bias evaluation and mitigation of Chinese conversational language models.
Outcome:	The proposed dataset includes under-explored bias categories, such as ageism and appearance biases, which received less attention in previous studies.

Copied to clipboard

Iftitahu Nimah, Meng Fang, Vlado Menkovski, Mykola Pechenizkiy

RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering (2024.findings-acl)

Challenge:	Existing methods to detect out-of-domain (OOD) inputs are limited and lack data.
Approach:	They propose a new architecture that extends Prototypical Networks to process in-domain and OOD sentences via Mutual Information Maximization objective.
Outcome:	The proposed method significantly improves performance up to 20% for OOD detection in low resource settings of text classification.

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen

PresentAgent: Multimodal Agent for Presentation Video Generation (2025.emnlp-demos)

Challenge:	Existing methods for assessing retrieval of relevant information are understudied . previous studies have neglected to evaluate ARAG methods .
Approach:	They propose a benchmark to evaluate existing ARAG methods that use threshold tuning to adjust retrieval for queries instead of indiscriminate retrieval.
Outcome:	The proposed method can be used to evaluate existing ARAG methods without calibration or training.

Copied to clipboard

Jingwei Shi, Zeyu Zhang, Biao Wu, Yanjie Liang, Meng Fang, Ling Chen, Yang Zhao

DAGN: Discourse-Aware Graph Network for Logical Reasoning (2021.naacl-main)

Challenge:	Existing methods for generating static slides or text summaries are limited to producing narrated presentations.
Approach:	They propose a multimodal agent that transforms long-form documents into narrated presentations.
Outcome:	The present agent produces fully synchronized visual and spoken content that closely mimics human-style presentations.

Copied to clipboard

Yinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang

Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding (2025.acl-short)

Challenge:	Recent QA with logical reasoning questions requires passage-level relations among the sentences.
Approach:	They propose a discourse-aware graph network that aggregates passage-level clues for QA by using discourse-based information.
Outcome:	The proposed model achieves competitive results on two logical reasoning QA datasets.

Copied to clipboard

Keqin Peng, Liang Ding, Yuanxin Ouyang, Meng Fang, Yancheng Yuan, Dacheng Tao

Pretrained Language Models for Dialogue Generation with Multiple Input Sources (2020.findings-emnlp)

Challenge:	Prior research has found that large language models overlook input-label mapping information in ICL, relying more on their pre-trained knowledge.
Approach:	They propose a novel method that contrasts input-label mappings between positive and negative in-context examples to improve model performance.
Outcome:	The proposed method improves performance on 7 natural language understanding tasks without additional training.

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Dacheng Tao

REANO: Optimising Retrieval-Augmented Reader Models through Knowledge Graph Generation (2024.acl-long)

Challenge:	Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks.
Approach:	They propose to fuse attention information from multiple input sources to achieve better relevance with dialogue history than simple fusion baselines.
Outcome:	The proposed models deliver higher relevance with dialogue history than baselines.

Copied to clipboard

Jinyuan Fang, Zaiqiao Meng, Craig MacDonald

NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist (2023.acl-long)

Challenge:	Existing knowledge graphs suffer from incompleteness and lack information critical for answering given questions.
Approach:	They propose to enhance the open domain question answering model with a knowledge graph generation module that generates KGs from the passages and an answer predictor.
Outcome:	The proposed model improves the exact match score by 2.7% on the EntityQuestion dataset, with an average improvement of 1.8% across all the datasets.

Copied to clipboard

Iftitahu Nimah, Meng Fang, Vlado Menkovski, Mykola Pechenizkiy

Text Generation

Challenge:	a systematic review of automatic evaluation metrics for Natural Language Generation (NLG) shows that task-agnostic metrics have a weak correlation with human .
Approach:	They propose a framework to assess the effectiveness of automatic metrics in three NLG tasks . they propose task-agnostic and human-aligned metrics to be used for evaluation .
Outcome:	The proposed framework provides access to the evaluation tools for three NLG tasks.

Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games (2022.acl-short)

Copied to clipboard

Dongwon Ryu, Ehsan Shareghi, Meng Fang, Yunqiu Xu, Shirui Pan, Reza Haf

BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering (N19-1)

Challenge:	Existing RL agents are far away from solving text-based games due to their combinatorially large action spaces that hinders efficient exploration.
Approach:	They propose an exploration technique that injects external commonsense knowledge, via a pretrained language model, into the agent during training when the agent is the most uncertain about its next action.
Outcome:	The proposed method exhibits improvement on the collected game scores during the training in four out of nine games from Jericho.

Copied to clipboard

Yu Cao, Meng Fang, Dacheng Tao

GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input (2021.naacl-main)

Challenge:	Existing datasets for question answering and machine comprehension (MC) are limited to a single paragraph, or even part of it.
Approach:	They propose a bi-directional Attention Entity Graph Convolutional Network (BAG) that leverages relationships between nodes in an entity graph and attention information between a query and the entity graph to generate a prediction.
Outcome:	Experimental results show that the proposed network achieves state-of-the-art accuracy on the QAngaroo WIKIHOP dataset.

Copied to clipboard

Tao Meng, Anjie Fang, Oleg Rokhlenko, Shervin Malmasi

Representation Learning

Challenge:	Named Entity Recognition (NER) is difficult in real-world settings due to short texts, emerging entities, and complex entities.
Approach:	They propose a flexible Gazetteer Representation encoder and a Mixture-of-Experts gating network for gazetteer knowledge integration.
Outcome:	The proposed approach shows large gains (up to +49% F1) in recognizing difficult entities compared to baselines.

CHAmbi: A New Benchmark on Chinese Ambiguity Challenges for Large Language Models (2024.findings-emnlp)

Copied to clipboard

Qin Zhang, Sihan Cai, Jiaxu Zhao, Mykola Pechenizkiy, Meng Fang

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners (2024.naacl-long)

Challenge:	Ambiguity is an inherent feature of language, whose management is crucial for effective communication and collaboration.
Approach:	They propose a dataset to evaluate LLMs' ability to handle ambiguity in Chinese by using a specialized Chinese multi-label disambiguation dataset formatted in Natural Language Inference.
Outcome:	The CHAmbi dataset comprises 4,991 pairs of premises and hypotheses, including 824 examples featuring a wide range of ambiguities.

Copied to clipboard

Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Fang Guo, Qinglin Qi, Jie Zhou, Yue Zhang

Perceiving the World: Question-guided Reinforcement Learning for Text-based Games (2022.acl-long)

Challenge:	Existing methods for active learning rely on model uncertainty or disagreement to pick unlabeled data, leading to over-confidence in superficial patterns and lack of exploration.
Approach:	They propose to use a bi-directional encoder and a uni-directional decoder to generate and score an explanation for low-resource text classification.
Outcome:	The proposed model improves on 9 strong baselines on six datasets and can generate explanations for its predictions.

Copied to clipboard

Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Joey Zhou, Chengqi Zhang

Green & Sustainable NLP

Challenge:	Text-based games provide an interactive way to study natural language processing.
Approach:	They propose a two-phase training framework to decouple language learning from reinforcement learning and improve the sample efficiency.
Outcome:	The proposed method significantly improves performance and sample efficiency against compound error and limited pre-training data.

Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics (2022.naacl-main)

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen, Mohammad Reza Namazi Rad

Information Extraction & Text Mining

Challenge:	Recent work incorporates pre-trained word embeddings into Neural Topic Models (NTMs), generating highly coherent topics.
Approach:	They conduct thorough experiments to investigate whether embeddings directly with an appropriate word selection method can generate more coherent and diverse topics than NTMs.
Outcome:	The proposed model generates more coherent and diverse topics than traditional NTMs, achieving higher efficiency and simplicity.

MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents (2025.findings-naacl)

Copied to clipboard

Wanqi Yang, Yanda Li, Meng Fang, Ling Chen

VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery (2026.findings-eacl)

Challenge:	Existing time-aware datasets that focus on persona-grounded conversations focus on temporal dynamics, which narrows their scope and diminishes their complexity.
Approach:	They propose a multimodal, time-aware persona dialogue dataset that integrates linguistic, visual, and temporal elements within dialogue and persona memory.
Outcome:	The proposed framework integrates linguistic, visual, and temporal elements within dialogue and persona memory to assess a model’s ability to understand implicit temporal cues and dynamic interactions.

Copied to clipboard

Jinchao Ge, Tengfei Cheng, Biao Wu, Zeyu Zhang, Shiya Huang, Judith Bishop, Gillian Shepherd, Meng Fang, Ling Chen, Yang Zhao

MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)

Challenge:	MLLMs that use domain-specific data are limited in understanding cultural heritage artifacts such as ancient Greek pottery . supervised fine-tuning improves adaptation to domain knowledge, but it struggles with deeper reasoning tasks.
Approach:	They propose a visual question-answer tool that augments SFT with reinforcement learning using verifiable rewards.
Outcome:	The proposed model outperforms baseline models on reasoning-intensive questions on ancient Greek pottery.

Copied to clipboard

Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie

FactSearch: An Interactive Agentic Fact Search System for Verifying Large Language Model Outputs (2026.acl-demo)

Challenge:	telemedicine is a medical practice that provides patient care remotely using video conferencing tools.
Approach:	They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance .
Outcome:	The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues.

Copied to clipboard

Meng Fang, Harry Mackenzie

Benchmarking Web Agent Safety under E-commerce Deceptive Interfaces (2026.acl-long)

Challenge:	Existing tool-augmented verification systems depend on opaque search APIs, introducing uncontrolled variability into factuality evaluation.
Approach:	They propose a reproducibility-oriented agentic fact search system for claim-level factuality verification built on a locally aggregated open-source search infrastructure.
Outcome:	The proposed system decomposes model outputs into atomic factual claims, generates targeted search queries, retrieves supporting evidence via a self-hosted meta-search engine, and performs modular verification within a fully configurable pipeline.

Copied to clipboard

Zijing Shi, Meng Fang, Ling Chen

Challenge:	Existing web agents are highly susceptible to multiple classes of deceptive interfaces, but they are not designed to mitigate these failures.
Approach:	They propose a lightweight plugin framework that allows controlled injection of deceptive interface patterns into existing web environments.
Outcome:	The proposed framework enables controlled injection of deceptive interface patterns into web environments.

MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages (2026.findings-acl)

Copied to clipboard

Wenhan Han, Yifan Zhang, Zhixun Chen, null Binbinliu, Mykola Pechenizkiy, Meng Fang, Yin Zheng

ATLAS: Agent Tuning via Learning Critical Steps (2025.findings-acl)

Challenge:	Existing evaluation datasets lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage.
Approach:	They propose to use multilingual consistency as a complementary metric to assess performance bottlenecks and guide model improvement.
Outcome:	The proposed model lacks cross-lingual alignment and language coverage gaps between state-of-the-art models.

Copied to clipboard

Zhixun Chen, Ming Li, Yuxuan Huang, Yali Du, Meng Fang, Tianyi Zhou

SPARKLE: A Structured and Plug-and-play Agentic Retrieval Policy for Adaptive RAG Models (2026.acl-long)

Challenge:	Existing agent tuning approaches employ supervised finetuning on entire expert trajectories, but behavior-cloning of full traitories introduces expert bias and weakens generalization to states not covered by the expert data.
Approach:	They propose a method that finetunes LLMs on critical steps in expert trajectories and identifies and finetuns them on these steps with reduced costs.
Outcome:	The proposed method outperforms existing methods and open-source LLM agents on only 30% critical steps in extensive experiments.

Copied to clipboard

Jinyuan Fang, Zaiqiao Meng, Craig Macdonald

KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Existing methods for integrating external knowledge rely on frozen large language models without explicit supervision or require costly LLM finetuning.
Approach:	They propose a structured and plug-and-play agentic retrieval policy with an additional proxy model to control the retrieval process.
Outcome:	Experiments on three in-domain and four out-of-domain QA benchmarks show that SPARKLE outperforms state-of the-art adaptive RAG models, achieving average improvements of 9.17% and 2.85%, respectively.

Copied to clipboard

Jinyuan Fang, Zaiqiao Meng, Craig MacDonald

Question Answering

Challenge:	Iterative retrieval-augmented generation models are difficult to use for multihop question answering (QA) . their retrieval processes can be disrupted by irrelevant documents or factually inaccurate chain-of-thoughts .
Approach:	They propose a knowledge-driven iterative retriever model that decomposes documents into knowledge triples and performs iterativ retrieval with these triples to enable a factually reliable retrieval process.
Outcome:	The proposed model outperforms existing iRAG models with an average improvement of 9.40% in R@3 and 5.14% in F1 on multi-hop QA datasets.

CITB: A Benchmark for Continual Instruction Tuning (2023.findings-emnlp)

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad

Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies (2025.naacl-long)

Challenge:	Existing methods for instruction tuning do not leverage the rich natural language instructions.
Approach:	They propose to use a benchmark to study how instruction tuning works in CL tasks.
Outcome:	The proposed method can achieve similar or better results than existing CL methods.

Copied to clipboard

Zirui Song, Guangxian Ouyang, Meng Fang, Hongbin Na, Zijing Shi, Zhenhao Chen, Fu Yujie, Zeyu Zhang, Shiyu Jiang, Miao Fang, Ling Chen, Xiuying Chen

Challenge:	Existing household robots are inability to recognize potential problems or dangers in home environments.
Approach:	They propose a task of creating anomaly scenarios using generative models instead of manually labeled data to build simulated environments.
Outcome:	The proposed framework outperforms existing models in terms of task description and scene diversity.

A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation (2022.acl-long)

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Shuming Shi, Dacheng Tao

Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models (2025.findings-acl)

Challenge:	Existing models for introducing explicit personas are expensive due to their expensive collection costs.
Approach:	They propose a data manipulation method which is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.
Outcome:	The proposed method is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.

Copied to clipboard

Wanqi Yang, Yanda Li, Meng Fang, Yunchao Wei, Ling Chen

Robustness in NLP

Challenge:	Existing research focused on model-specific adversarial methods, but real-world applications demand a more generalizable approach to audio adversarials.
Approach:	They propose a Chat-Audio Attacks benchmark to evaluate LALMs' robustness . they propose standard evaluation, GPT-4o-based evaluation and human evaluation .
Outcome:	The proposed benchmark aims to explore the robustness of six state-of-the-art LALMs with voice interaction capabilities.

Dict-BERT: Enhancing Language Model Pre-training with Dictionary (2022.findings-acl)

Copied to clipboard

Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang

Self-imitation Learning for Action Generation in Text-based Games (2023.eacl-main)

Challenge:	Pre-trained language models (PLMs) capture word semantics in different contexts, hence the embeddings of rare words on the tail are poorly optimized.
Approach:	They propose to leverage definitions of rare words in dictionaries to enhance language model pre-training by leveraging dictionary definitions.
Outcome:	The proposed model improves understanding of rare words and boosts performance on various NLP downstream tasks.

Copied to clipboard

Zijing Shi, Yunqiu Xu, Meng Fang, Ling Chen

A Survey for Efficient Open Domain Question Answering (2023.acl-long)

Challenge:	Text-based games are situated systems where the game agents observe textual descriptions, and generate textual commands to interact with the environment.
Approach:	They propose a confidence-based self-imitation model to generate action candidates for the RL agent by exploiting past valuable trajectories to adapt a pre-trained language model towards a target game.
Outcome:	The proposed model performs well in multiple challenging games.

Copied to clipboard

Qin Zhang, Shangsi Chen, Dongkuan Xu, Qingqing Cao, Xiaojun Chen, Trevor Cohn, Meng Fang

Natural Language Interfaces

Challenge:	Open domain question answering (ODQA) is a longstanding task that can answer factoid questions without explicit evidence in natural language processing (NLP).
Approach:	They propose to use open domain question answering to answer factual questions from a large knowledge corpus without explicit evidence.
Outcome:	The proposed models can answer factoid questions from a large knowledge corpus without explicit evidence.

Understanding Large Language Model Vulnerabilities to Social Bias Attacks (2025.acl-long)

Copied to clipboard

Jiaxu Zhao, Meng Fang, Fanghua Ye, Ke Xu, Qin Zhang, Joey Tianyi Zhou, Mykola Pechenizkiy

MATH-IDN: A Multilingual Mathematical Problem Solving Dataset Featuring Local Languages in Indonesia (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic capabilities across tasks . however, there is a growing concern about their potential to perpetuate social biases .
Approach:	They evaluate LLMs across gender, racial, and religious bias types . they also explore cross-bias and multiple-biases attacks .
Outcome:	The proposed models are more susceptible to gender bias attacks than racial or religious biases.

Copied to clipboard

Xiao Xiao, Iftitahu Ni'mah, Yuyun Wabula, Mykola Pechenizkiy, Meng Fang

Reasoning

Challenge:	Large Language Models excel at mathematical reasoning in English, but their performance in low-resource languages remains underexplored.
Approach:	They propose a multilingual benchmark for mathematical problem solving in Indonesian, Javanese, Sundanese, and Buginese with English as a reference.
Outcome:	The proposed model reveals significant performance gaps in low-resource languages, particularly Buginese, and highlights key limitations in current multilingual reasoning capabilities.

PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning (2024.acl-long)

Copied to clipboard

Zhihan Zhang, Dong-Ho Lee, Yuwei Fang, Wenhao Yu, Mengzhao Jia, Meng Jiang, Francesco Barbieri

Cross-Lingual Transfer

Challenge:	Instruction tuning has advanced large language models (LLMs) but its application in lower-resource languages faces challenges due to the imbalanced foundational abilities of LLMs across different languages.
Approach:	They propose a pivot language guided generation approach that utilizes a high-resource language as the pivot to enhance instruction tuning in lower-resourced languages.
Outcome:	The proposed approach improves instruction-following abilities of LLMs by 29% on average compared to directly responding in the target language alone.

FARSS: Fisher-Optimized Adaptive Low-Rank and Singular-Vector Selection for Knowledge-Preserving Fine-Tuning (2026.findings-acl)

Copied to clipboard

Renxing Chen, Ziwei Xiang, Peisong Wang, Hongjian Fang, Meng Li, Fanhu Zeng, Yanan Zhu, Peipei Yang, Xu-Yao Zhang, Jian Cheng

Unveiling Multimodal Processing: Exploring Activation Patterns in Multimodal LLMs for Interpretability and Efficiency (2025.findings-emnlp)

Challenge:	Low-rank adaptation methods for large language models have limitations in preserving world knowledge and limiting updates to preserve world knowledge.
Approach:	They propose a Fisher-optimized adaptive low Rank and Singular-VectorSelection framework for knowledge-preserving fine-tuning that allows efficient and task-sensitive updates.
Outcome:	The proposed framework outperforms existing methods for knowledge-preserving fine-tuning.

Copied to clipboard

Chuan Wu, Meng Su, Youxuan Fang, Shaolin Zhu

Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models (2025.acl-long)

Challenge:	Recent advances in multimodal large language models have remained opaque.
Approach:	They propose a method to convert dense MLLMs into fine-grained Mixture-of-Experts architectures.
Outcome:	The proposed method outperforms random expert pruning and sparse activation and model pruning.

Copied to clipboard

Jiaxu Zhao, Meng Fang, Kun Zhang, Mykola Pechenizkiy

MANNER: A Variational Memory-Augmented Model for Cross Domain Few-Shot Named Entity Recognition (2023.acl-long)

Challenge:	Existing methods to assess social biases in natural language processing models show unexpected instability when input texts undergo minor stylistic changes.
Approach:	They conduct a comprehensive analysis of how style transformations impact bias evaluation results . they find formal style transformation significantly affects bias scores . larger models show greater sensitivity to stylistic variations, they find .
Outcome:	The proposed method fails to detect appearance bias, sexual orientation bias, religious bias and religious bias in large language models.

Copied to clipboard

Jinyuan Fang, Xiaobin Wang, Zaiqiao Meng, Pengjun Xie, Fei Huang, Yong Jiang

Low-Resource NLP

Challenge:	Named Entity Recognition (NER) is a fundamental NLP task that aims at classifying mention spans into entity types.
Approach:	They propose a variational memory-augmented few-shot named entity recognition model that uses a memory module to store information from source domain and retrieve relevant information from the memory to augment few-shot task in target domain.
Outcome:	The proposed model can adapt the learned knowledge from source domain to target domain and achieve superior performance on English and Chinese cross domain few-shot NER datasets.

Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering (2024.findings-emnlp)

Copied to clipboard

Wanqi Yang, Yanda Li, Meng Fang, Ling Chen

Natural Language Interfaces

Challenge:	Existing language models have limited sensitivity to temporal information and inadequate temporal reasoning capabilities.
Approach:	They propose a framework that enhances temporal awareness and reasoning . they propose to use Temporal Information-Aware Embedding and Granular Contrastive Reinforcement Learning .
Outcome:	The proposed framework outperforms existing LLMs on time-sensitive question answering tasks.

MedINST: Meta Dataset of Biomedical Instructions (2024.findings-emnlp)

Copied to clipboard

Wenhan Han, Meng Fang, Zihan Zhang, Yu Yin, Zirui Song, Ling Chen, Mykola Pechenizkiy, Qingyu Chen

Turn-Level Active Learning for Dialogue State Tracking (2023.emnlp-main)

Challenge:	Medical data and tasks require extensive preprocessing and standardization for effective use in training LLMs.
Approach:	They propose to use MedINST as a meta-dataset to evaluate LLMs' generalization ability.
Outcome:	The meta-dataset of biomedical instruction measures the generalization ability of LLMs across multiple open-domain tasks.

Copied to clipboard

Zihan Zhang, Meng Fang, Fanghua Ye, Ling Chen, Mohammad-Reza Namazi-Rad

Phrase-level Textual Adversarial Attack with Label Preservation (2022.findings-naacl)

Challenge:	Existing approaches to annotate dialogues require supervised training, which requires human workers to manually annotates dialogues.
Approach:	They propose a turn-level active learning framework to actively select dialogue turns to annotate . their approach can achieve comparable performance to traditional training approaches .
Outcome:	The proposed model achieves comparable performance to existing training approaches with significantly less annotated data.

Copied to clipboard

Yibin Lei, Yu Cao, Dianqi Li, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy

Robustness in NLP

Challenge:	Existing adversarial attacks are usually realized through word-level or sentence-level perturbations, which either limit the perturbation space or sacrifice fluency and textual quality.
Approach:	They propose a phrase-level perturbation-based adversarial ATtack that generates adversarials through phrase- level perturbations.
Outcome:	The proposed approach improves the performance of natural language processing models by reducing the need for word-level perturbations and preserving the fluency and grammaticality of the samples.

More than Minorities and Majorities: Understanding Multilateral Bias in Language Generation (2024.findings-acl)

Copied to clipboard

Jiaxu Zhao, Zijing Shi, Yitong Li, Yulong Pei, Ling Chen, Meng Fang, Mykola Pechenizkiy