Papers by Di Yang

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026.acl-long)

Challenge:	Multimodal sentiment analysis aims to predict the sentiment of video content.
Approach:	They propose a framework that performs contrastive representation learning and contrastive feature decomposition to enhance the representation of multimodal information.
Outcome:	The proposed framework outperforms baseline methods on CH-SIMS, MOSI and MOSEI datasets on a range of metrics.

Copied to clipboard

Wenrui Zhou, Mohamed Hendy, Shu Yang, Qingsong Yang, Zikun Guo, Yuyu Luo, Lijie Hu, Di Wang

Instruction Fusion: Advancing Prompt Evolution through Hybridization (2024.acl-long)

Challenge:	Current sycophancy research has largely overlooked its specific manifestations in the video-language domain.
Approach:	They propose a video-LLM sycophancy benchmarking and evaluation to evaluate scophancies in video-LLMs.
Outcome:	The proposed benchmark evaluates sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks.

Copied to clipboard

Weidong Guo, Jiuding Yang, Kaitong Yang, Xiangyang Li, Zhuwei Rao, Yu Xu, Di Niu

Text Generation

Challenge:	Existing methods for fine-tuning Large Language Models (LLMs) encounter performance limitations, impeding further enhancements in code generation tasks.
Approach:	They propose to combine two distinct prompts through a hybridization process to enhance the evolution of training prompts for code LLMs.
Outcome:	The proposed method significantly improves the performance of Code LLMs across five code generation benchmarks, namely HumanEval, HumanEva+, MBPP, mbap+ and MultiPL-E.

Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Haonan He, Yuchen Ren, Yining Tang, Ziyang Xu, Junxian Li, Minghao Yang, Di Zhang, Yuan Dong, Tao Chen, Shufei Zhang, Yuqiang Li, Nanqing Dong, Wanli Ouyang, Dongzhan Zhou, Peng Ye

TaCIE: Enhancing Instruction Comprehension in Large Language Models through Task-Centred Instruction Evolution (2025.coling-main)

Challenge:	Biology-Instructions is the first large-scale instruction-tuning dataset for multi-omics biological sequences.
Approach:	They propose a large-scale instruction-tuning dataset for multi-omics biological sequences . they propose 'chatMultiOmics' to overcome limitations of current LLMs on multi-ome tasks .
Outcome:	The proposed dataset bridges LLMs and complex biological sequence-related tasks while maintaining conversational fluency.

Copied to clipboard

Jiuding Yang, Shengyao Lu, Weidong Guo, Xiangyang Li, Kaitong Yang, Yu Xu, Di Niu

PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction (2021.acl-long)

Challenge:	Existing methods for fine-tuning Large Language Models (LLMs) encounter performance limitations, impeding further enhancements in code generation tasks.
Approach:	They propose to combine two distinct prompts through a hybridization process to enhance the evolution of training prompts for code LLMs.
Outcome:	The proposed method significantly improves the performance of Code LLMs across five code generation benchmarks.

Copied to clipboard

Shulin Liu, Tao Yang, Tianchi Yue, Feng Zhang, Di Wang

From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis (2026.acl-long)

Challenge:	Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts.
Approach:	They propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) which jointly learns how to understand language and correct spelling errors.
Outcome:	The proposed model outperforms state-of-the-art methods on widely used benchmarks and achieves superior performance against existing models.

Copied to clipboard

Zhi Zeng, Jiaying Wu, Minnan Luo, Di Zhang, Yifei Yang, Xiangzheng Kong, Herun Wan, Zihan Ma

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models (2026.acl-long)

Challenge:	Existing benchmarks focus on binary veracity judgments and do not evaluate process-level justifications for misinformation models.
Approach:	They propose a video misinformation analysis benchmark that assesses reasoning in video misinterpretation.
Outcome:	The proposed framework improves reasoning accuracy and explanation quality compared to existing models . it covers 12 fine-grained deception categories and progresses from perceptual attribution to intent and persuasion analysis.

Copied to clipboard

Jiayi Zhang, Shu Yang, Junchao Wu, Derek F. Wong, Di Wang

DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines (2023.findings-emnlp)

Challenge:	Recent studies have focused on the internal representations of large language models and the mechanisms that lead to unintended cross-topic generalization.
Approach:	They propose a method that uses inhibition to localize political neurons and a technique that uses topic-specific blocking to mitigate the cross-topic generalization.
Outcome:	The proposed method reduces cross-topic generalization by 20% while preserving topic-specific performance.

Copied to clipboard

Prakhar Gupta, Yang Liu, Di Jin, Behnam Hedayatnia, Spandana Gella, Sijia Liu, Patrick Lange, Julia Hirschberg, Dilek Hakkani-Tur

ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis (2023.findings-acl)

Challenge:	Dialogue models are able to generate fluent and interesting responses, but they can be difficult to control and may produce non-engaging, unsafe results.
Approach:	They propose a framework for controlling dialogue model behavior using natural language rules, or guidelines, which provide information about the context they are applicable to and what should be included in the response.
Outcome:	The proposed framework is effective in three open-domain dialogue response generation tasks and is consistent with the developer's expectations and intent.

Copied to clipboard

Yakun Yu, Mingjun Zhao, Shi-ang Qi, Feiran Sun, Baoxun Wang, Weidong Guo, Xiaoli Wang, Lei Yang, Di Niu

MatRank: Text Re-ranking by Latent Preference Matrix (2022.findings-emnlp)

Challenge:	Existing methods for multimodal sentiment analysis focus on general knowledge, which is inadequate to identify specific sentiments across modalities.
Approach:	They propose a method where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture.
Outcome:	The proposed method outperforms all prior methods on three popular benchmarks on multimodal sentiment analysis metrics.

Copied to clipboard

Jinwen Luo, Jiuding Yang, Weidong Guo, Chenglin Li, Di Niu, Yu Xu

Information Retrieval

Challenge:	Existing methods for text ranking have improved performance, but there are still challenges.
Approach:	They propose a method that learns to re-rank the text retrieved for a given query by learning to predict the most relevant passage based on a latent preference matrix.
Outcome:	The proposed method outperforms all prior methods on datasets with extensive results.

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Copied to clipboard

Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing

Text Generation

Challenge:	Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach:	They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome:	Texar supports machine translation, summarization, dialog, content manipulation, and more.

iMOVE : Instance-Motion-Aware Video Understanding (2025.findings-acl)

Copied to clipboard

Jiaze Li, Yaya Shi, Zongyang Ma, Haoran Xu, Yandong.bai Yandong.bai, Huihui Xiao, Ruiwen Kang, Fan Yang, Tingting Gao, Di Zhang

Visual Data in NLP

Challenge:	Recent advances in Video Large Language Models have led to rapid development, significantly enhancing the capture of overall video semantics and achieving remarkable performance in general video understanding tasks.
Approach:	They propose a large-scale instance-motion-aware video instruction-tuning dataset iMOVE that utilizes Event-awful Spatiotemporal Efficient Modeling to retain informative instance spatiotemporal motion details while maintaining computational efficiency.
Outcome:	The proposed model excels in video temporal understanding and general video understanding.

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)

Copied to clipboard

Yi Su, Jiayi Zhang, Shu Yang, Xinhai Wang, Lijie Hu, Di Wang

Explainability & Interpretability in NLP

Challenge:	Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis.
Approach:	They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts .
Outcome:	The proposed method bridges psychological value frameworks with neuron analysis in large language models.

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images (2026.acl-long)

Copied to clipboard

Qishun Yang, Shu Yang, Lijie Hu, Di Wang

Visual Data in NLP

Challenge:	Existing methods require explicit safety labels or contrastive data, yet visual inputs enable harmful outputs.
Approach:	They propose a visual self-fulfilling alignment mechanism that fine-tunes vision-language models on neutral VQA tasks without any safety labels.
Outcome:	The proposed approach reduces attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities.

Private Language Models via Truncated Laplacian Mechanism (2024.emnlp-main)

Copied to clipboard

Tianhao Huang, Tao Yang, Ivan Habernal, Lijie Hu, Di Wang

AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor (2026.findings-acl)

Challenge:	Existing methods for word embedding are prone to privacy leakage, resulting in weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength.
Approach:	They propose a method for private word embedding that uses a non-trivial extension of the truncated Laplacian mechanism and propose to test its effectiveness.
Outcome:	The proposed method has lower variance compared to the previous methods.

Copied to clipboard

Shu Yang, Jingyu Hu, Tong Li, Hanqi Yan, Wenxuan Wang, Di Wang

Challenge:	AutoMonitor-Bench evaluates the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes.
Approach:	They introduce AutoMonitor-Bench, a benchmark designed to evaluate misbehavior monitors across diverse tasks and failure modes.
Outcome:	The new benchmark evaluates the reliability of LLM-based misbehavior monitors across tasks and failure modes.

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

Reasoning

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations (2025.coling-main)

Copied to clipboard

Jiahao Zhao, Jingwei Zhu, Minghuan Tan, Min Yang, Renhao Li, Yang Di, Chenhao Zhang, Guancheng Ye, Chengming Li, Xiping Hu, Derek F. Wong

Challenge:	CPsyExam prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.
Approach:	They propose a psychological benchmark, CPsyExam, constructed from questions from Chinese examination systems.
Outcome:	The proposed benchmark prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.

Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning (2022.emnlp-main)

Copied to clipboard

Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur

Green & Sustainable NLP

Challenge:	Prefix-tuning is an essential paradigm of parameter-efficient transfer learning . fine-tuned models require separate copies of model parameters for each task .
Approach:	They propose to understand and further develop prefix-tuning through the kernel lens . they propose a new variant of prefix tuning that shares the exact mechanism as prefix tun .
Outcome:	The proposed method improves prefix-tuning performance by training only a small portion of parameters.

Exploiting Hierarchically Structured Categories in Fine-grained Chinese Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Jiuding Yang, Jinwen Luo, Weidong Guo, Di Niu, Yu Xu

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (CNER) is a widely used technology in various applications.
Approach:	They propose a method that uses a custom-designed relevance scoring function to learn the potential relevance between different flattened hierarchical labels.
Outcome:	The proposed method outperforms the state-of-the-art on the FiNE dataset.

CODEMENV: Benchmarking Large Language Models on Code Migration (2025.findings-acl)

Copied to clipboard

Keyuan Cheng, Xudong Shen, Yihao Yang, TengyueWang TengyueWang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, Di Wang

From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues (2024.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated remarkable proficiency in handling a wide range of tasks within the software engineering domain, but their ability to perform code migration—adapting code to different environments—remains underexplored.
Approach:	They propose a benchmark to evaluate large language models’ performance in handling code migration tasks.
Outcome:	The proposed benchmark comprises 922 data points across 19 Python and Java packages and offers three tasks to systematically evaluate code migration: identifying version-incompatible functions, determining function changes, and adapting code to target environments.

Copied to clipboard

Yu Li, Devamanyu Hazarika, Di Jin, Julia Hirschberg, Yang Liu

T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation (2023.findings-acl)

Challenge:	a recent study shows that robots display human-like characteristics in dialogues . this anthropomorphism raises concerns about the accuracy of AI and its capabilities .
Approach:	They propose to use a dataset to analyze self-anthropomorphic and non-self-anthropophilic responses in robots . they propose to combine these two types of responses to create a new category of bot responses .
Outcome:	The proposed approach preserves the original dialogues from existing corpora and enhances them with paired responses: self-anthropomorphic and non-self-anthropophilic for each original bot response.

Copied to clipboard

Jialu Wang, Xinyue Liu, Zonglin Di, Yang Liu, Xin Wang

Visual Data in NLP

Challenge:	Recent advances in text-to-image generative models have produced high quality images with a breakthrough of inference speed.
Approach:	They propose a text-to-image association test framework that quantifies implicit stereotypes between concepts and valence and those in images.
Outcome:	The proposed framework quantifies implicit stereotypes between concepts and valence and those in images.

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Jingkun Ma, Runzhe Zhan, Yang Li, Di Sun, Hou Pong Chan, Lidia S. Chao, Derek F. Wong

Reasoning

Challenge:	Existing Large Multi-modal Models lack a robust visual processing capability that is often masked by evaluation metrics that prioritize final-answer accuracy.
Approach:	They propose a three-layer evaluation framework that scrutinizes the generation of valid visual aids and the soundness of subsequent reasoning steps.
Outcome:	The proposed framework examines the generation of valid visual aids and the soundness of subsequent reasoning steps on state-of-the-art models.

PerfCoder: Large Language Models for Interpretable Code Performance Optimization (2026.findings-acl)

Copied to clipboard

Jiuding Yang, Shengyao Lu, Hongxuan Liu, Shayan Shirahmad Gale Bagi, Zahra Fazel, Tomasz Czajkowski, Di Niu

SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution (2026.findings-acl)

Challenge:	Large language models (LLMs) have advanced automatic code generation, but their ability to produce high-performance code remains limited.
Approach:	They propose a family of large language models that generate performance-enhanced code through interpretable and customized optimization strategies.
Outcome:	The proposed model outperforms existing models on the PIE code performance benchmark and produces interpretable feedback that can guide larger LLMs in a planner–optimizer workflow.

Copied to clipboard

Zhenyu He, Qingping Yang, Wei Shen, Xiaojian Zhong, Kechi Zhang, Chenxin An, Wenlei Shi, Tianle Cai, Di He, Jiaze Chen, Jingjing Xu

CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling (2024.findings-acl)

Challenge:	SWE-Swiss-32B demonstrates strong generalization to other common LLM benchmarks.
Approach:	They propose a two-phase training recipe that decomposes issue resolution into three core skills: Localization, Repair, and Unit Test Generation.
Outcome:	The proposed model achieves a 60.2% score on the SWE-bench Verified benchmark and is in the top-tier performance bracket of much larger models.

Copied to clipboard

Chenhao Zhang, Renhao Li, Minghuan Tan, Min Yang, Jingwei Zhu, Di Yang, Jiahao Zhao, Guancheng Ye, Chengming Li, Xiping Hu

Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements (2025.findings-acl)

Challenge:	Existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence.
Approach:	They propose a report-based multi-turn dialogue reconstruction framework for Chinese psychological counseling that uses large language models to assist counseling.
Outcome:	The proposed framework is open-source and can be used in future research.

Copied to clipboard

Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, Di Wang

Robustness in NLP

Challenge:	Existing fraud detection benchmarks focus on single-turn classification tasks, failing to capture dynamic nature of real-world fraud attempts.
Approach:	They propose a bilingual benchmark to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships.
Outcome:	The proposed model improves in role-play settings and in e-commerce and recommendation systems.

Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions (2023.findings-acl)

Copied to clipboard

Yibin Wang, Yichen Yang, Di He, Kun He

Robustness in NLP

Challenge:	Embedding interval bound constraint is important for NLP models to be certified robust, but adversarial examples can be crafted by synonym substitutions.
Approach:	They propose a triplet loss to train robustness-aware word embeddings for better certified robustness.
Outcome:	The proposed method outperforms state-of-the-art certified defense baselines and generalizes well to unseen substitutions.

HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)

Copied to clipboard

An Wang, Xingwu Sun, Ruobing Xie, Shuaipeng Li, Jiaqi Zhu, Zhen Yang, Pinxue Zhao, Weidong Han, Zhanhui Kang, Di Wang, Naoaki Okazaki, Cheng-zhong Xu

Error Analysis of Uyghur Name Tagging: Language-specific Techniques and Remaining Challenges (L18-1)

Challenge:	Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization.
Approach:	They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts .
Outcome:	The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters.

Copied to clipboard

Halidanmu Abudukelimu, Abudoukelimu Abulizi, Boliang Zhang, Xiaoman Pan, Di Lu, Heng Ji, Yang Liu

Syntactic Text Processing

Challenge:	despite efforts at name tagging, there is limited understanding on the performance ceiling . despite the high-resource language, there are very few natural language processing tools available .
Approach:	They propose to use a machine learning model to identify Uyghur name tagger errors . they conclude that such a model is unlikely to be effective for Uygur, or low-resource languages .
Outcome:	The proposed model is unlikely to be effective for Uyghur, or low-resource languages in general, the authors argue . they show that the proposed model can be used for high-res languages with superficial features .

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward (2025.naacl-long)

Copied to clipboard

Ruohong Zhang, Liangke Gui, Zhiqing Sun, Yihao Feng, Keyang Xu, Yuanhan Zhang, Di Fu, Chunyuan Li, Alexander G Hauptmann, Yonatan Bisk, Yiming Yang

Improving Translation Quality Estimation with Bias Mitigation (2023.acl-long)

Challenge:	Existing studies have demonstrated that direct preference optimization (DPO) can be effective in generalizing large language models, but its effectiveness in video domain remains limited.
Approach:	They propose a framework that utilizes detailed video captions as a proxy of video content to enable language models to incorporate this information as supporting evidence for scoring video Question Answering (QA) predictions.
Outcome:	The proposed framework shows that it can be used to align language models with video content and improves performance on open-ended video QA tasks.

Copied to clipboard

Hui Huang, Shuangzhi Wu, Kehai Chen, Hui Di, Muyun Yang, Tiejun Zhao

Multilinguality

Challenge:	State-of-the-art translation Quality Estimation models are biased, relying on monolingual features while ignoring the bilingual semantic alignment.
Approach:	They propose a method to mitigate the bias of translation quality estimation models by contrastive learning between clean and noisy sentence pairs.
Outcome:	The proposed method improves the estimation performance while mitigating the bias.

Challenges to Open-Domain Constituency Parsing (2022.findings-acl)

Copied to clipboard

Sen Yang, Leyang Cui, Ruoxi Ning, Di Wu, Yue Zhang

Challenge:	Existing findings on cross-domain constituency parsing are only made on a limited number of domains.
Approach:	They manually annotate a high-quality constituency treebank containing five domains and analyze challenges to open-domain constituency parsing using a set of linguistic features.
Outcome:	The proposed model significantly improves the performance of the proposed model on the domain-variant features.

Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention (2022.findings-naacl)

Copied to clipboard

Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur

Dissecting Fine-Tuning Unlearning in Large Language Models (2024.emnlp-main)

Challenge:	Existing methods to fine-tune pre-trained language models are parameter efficient . fine- tuning the models requires multiple copies of the parameters, which is inefficient.
Approach:	They propose to use kernel-based adapters to tune only a few parameters while freezing the rest of the parameters.
Outcome:	The proposed methods achieve or improve strong performance over a diverse set of natural language generation and understanding tasks.

Copied to clipboard

Yihuai Hong, Yuelin Zou, Lijie Hu, Ziqian Zeng, Di Wang, Haiqin Yang

Understanding the Repeat Curse in Large Language Models from a Feature Perspective (2025.findings-acl)

Challenge:	Existing methods for fine-tuning-based unlearning are ineffective at completely erasing model-embedded knowledge, but their true effectiveness remains unclear.
Approach:	They propose to use activation patching and parameter restoration experiments to examine the limitations of fine-tuning-based unlearning methods for erasing harmful, sensitive, or copyrighted information within large language models.
Outcome:	The proposed methods alter the model’s knowledge retrieval process rather than genuinely erasing the problematic knowledge embedded in the model parameters.

Copied to clipboard

Junchi Yao, Shu Yang, Jianhua Xu, Lijie Hu, Mengdi Li, Di Wang

Using In-Context Learning to Improve Dialogue Safety (2023.findings-emnlp)

Challenge:	Large language models suffer from repetitive text generation, a phenomenon we refer to as the ”Repeat Curse”.
Approach:	They propose a method to induce and analyze the Repeat Curse in large language models by using mechanistic interpretability.
Outcome:	The proposed method induces and analyzes the Repeat Curse in large language models using mechanistic interpretability.

Copied to clipboard

Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tur

Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences (2022.naacl-main)

Challenge:	Recent work has highlighted safety issues with large neural-based conversational models.
Approach:	They propose a retrieval-based approach for reducing bias and toxicity in chatbot responses . they retrieve demonstrations of safe responses to similar dialogue contexts to generate a response .
Outcome:	The proposed method reduces bias and toxicity in three chatbot models . it can be used in compliment to existing dialogue safety approaches, such as RLHF.

Copied to clipboard

Yifan Chen, Qi Zeng, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang

Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech (D19-3)

Challenge:	Existing models for long sequences are not efficient due to the quadratic space and time complexity of the self-attention modules.
Approach:	They propose to reduce the quadratic complexity to linear (modulo logarithmic factors) by low-dimensional projection and row selection.
Outcome:	The proposed methods outperform transformer-based models with smaller time/space footprint on the Long Range Arena benchmark.

Copied to clipboard

Yuanfeng Song, Di Jiang, Weiwei Zhao, Qian Xu, Raymond Chi-Wing Wong, Qiang Yang

Speech & Audio in NLP

Challenge:	Language model adaptation (LMA) is a promising solution for conversational speech recognition systems.
Approach:	They propose to use language model adaptation techniques to adapt language models to conversational speech recognition.
Outcome:	The proposed toolkit compares state-of-the-art language model adaptation techniques in conversational speech recognition tasks.

Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation (2025.findings-emnlp)

Copied to clipboard

Tong Li, Shu Yang, Junchao Wu, Jiyao Wei, Lijie Hu, Mengdi Li, Derek F. Wong, Joshua R. Oltmanns, Di Wang

Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding (2022.findings-emnlp)

Challenge:	Existing data on suicidal ideation in private conversations are limited . a new dataset of 1,200 test cases is presented to address this gap .
Approach:	They propose a dataset of 1,200 test cases simulating implicit suicidal ideation in private contexts.
Outcome:	The proposed dataset includes 1,200 test cases simulating implicit suicidal ideation in dialogue scenarios.

Copied to clipboard

Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, Zeyu Xiong

Code Reffix: A Benchmark for Reflection-Guided Code Repair with Large Language Models (2026.findings-acl)

Challenge:	Existing methods for temporal sentence grounding ignore two crucial issues . 1) Boundary-bias: the video downsampling process may lose these two frames . 2) Reasoning-biases: such incorrect new boundary frames lead to the reasoning bias .
Approach:	They propose a siamese sampling mechanism to generate additional contextual frames . they use a reasoning strategy to learn the inter-relationship among these frames a .
Outcome:	Extensive experiments demonstrate the effectiveness of a new siamese sampling network on three challenging datasets.

Copied to clipboard

Zaiyuan Di, Jianting Chen, Yunxiao Yang, Xiaoying Gao, Li Yang, Zhihao Wang, Yang Xiang

New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs (2026.acl-long)

Challenge:	Existing benchmarks focus on the repair generation capability of LLMs, lacking fine-grained evaluation of reflection.
Approach:	They propose a benchmark with oracle reflections and a dual-task protocol to decouple evaluation of reflection from repair.
Outcome:	The proposed benchmarks show that underperforming reflection capabilities remain a bottleneck for code repair.

Copied to clipboard

Shiyao Cui, QingLin Zhang, Di Wang, Yida Lu, Zhexin Zhang, Jinhua Gao, Jinglin Yang, Min He, Han Qiu, Minlie Huang

Information Retrieval

Challenge:	Neologisms can foster new linguistic consensus by stabilizing shared meanings and usage in common communicative norms.
Approach:	They propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms . they propose 'SeTox' framework that integrates real-time web context for naeologim detection .
Outcome:	The proposed framework outperforms large-scale models in detecting neologism toxicity.

HypMix: Hyperbolic Interpolative Data Augmentation (2021.emnlp-main)

Copied to clipboard

Ramit Sawhney, Megh Thakkar, Shivam Agarwal, Di Jin, Diyi Yang, Lucie Flek

Responsible & Trustworthy NLP

Challenge:	Existing methods for data augmentation involve performing mathematical operations over the raw input samples or their latent states representations, but these operations are performed in the Euclidean space, simplifying these representations and resulting in noisy interpolations.
Approach:	They propose a model-, data-, and modality-agnostic interpolative data augmentation technique operating in the hyperbolic space that captures the complex geometry of input and hidden state hierarchies better than its contemporaries.
Outcome:	The proposed technique outperforms state-of-the-art methods on benchmark and low resource datasets across speech, text, and vision modalities.

Decoder-Only LLMs can be Masked Auto-Encoders (2025.acl-short)

Copied to clipboard

Dan Qiao, Yuan Gao, Zheming Yang, Di Yang, Ziheng Wu, Pengcheng Lu, Minghui Qiu, Juntao Li, Min Zhang

Bridging the Gap between Training and Inference for Neural Machine Translation (P19-1)

Challenge:	Modern NLP workflows require different models for generation and embedding tasks.
Approach:	They propose a method that transforms an LLM into a Uni-Directional Masked Auto-Encoder.
Outcome:	The proposed method achieves state-of-the-art under unsupervised conditions with merely 100 training steps.

Copied to clipboard

Wen Zhang, Yang Feng, Fandong Meng, Di You, Qun Liu

Machine Translation

Challenge:	Neural Machine Translation generates target words sequentially while at inference it has to generate the entire sequence from scratch.
Approach:	They propose to use ground truth and inference to generate target words sequentially while at inference it has to generate the entire sequence from scratch.
Outcome:	Experiments on Chinese->English and WMT’14 English->German translation tasks show that the proposed model can achieve significant improvements on multiple datasets.

DMix: Adaptive Distance-aware Interpolative Mixup (2022.acl-short)

Copied to clipboard

Ramit Sawhney, Megh Thakkar, Shrey Pandit, Ritesh Soun, Di Jin, Diyi Yang, Lucie Flek

Challenge:	Interpolation-based regularisation methods such as Mixup have shown to be effective for various tasks and modalities.
Approach:	They propose an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space.
Outcome:	The proposed method achieves state-of-the-art on sentence classification over existing methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations.

Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information (2023.eacl-main)

Copied to clipboard

Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Sungjin Lee, Devamanyu Hazarika, Mahdi Namazifar, Di Jin, Yang Liu, Dilek Hakkani-Tur

Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs (2022.naacl-main)

Challenge:	Intent detection is a fundamental element in task-oriented dialogue systems, usually occurring within the Natural Language Understanding component.
Approach:	They propose an in-context data augmentation approach that fine-tunes a pre-trained language model and synthesizes new datapoints that correspond to given intents.
Outcome:	The proposed method produces training data that achieves state-of-the-art on three challenging intent detection datasets and performs on par with the state- of-the art in full-shot settings.

Copied to clipboard

Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur

Structured Data in NLP

Challenge:	Existing conversation models treat knowledge selection as a sentence ranking problem where each sentence is handled individually, ignoring the internal semantic connection between sentences.
Approach:	They propose to automatically convert background knowledge documents into document semantic graphs and perform knowledge selection over such graphs.
Outcome:	The proposed model improves on the knowledge selection task and the response generation task on HollE and generalizes on unseen topics in WoW.

MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL (2025.coling-main)

Copied to clipboard

Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li

Programming Languages in NLP

Challenge:	Recent LLM-based Text-to-SQL methods suffer from performance degradation on “huge” databases and complex user questions that require multi-step reasoning.
Approach:	They propose a framework that integrates a decomposer agent and auxiliary agents to generate SQL queries from natural language text.
Outcome:	The proposed framework achieves comparable execution accuracy on SQL-Llama tasks compared to the baseline model.

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs (2025.findings-acl)

Copied to clipboard

Guhao Feng, Kai Yang, Yuntian Gu, Xinyue Ai, Shengjie Luo, Jiacheng Sun, Di He, Zhenguo Li, Liwei Wang

Reasoning

Challenge:	Despite the success of transformer-based large language models, understanding and enhancing their mathematical capabilities remains a significant challenge.
Approach:	They propose to use numerical precision as a key factor that influences LLMs' effectiveness in arithmetical tasks to determine their effectiveness.
Outcome:	The proposed models perform better in arithmetic tasks than transformer-based models with standard numerical precision.

WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition (D18-1)

Copied to clipboard

Yufeng Diao, Hongfei Lin, Di Wu, Liang Yang, Kan Xu, Zhihao Yang, Jian Wang, Shaowu Zhang, Bo Xu, Dongyu Zhang