Papers by Ting Zhang

R2A-TLS: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Integration (2025.findings-emnlp)

Challenge:	Existing evaluation metrics are expensive and easy to conduct but ineffective to reflect dialogue quality.
Approach:	They propose a self-supervised fine-grained dialogue evaluation framework which can automatically assign fine-granular scores for arbitrarily dialogue data.
Outcome:	The proposed framework is highly consistent with human evaluations and better than the state-of-the-art models.

Copied to clipboard

Chenlong Bao, Shijie Li, Minghao Hu, Ming Qiao, Bin Zhang, Jin-Tao Tang, Shasha Li, Ting Wang

Information Retrieval

Challenge:	Existing methods struggle to capture coherent event narratives due to fragmented descriptions . Existing approaches accumulate noise through iterative retrieval strategies that lack relevance evaluation.
Approach:	They propose a reflective retrieval-augmented timeline summarization with Causal-Semantic Intergration approach for open-domain timeline summarizing .
Outcome:	The proposed approach outperforms the best prior published approaches.

A Self-verified Method for Exploring Simile Knowledge from Pre-trained Language Models (2024.lrec-main)

Copied to clipboard

Longxuan Ma, Changxin Ke, Shuhan Zhou, Churui Sun, Wei-Nan Zhang, Ting Liu

VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models (2024.emnlp-main)

Challenge:	Pre-trained language models (PLMs) have succeeded in natural language processing because they learn generic knowledge from a large corpus.
Approach:	They propose a method that allows pre-trained language models to explore simile knowledge from PLMs . they enhance PLM models with a multi-level simile recognition task that evaluates similes aplenty .
Outcome:	The proposed method can explore more accurate simile knowledge for PLMs.

Copied to clipboard

Yifei Liu, Jicheng Wen, Yang Wang, Shengyu Ye, Li Lyna Zhang, Ting Cao, Cheng Li, Mao Yang

Stimulate the Critical Thinking of LLMs via Debiasing Discussion (2025.emnlp-main)

Challenge:	Recent research has focused on pushing weight-only quantization to extremely low-bit due to numerical representation limitations.
Approach:	They propose a vector-based quantization approach that pushes LLMs to extremely low-bit . they propose scalar-based weight quantization that reduces memory requirements and optimizes storage costs .
Outcome:	The proposed method reduces model quantization perplexity by 0.01-0.34 on LLaMA-2, 0.38-0.68 on mistral-7B, 4.41-7.34, on llaMA-3 on QA tasks on average.

Copied to clipboard

Ruiyu Xiao, Lei Wu, Yuanxing Liu, Weinan Zhang, Ting Liu

Robustness in NLP

Challenge:	Existing studies show that large language models (LLMs) are often prone to stance homogeneity and human preference biases when faced with conflicting perspectives.
Approach:	They propose a novel two-stage training framework to address stance homogeneity bias and human preference bias by generating multi-model discussion datasets and optimizing reinforcement learning from human feedback to align with discussion correctness.
Outcome:	The proposed framework reduces stance homogeneity bias and human preference bias and improves generalization capabilities on non-discussion scenarios and out-of-domain datasets.

SMART: Evaluating LLMs’ Mathematical Reasoning via a Human Cognitive Process-Inspired Benchmark (2026.acl-long)

Copied to clipboard

Yujie Hou, Mei Wang, Yaoyao Zhong, Ting Zhang, Xuetao Ma, Hua Huang

Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective (2022.coling-1)

Challenge:	Existing evaluation methods focus on the final answer or on the intermediate reasoning steps, overlooking its inherently multi-stage and multi-dimensional nature.
Approach:	They propose a benchmark that decomposes mathematical problem-solving into four cognitive dimensions and introduces dimension-specific tasks to measure their cognitive processes.
Outcome:	The proposed model decomposes mathematical problem-solving into four cognitive dimensions and introduces dimension-specific tasks to measure their cognitive processes.

Copied to clipboard

Shihan Dou, Rui Zheng, Ting Wu, SongYang Gao, Junjie Shan, Qi Zhang, Yueming Wu, Xuanjing Huang

A Survey on LLMs for Story Generation (2025.findings-emnlp)

Challenge:	Existing methods to debiase samples with biased features obstructs the model in learning from non-biased parts of the samples.
Approach:	They propose to eliminate spurious correlations in a fine-grained manner from a feature space perspective by using Random Fourier Features and weighted re-sampling to decorrelate dependencies between features.
Outcome:	The proposed method eliminates spurious correlations in a fine-grained manner from a feature space perspective.

Copied to clipboard

Maria Teleki, Vedangi Bengali, Xiangjue Dong, Sai Tejas Janjur, Haoran Liu, Tian Liu, Cong Wang, Ting Liu, Yin Zhang, Frank Shipman, James Caverlee

Interpreting Twitter User Geolocation (2020.acl-main)

Challenge:	Methods for story generation with Large Language Models (LLMs) have come into the spotlight recently.
Approach:	They propose a novel taxonomy of LLMs for story generation consisting of two major paradigms: independent story generation by an LLM, and author-assistance for story creation .
Outcome:	The proposed taxonomy compares existing work on the topic with those of novel author-assistance models.

Copied to clipboard

Ting Zhong, Tianliang Wang, Fan Zhou, Goce Trajcevski, Kunpeng Zhang, Yi Yang

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)

Challenge:	Existing methods for identifying user geolocation suffer from a lack of interpretability on the corresponding results.
Approach:	They adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting locations.
Outcome:	The proposed method provides meaningful explanations on prediction results and also uncovers the so-called "black-box" GNN-based models by investigating the effect of individual nodes.

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting (2023.findings-emnlp)

Challenge:	Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters.
Approach:	They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety.
Outcome:	The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings.

Copied to clipboard

Haoyang Huang, Tianyi Tang, Dongdong Zhang, Xin Zhao, Ting Song, Yan Xia, Furu Wei

Low-Resource NLP

Challenge:	Large language models (LLMs) demonstrate impressive multilingual capability, but their performance varies substantially across different languages.
Approach:	They propose a generic template prompt that stimulates cross-lingual and logical reasoning skills to enhance task performance across languages.
Outcome:	The proposed method improves multilingual capability across languages and covers high-resource and low-resourced languages.

Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents (2023.findings-eacl)

Copied to clipboard

Yanfei Dong, Lambert Deng, Jiazheng Zhang, Xiaodong Yu, Ting Lin, Francesco Gelli, Soujanya Poria, Wee Sun Lee

Zero Pronoun Resolution with Attention-based Neural Network (C18-1)

Challenge:	Existing datasets do not cover documents with complex spatial structures and a lack of spatial information for document entity classification.
Approach:	They propose a new spatial bias in attention calculation based on the K-nearest-neighbor graph of document entities that limits entities’ attention to their local radius.
Outcome:	The proposed model outperforms baselines in most entity types and is highly parameter-efficient compared to existing methods.

Copied to clipboard

Qingyu Yin, Yu Zhang, Weinan Zhang, Ting Liu, William Yang Wang

Challenge:	Recent neural network methods for zero pronoun resolution use contextual information to encode the zero pronomins since they contain no actual content.
Approach:	They propose a self-attention mechanism for encoding zero pronouns that focus on some informative parts of the associated texts and produce an efficient way of encode them.
Outcome:	The proposed model significantly surpasses existing Chinese zero pronoun resolution baseline systems.

RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning (2025.emnlp-main)

Copied to clipboard

Yu Wang, Shiwan Zhao, Zhihu Wang, Ming Fan, Xicheng Zhang, Yubo Zhang, Zhengfan Wang, Heyuan Huang, Ting Liu

Information Retrieval

Challenge:	Existing RAG paradigms often overlook the cognitive step of applying knowledge, leaving a gap between retrieved facts and task-specific reasoning.
Approach:	They introduce a module extension that integrates application-aware reasoning into the RAG pipeline.
Outcome:	Experiments show that RAG+ outperforms standard RAG variants and achieves gains of 3–5% in complex scenarios.

Multi-Stage Pre-training for Automated Chinese Essay Scoring (2020.emnlp-main)

Copied to clipboard

Wei Song, Kai Zhang, Ruiji Fu, Lizhen Liu, Ting Liu, Miaomiao Cheng

TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification (2025.acl-long)

Challenge:	Existing methods for automatic essay scoring are based on hand-crafted surface-level features, but recent advances in representation learning have improved performance.
Approach:	They propose a pre-training based automated Chinese essay scoring method with weakly supervised pre- training, supervised cross- prompt fine-tuning and supervised target- prompt refine-tuneing.
Outcome:	The proposed method improves a state-of-the-art neural essay scorer in terms of effectiveness and domain adaptation ability, while in-depth analysis also reveals its limitations.

Copied to clipboard

Yindu Su, Huike Zou, Lin Sun, Ting Zhang, Haiyang Yang, Chen Li Yu, David Lo, Qingheng Zhang, Shuguang Han, Jufeng Chen

Green & Sustainable NLP

Challenge:	Existing methods for product attribute value identification face critical challenges . seller-provided attribute values are often incomplete or inaccurate .
Approach:	They propose a retrieval-based method that uses taxonomy-aware contrastive learning . they use product profiles and candidate values to encode and retrieve attributes based on similarity .
Outcome:	The proposed method is based on a taxonomy-aware, hard negative sampling and adaptive inference with dynamic thresholds.

CLIP Models are Few-Shot Learners: Empirical Studies on VQA and Visual Entailment (2022.acl-long)

Copied to clipboard

Haoyu Song, Li Dong, Weinan Zhang, Ting Liu, Furu Wei

Visual Data in NLP

Challenge:	Previously, CLIP was only regarded as a powerful visual encoder.
Approach:	They propose a parameter-efficient fine-tuning strategy to boost CLIP's few-shot performance on a visual entailment task without introducing any additional pre-training procedure.
Outcome:	The proposed strategy achieves competitive zero/few-shot results on visual question answering and visual entailment tasks without introducing any additional pre-training procedure.

Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements (2023.findings-emnlp)

Copied to clipboard

Yushan Qian, Weinan Zhang, Ting Liu

LLMs Meet Isolation Kernel: Lightweight, Learning-free Binary Embeddings for Fast Retrieval (2026.findings-acl)

Challenge:	Empathetic dialogue is an essential part of building harmonious social relationships and contributes to the development of a helpful AI.
Approach:	They propose three methods to improve the performance of large language models (LLMs) they propose semantically similar in-context learning, two-stage interactive generation and combination with the knowledge base.
Outcome:	The proposed methods achieve state-of-the-art in automatic and human evaluations and the possibility of GPT-4 simulating human evaluators.

Copied to clipboard

Zhibo Zhang, Yang Xu, Kai Ming Ting, Cam-Tu Nguyen

Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages (2025.acl-long)

Challenge:	Large language models (LLMs) embeddings are typically high-dimensional, leading to substantial storage and retrieval overhead.
Approach:	They propose a learning-free method that transforms an LLM embedding into a binary embeddable using Isolation Kernel (IKE).
Outcome:	The proposed method performs 16.7 faster retrieval and 16 lower memory usage than the original LLM embeddings while maintaining comparable accuracy.

Copied to clipboard

Zeli Su, Ziyin Zhang, Guixian Xu, Jianing Liu, Xu Han, Ting Zhang, Yushuang Dong

DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering (2022.findings-acl)

Challenge:	XLM-R and mBART have advanced multilingualism in NLP, but low-resource languages such as Tibetan, Uyghur, Kazakh, and Mongolian are underserved.
Approach:	They propose a framework for adapting multilingual encoders to text generation in extremely low-resource languages by reusing the weights between the encoder and the decoder.
Outcome:	The proposed framework performs better on various downstream tasks even when compared with much larger models.

Copied to clipboard

Le Qi, Shangwen Lv, Hongyu Li, Jing Liu, Yu Zhang, Qiaoqiao She, Hua Wu, Haifeng Wang, Ting Liu

On Safety Risks in Experience-Driven Self-Evolving Agents (2026.findings-acl)

Challenge:	Open-domain question answering is a task that requires answering questions based on a collection of document images.
Approach:	They propose to use document images to answer questions using layouts and visual features instead of text.
Outcome:	The proposed approach reduces human cost and improves scalability of QA systems by incorporating layouts and visual features.

Copied to clipboard

Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, Hao He, Wanxiang Che, Bing Qin, Ting Liu

Challenge:	Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks.
Approach:	They investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments.
Outcome:	The findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation.

MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Multilinguality

Challenge:	Existing preference learning methods for safety alignment are monolingual and struggle with noisy multilingual data.
Approach:	They propose a multilingual reward gaP optimization approach that leverages the well-aligned safety capabilities of the dominant language to improve safety alignment across multiple languages.
Outcome:	Extensive experiments on three LLMs, LLaMA-3.1, Gemma-2 and Qwen2.5, validate MPO’s efficacy in multilingual safety alignment without degrading general multilingual utility.

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training (2022.findings-emnlp)

Copied to clipboard

Qi Shi, Qian Liu, Bei Chen, Yu Zhang, Ting Liu, Jian-Guang Lou

Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild (2024.acl-long)

Challenge:	Existing approaches to language-based environment manipulation are difficult to generalize across environments.
Approach:	They propose a general framework for language-based environment manipulation tasks that can deal with various environments using the same generative language model.
Outcome:	The proposed framework achieves new state-of-the-art results on four of the tasks and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.

Copied to clipboard

Ting Wu, Jingyi Liu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

A Multi-Modal Knowledge Graph for Classical Chinese Poetry (2022.findings-emnlp)

Challenge:	Existing methods for continual relation extraction (CRE) excel in preserving old knowledge but falter when confronted with contaminated data streams.
Approach:	They propose a noise-resistant contrastive framework for continual relation extraction (CRE) that preserves old knowledge while learning incremental corrupted relations.
Outcome:	The proposed framework outperforms state-of-the-art methods on various benchmarks with increasing noise rates.

Copied to clipboard

Yuqing Li, Yuxin Zhang, Bin Wu, Ji-Rong Wen, Ruihua Song, Ting Bai

SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework (2026.acl-long)

Challenge:	Existing studies in classical Chinese poetry area focus on generation and analysis of poetry.
Approach:	They propose to integrate the visual information of words in classical Chinese poetry into a multi-modal knowledge graph.
Outcome:	The proposed model bridges the semantic gap between two modalities and achieves state-of-the-art performance on the poetry-image retrieval task.

Copied to clipboard

Chengran Yang, Ting Zhang, Jinfeng Jiang, Xin Zhou, Haoye Tian, Mingzhe Du, Jieke Shi, Junkai Chen, Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, David Lo

LogRules: Enhancing Log Analysis Capability of Large Language Models through Rules (2025.findings-naacl)

Challenge:	Existing methods for automating vulnerability repair suffer from syntactic overfitting . nvd published 49,230 Common Vulnerabilities and Exposures (CVE) records in 2025 alone .
Approach:	They propose a semantic-aware reward framework that optimizes for code semantic equivalence rather than lexical mimicry.
Outcome:	The proposed framework outperforms state-of-the-art frameworks on repository-level splits . it incorporates expert-aligned reasoning mechanism that grounds patch generation in structured diagnosis.

Copied to clipboard

Xin Huang, Ting Zhang, Wen Zhao

CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China (2025.emnlp-main)

Challenge:	Existing large language models (LLMs) exhibit hallucinations when analyzing logs due to the implicit knowledge and rules in logs that LLMs cannot capture.
Approach:	They propose a lightweight log analysis framework that generates and utilizes rules through LLMs.
Outcome:	The proposed framework outperforms LLM-based methods in log parsing and anomaly detection tasks and achieves better performance compared to case-based approaches.

Copied to clipboard

Guixian Xu, Zeli Su, Ziyin Zhang, Jianing Liu, Xu Han, Ting Zhang, Yushuang Dong

Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction (2022.acl-long)

Challenge:	Minority languages in China face significant challenges due to their unique writing systems, which differ from international standards.
Approach:	They propose a dataset specifically curated for headline generation tasks for minority languages in China . they propose 50,000 entries each for Uyghur and Mongolian, and a test set annotated by native speakers .
Outcome:	The proposed dataset will help improve headline generation in minority languages . it includes 100,000 entries for Tibetan, 50,000 entries each for Uyghur and Mongolian .

Copied to clipboard

Kunyuan Pang, Haoyu Zhang, Jie Zhou, Ting Wang

Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog (2020.acl-main)

Challenge:	Existing FET noise learning methods rely on prediction distributions in instance-independent manner, which causes confirmation bias.
Approach:	They propose a clustering-based loss correction framework to address confirmation bias in FET . they first train a coarse backbone model as a feature extractor and noise estimator .
Outcome:	The proposed framework achieves the best performance over existing systems on three public datasets and is stable to hyperparameters.

Copied to clipboard

Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu

Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting (2021.findings-emnlp)

Challenge:	Recent studies show remarkable success in end-to-end task-oriented dialog systems . however, most models rely on large training data, which is difficult to scalable for new domains with limited labeled data.
Approach:	They propose a shared-private network which exploits the relevance between the target domain and each domain.
Outcome:	The proposed model outperforms existing methods on multi-domain dialogue by 13.9% on average.

Copied to clipboard

Yi Feng, Ting Wang, Chuanyi Li, Vincent Ng, Jidong Ge, Bin Luo, Yucheng Hu, Xiaopeng Zhang

Information Retrieval

Challenge:	a method for user targeting is developed to identify online users to whom an ad should be targeted.
Approach:	They propose a method for automatic augmentation of positive and negative clickthrough data for user targeting models.
Outcome:	The proposed method can increase positive and negative instances of positive training instances on two datasets.

Retrieval-Enhanced Adversarial Training for Neural Response Generation (P19-1)

Copied to clipboard

Qingfu Zhu, Lei Cui, Wei-Nan Zhang, Furu Wei, Ting Liu

FAER: Benchmarking VLMs for Failure-Aware Embodied Reasoning (2026.findings-acl)

Challenge:	Existing approaches to dialogue systems are labor-intensive and difficult to scale up.
Approach:	They propose a Retrieval-Enhanced Adversarial Training method for neural response generation that leverages an adversarial training paradigm while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator.
Outcome:	The proposed method outperforms the vanilla Seq2Seq model and conventional adversarial training approach on a large scale dataset.

Copied to clipboard

Hao Song, Kaifeng Liu, Yuanxing Liu, Xiang Tian, Xuesong Wang, Chen Yifan, Weinan Zhang, Ting Liu

Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization (2023.findings-acl)

Challenge:	Visual-language models (VLMs) are the core component of embodied agents in perceiving the environment and making decisions.
Approach:	They propose a failure-aware benchmark to evaluate the performance of visual language models (VLMs) in long-horizon tasks.
Outcome:	The proposed benchmark evaluates the performance of 16 widely utilized VLMs and 4 LLMs for FAER tasks.

Copied to clipboard

Ting Wu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Robustness in NLP

Challenge:	Existing methods for minimizing the worst-case loss of annotated groups are lacking in practice due to expensive annotations and privacy issues.
Approach:	They propose a distributionally robust optimization framework that relaxes group identification into direct parameterization by using an interactive training mode.
Outcome:	The proposed method outperforms state-of-the-art methods on synthetic and real-world text classification tasks.

BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data (2021.acl-long)

Copied to clipboard

Haoyu Song, Yan Wang, Kaiyan Zhang, Wei-Nan Zhang, Ting Liu

What Did You Refer to? Evaluating Co-References in Dialogue (2021.findings-acl)

Challenge:	Existing persona-based dialogue models use crowd-sourced data, such as the PersonaChat . however, the cost of such datasets is limited, and the model is not robust.
Approach:	They propose to disentangle persona-based dialogue generation into two sub-tasks by using a BERT-over-BERT model.
Outcome:	The proposed model outperforms baselines in response quality and persona consistency under different limited data settings.

Copied to clipboard

Wei-Nan Zhang, Yue Zhang, Hanlin Tang, Zhengyu Zhao, Caihai Zhu, Ting Liu

Natural Language Interfaces

Challenge:	Existing neural end-to-end dialogue models have limitations on exactly interpreting the linguistic structures in dialogue history context.
Approach:	They propose to directly measure the capability of neural end-to-end dialogue models on understanding the entity-oriented structures via question answering.
Outcome:	The proposed model can understand large-scale English and Chinese human human dialogues using a large-format dataset.

All Information is Valuable: Question Matching over Full Information Transmission Network (2022.findings-naacl)

Copied to clipboard

Le Qi, Yu Zhang, Qingyu Yin, Guidong Zheng, Wen Junjie, Jinlong Li, Ting Liu

RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict (2024.lrec-main)

Challenge:	Existing methods for question matching only transmit one kind of information while failing to utilize both kinds of information simultaneously.
Approach:	They propose a question matching network that can transmit both representation and interactive information together in a simultaneous fashion.
Outcome:	The proposed approach outperforms strong baseline models on two standard benchmarks.

Copied to clipboard

Yirong Zeng, Xiao Ding, Yi Zhao, Xiangyu Li, Jie Zhang, Chao Yao, Ting Liu, Bing Qin

Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation (2024.emnlp-main)

Challenge:	Existing methods to verify factuality of claims do not provide sufficient evidence for explainable fact-checking systems.
Approach:	They propose a method to automatically retrieve and summarize evidence from the Web and a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022.
Outcome:	The proposed method can retrieve and summarize evidence from the Web and generate explanations in 16 languages.

Copied to clipboard

Ruiyu Xiao, Lei Wu, Yuhang Gou, Weinan Zhang, Ting Liu

Challenge:	Existing arguments generation methods often overlook connections between opinions . Existing methods struggle with providing compelling proof .
Approach:	They propose a two-stage framework for argumentative essay generation with a focus on logical enhancement.
Outcome:	The proposed framework generates argumentative essays with better logical validity and persuasiveness than baseline models.

One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit (2025.acl-long)

Copied to clipboard

Weitao Ma, Xiyuan Du, Xiaocheng Feng, Lei Huang, Yichong Huang, Huiyi Zhang, Xiaoliang Yang, Baohang Li, Xiachong Feng, Ting Liu, Bing Qin

Green & Sustainable NLP

Challenge:	Existing methods for modifying large language models focus on individual models, resulting in errors and hallucinations.
Approach:	They propose an ensemble-based approach that employs a plug-in model as the editing module and a dynamic weight mechanism to enhance its effectiveness.
Outcome:	The proposed approach outperforms existing methods while achieving superior editing efficiency.

PromptBERT: Improving BERT Sentence Embeddings with Prompts (2022.emnlp-main)

Copied to clipboard

Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang

Context-Sensitive Generation of Open-Domain Conversational Responses (C18-1)

Challenge:	Existing research shows that BERT and RoBERTa are poor in sentence embeddings due to static token embeddable bias and ineffective BERT layers.
Approach:	They propose a novel contrastive learning method for better sentence embeddings by using a template denoising technique.
Outcome:	The proposed method achieves 2.29 and 2.58 points of improvement compared to SimCSE and RoBERTa in the unsupervised setting.

Copied to clipboard

Weinan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, Ting Liu

FTibSuite: A Comprehensive Resource Suite for Tibetan Vision–Language Modeling (2026.findings-acl)

Challenge:	Existing studies on single-turn conversation generation focus on coherence and context-sensitive generation of open-domain conversational responses.
Approach:	They propose static and dynamic attention based approaches for context-sensitive generation of open-domain conversational responses.
Outcome:	The proposed model outperforms all baselines on automatic and human evaluation on two public datasets.

Copied to clipboard

Guixian Xu, Yide Liang, Zeli Su, Xuexian Song, Ziyin Zhang, Yushuang Dong, Ting Zhang, Xu Han

PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning (2024.naacl-long)

Challenge:	FTibSuite provides an end-to-end training-and-evaluation workflow for vision–language models . Tibetan is underserved due to the lack of infrastructure for reproducible training and evaluation.
Approach:	They propose a resource-centric workflow for Tibetan VLMs that provides an end-to-end training-and-evaluation workflow and human-verified multimodal annotations.
Outcome:	FTibSuite provides an end-to-end training-and-evaluation workflow and human-verified multimodal annotations.

Copied to clipboard

Tianrong Zhang, Zhaohan Xi, Ting Wang, Prasenjit Mitra, Jinghui Chen

Profile Consistency Identification for Open-domain Dialogue Agents (2020.emnlp-main)

Challenge:	Existing studies have shown that pre-trained language models can be backdoored such that model behavior is manipulated when trigger tokens are presented.
Approach:	They propose a backdoor mitigation strategy for NLP models via adversarial prompt-tuning in few-shot settings that uses two extra sets of soft tokens which approximate the trigger and counteract it respectively.
Outcome:	The proposed method keeps model parameters intact and only utilizes two extra sets of soft tokens which approximate the trigger and counteract it respectively.

Copied to clipboard

Haoyu Song, Yan Wang, Wei-Nan Zhang, Zhengyu Zhao, Ting Liu, Xiaojiang Liu

FastSeq: Make Sequence Generation Faster (2021.acl-demo)

Challenge:	Existing studies on improving attribute consistency focus on incorporating attribute information in responses, but few efforts have identified the consistency relations between response and attribute profile.
Approach:	They propose a key-value structure information enriched BERT model to identify the profile consistency . they propose to incorporate attribute information into the generated responses .
Outcome:	The proposed model improves over strong baselines on downstream tasks.

Copied to clipboard

Yu Yan, Fei Hu, Jiusheng Chen, Nikhil Bhendawade, Ting Ye, Yeyun Gong, Nan Duan, Desheng Cui, Bingyu Chi, Ruofei Zhang

Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation (2025.acl-long)

Challenge:	Transformer-based models have made tremendous impact in natural language generation, but inference speed is still a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process.
Approach:	They propose an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O to accelerate sequence generation without loss of accuracy.
Outcome:	The proposed framework can accelerate the sequence generation by 4x to 9x with a simple one-line code change for a set of widely used and diverse models.

Copied to clipboard

Guofu Xie, Xiao Zhang, Ting Yao, Yunsheng Shi

Green & Sustainable NLP

Challenge:	Existing approaches focus on merging language models tuned on single objectives . existing approaches ignore the impacts of competing objectives on model tuning .
Approach:	They propose a model merging approach that seeks a series of backbone models and merges them according to user preferences.
Outcome:	The proposed approach exhibits strong controllability and Pareto optimality in controllable multi-objective generation.

Weakly Supervised Semantic Parsing by Learning from Mistakes (2021.findings-emnlp)

Copied to clipboard

Jiaqi Guo, Jian-Guang Lou, Ting Liu, Dongmei Zhang

Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation (2020.acl-main)

Challenge:	Weakly supervised semantic parsing requires searching consistent logical forms in a huge space and dealing with spurious logical form.
Approach:	They propose a learning framework that trains parsers via utterance-denotation pairs . they use utterrance-logical form pairs created from mistakes to bootstrap parser .
Outcome:	The proposed framework outperforms state-of-the-art methods on WikiSQL, TabFact and other datasets.

Copied to clipboard

Haoyu Song, Yan Wang, Wei-Nan Zhang, Xiaojiang Liu, Ting Liu

Counterfactual Off-Policy Training for Neural Dialogue Generation (2020.emnlp-main)

Challenge:	Existing persona-based dialogue models generate human-like responses but can hardly avoid the generation of inconsistent persona words.
Approach:	They propose a framework that deletes inconsistent words from a generated response prototype and further rewrites it to a personality-consistent one.
Outcome:	The proposed framework achieves good performance on the persona-chat dataset.

Copied to clipboard

Qingfu Zhu, Wei-Nan Zhang, Ting Liu, William Yang Wang

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)

Challenge:	Existing models for open-domain dialogue generation suffer from data insufficiency . a potential response inferred in hindsight is called a counterfactual reasoning .
Approach:	They propose to explore potential responses by counterfactual reasoning . given an observed response, the model automatically infers the outcome of an alternative policy that could have been taken .
Outcome:	The proposed model outperforms the HRED model and conventional learning frameworks on the DailyDialog dataset.

Copied to clipboard

Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Neural Stylistic Response Generation with Disentangled Latent Variables (2021.acl-long)

Challenge:	Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs.
Approach:	They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics.
Outcome:	The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility.

Copied to clipboard

Qingfu Zhu, Wei-Nan Zhang, Ting Liu, William Yang Wang

BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation (2024.acl-long)

Challenge:	Existing parallel datasets for creating stylistic responses are not stylistically consistent.
Approach:	They propose to disentangle the content and style in latent space by diluting sentence-level information in style representations.
Outcome:	The proposed approach achieves a higher BERT-based style intensity score and comparable BLEU scores, compared with baselines.

Copied to clipboard

DaYou Du, Yijia Zhang, Shijie Cao, Jiaqi Guo, Ting Cao, Xiaowen Chu, Ningyi Xu

Learning Target-Specific Representations of Financial News Documents For Cumulative Abnormal Return Prediction (C18-1)

Challenge:	Weight quantization has emerged as a popular solution to reduce memory and computational demands.
Approach:	They propose a framework that synergizes Quantization-Aware Training (QAT) with Knowledge Distillation (KD) to boost the performance of LLMs at sub-4-bit.
Outcome:	The proposed framework outperforms existing QAT methods on language understanding and complex reasoning benchmarks on sub-4-bit models.

Copied to clipboard

Junwen Duan, Yue Zhang, Xiao Ding, Ching-Yun Chang, Ting Liu

Representation Learning

Challenge:	Recent work considers learning dense representations for news titles and abstracts . text representations can address the sparsity of discrete indicators in statistical models .
Approach:	They propose to use news abstracts to combine the most informative sentences in news content to learn dense representations for text elements.
Outcome:	The proposed model can be used to estimate abnormal returns of companies when compared to titles and abstracts.

Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification (2021.emnlp-main)

Copied to clipboard

Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu

Com2 : A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models (2025.acl-long)

Challenge:	Existing methods leverage programs that contain rich logical information to enhance the verification process.
Approach:	They propose a table-based fact verification task as an evidence retrieval framework . they retrieve logic-level program-like evidence from the given table and a statement as supplementary evidence for the table .
Outcome:	The proposed method is able to retrieve logic-level program-like evidence from a table and a statement as supplementary evidence for the table.

Copied to clipboard

Kai Xiong, Xiao Ding, Yixin Cao, Yuxiong Yan, Li Du, Yufei Zhang, Jinglong Gao, Jiaqian Liu, Bing Qin, Ting Liu

AFPQ: Asymmetric Floating Point Quantization for LLMs (2024.findings-acl)

Challenge:	Existing works focus on complex tasks like math and code, while complex commonsense reasoning remains underexplored due to its uncertainty and lack of structure.
Approach:	They propose to build a benchmark for large language models based on complex commonsense reasoning based upon causal event graphs and causal theory.
Outcome:	The proposed benchmark combines a complex commonsense reasoning benchmark with a detective story to achieve a more challenging subset.

Copied to clipboard

Yijia Zhang, Sicheng Zhang, Shijie Cao, DaYou Du, Jianyu Wei, Ting Cao, Ningyi Xu

STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing (2022.emnlp-main)

Challenge:	Low-bit weight quantization can save memory and accelerate inference.
Approach:	They propose asymmetric FP quantization which sets separate scales for positive and negative values.
Outcome:	The proposed method leads to large accuracy improvements and can be easily plugged into other quantization methods, including GPTQ and AWQ, for better performance.

Copied to clipboard

Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu

Deep Reinforcement Learning for Chinese Zero Pronoun Resolution (P18-1)

Challenge:	Existing work to mitigate the effect of noisy labels is limited to specific tasks or training procedures, making it hard to be widely used.
Approach:	They propose a stochastic tailor-made gradient noise to mitigate the effect of noisy labels by introducing benign noise into stochistic gradient descent.
Outcome:	The proposed method can be used to discriminate correct samples from incorrect ones and boost existing training methods.

Copied to clipboard

Qingyu Yin, Yu Zhang, Wei-Nan Zhang, Ting Liu, William Yang Wang

NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing (2023.findings-acl)

Challenge:	Recent models for zero pronoun resolution in Chinese are short-sighted and do not capture semantic information for zeros and candidate antecedents.
Approach:	They propose to integrate a deep reinforcement learning approach to Chinese zero pronoun resolution.
Outcome:	The proposed approach outperforms the state-of-the-art methods in three experimental settings.

Copied to clipboard

Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang, Bing Qin, Ting Liu

Challenge:	Large-scale datasets in the real world often contain label noise, which can cause model overfitting and degrade generalization.
Approach:	They propose to use label noise to imitate human errors in annotations . they use a noisy label noise benchmark to evaluate their methods .
Outcome:	The proposed benchmarks are different from data with heterogeneous label noises in the real world.

SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications (D18-1)

Copied to clipboard

Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang

Nullspace Disentanglement for Red Teaming Language Models (2025.emnlp-main)

Challenge:	Existing approaches to generate programs from natural language do not address program aliasing . semantically equivalent programs may have many syntactically different forms .
Approach:	They propose a semantics-based approach to generate regular expressions from natural language.
Outcome:	The proposed approach improves on three public datasets.

Copied to clipboard

Yi Han, Yuanxing Liu, Weinan Zhang, Ting Liu

Exploring and Distilling Multi-Dimensional Clues for Interpretable Social Bot Detection (2026.acl-long)

Challenge:	Existing work mainly leverages crowd workers to construct test cases.
Approach:	They propose a black-box approach that exploits the unique properties of the nullspace to disentangle and regulate the crucial success information within test cases.
Outcome:	The proposed approach outperforms baseline methods regarding the attack success rate and excels in aspects of diversity and fluency.

Copied to clipboard

Yi Han, Haiqi Lu, Lizi Liao, Shuhan Zhou, Yuanxing Liu, Weinan Zhang, Ting Liu

A Compare Aggregate Transformer for Understanding Document-grounded Dialogue (2020.findings-emnlp)

Challenge:	Existing research on social bot detection results directly without corresponding supportive explanations, making it difficult to assess the extent to which such predictions are trustworthy.
Approach:	They propose a four-dimensional clue framework that uses outcome-reward reinforcement learning to train inspectors to generate faithful, grounded clues from user information, semantic features, interactive situation, and behavioral pattern.
Outcome:	The proposed framework outperforms baselines in detection performance and significantly improves the performance of large language models.

Copied to clipboard

Longxuan Ma, Wei-Nan Zhang, Runxin Sun, Ting Liu

Online Iterative Self-Alignment for Radiology Report Generation (2025.acl-long)

Challenge:	Existing studies have focused on KS in unstructured documents, but dialogue history that is not related to the current dialogue may introduce noise in the KS processing.
Approach:	They propose a Compare Aggregate Transformer to jointly denoise the dialogue context and aggregate the document information for response generation.
Outcome:	The proposed model outperforms the state-of-the-art approach and strong baselines on a CMU_DoG dataset.

Copied to clipboard

Ting Xiao, Lei Shi, Yang Zhang, HaoFeng Yang, Zhe Wang, Chenjia Bai

A Graph Enhanced BERT Model for Event Prediction (2022.findings-acl)

Challenge:	Existing methods for RRG rely on supervised fine-tuning based on data pairs of radiological images and corresponding radiologist-annotated reports.
Approach:	They propose a method that performs supervised fine-tuning on data pairs of radiological images and corresponding radiologist-annotated reports.
Outcome:	The proposed method surpasses existing methods and achieves state-of-the-art performance across multiple evaluation metrics.

Copied to clipboard

Li Du, Xiao Ding, Yue Zhang, Ting Liu, Bing Qin

Structured Data in NLP

Challenge:	Existing methods to predict subsequent events use sparsity of event graph to improve performance.
Approach:	They propose to automatically build event graph using a BERT model by adding a structured variable to the model to learn to predict event connections.
Outcome:	The proposed model outperforms state-of-the-art models on two event prediction tasks.

Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification (2020.coling-main)

Copied to clipboard

Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu

Process-Supervised Reinforcement Learning for Code Generation (2025.emnlp-main)

Challenge:	Existing methods for fact verification lack attention to combine linguistic and symbolic information.
Approach:	They propose a graph-based reasoning approach that learns to combine linguistic and symbolic information effectively.
Outcome:	The proposed method can combine linguistic and symbolic information effectively.

Copied to clipboard

Yufan Ye, Ting Zhang, Wenbin Jiang, Hua Huang

Programming Languages in NLP

Challenge:	Existing reinforcement learning strategies based on outcome supervision have shown effectiveness in code generation tasks, but their effectiveness in the field of code generation remains limited.
Approach:	They propose a method that uses a teacher model to mutate and refactor statements and a compiler to automatically label them.
Outcome:	The proposed method improves performance in complex code generation tasks.

Prompt Combines Paraphrase: Teaching Pre-trained Models to Understand Rare Biomedical Words (2022.coling-1)

Copied to clipboard

Haochun Wang, Chi Liu, Nuwa Xi, Sendong Zhao, Meizhi Ju, Shiwei Zhang, Ziheng Zhang, Yefeng Zheng, Bing Qin, Ting Liu