Papers by Ting 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

Responsible & Trustworthy NLP

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.

Bridging the Memorization-Utilization Gap: Near-Lossless Context Compression via Reinforcement Learning (2026.acl-long)

Copied to clipboard

Yujan Ting, Xu Tang, Terrence Chen, Weijing Huang

Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training (2021.emnlp-main)

Challenge:	Recent advances in context compression have failed to effectively utilize compressed representations for downstream tasks.
Approach:	They propose a holistic training paradigm that uses outcome-based RL to enable implicit expansion.
Outcome:	The proposed model outperforms previous models on NIAH, LongBench and multi-hop reasoning.

Copied to clipboard

Bo Zheng, Li Dong, Shaohan Huang, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei

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

Challenge:	Existing models require a more expressive vocabulary to represent all languages . however, increasing the vocabulary size significantly slows down the pre-training speed .
Approach:	They propose an algorithm VoCap to determine the desired vocabulary capacity of each language.
Outcome:	The proposed algorithm improves cross-lingual model pre-training while reducing side effects of increasing vocabulary size.

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.

Scaling Sentence Embeddings with Large Language Models (2024.findings-emnlp)

Copied to clipboard

Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, Fuzhen Zhuang

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

Challenge:	Current methods based on contrastive learning have generated high-quality sentence embeddings.
Approach:	They propose a method to enhance LLM performance on sentence embeddings with a one-word limitation.
Outcome:	The proposed method outperforms contrastive learning methods on sentence embeddings without fine-tuning and with fine-untun.

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.

A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction (2020.acl-main)

Copied to clipboard

Yilin Niu, Fangkai Jiao, Mantong Zhou, Ting Yao, Jingfang Xu, Minlie Huang

From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems (2025.findings-emnlp)

Challenge:	Existing models for machine reading comprehension lack evidence labels for training models.
Approach:	They propose a method which supervises the evidence extractor with auto-generated evidence labels in an iterative process.
Outcome:	The proposed method improves on three MRC tasks on seven datasets.

Copied to clipboard

Zekun Zhou, Xiaocheng Feng, Lei Huang, Xiachong Feng, Ziyun Song, Ruihan Chen, Liang Zhao, Weitao Ma, Yuxuan Gu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

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

Challenge:	rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance research.
Approach:	They organize the relevant studies into three main categories: hypothesis formulation, hypothesis validation, and manuscript publication.
Outcome:	The authors summarize the current state of research in three main areas: hypothesis formulation, hypothesis validation, and manuscript publication.

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.

Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin

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

Challenge:	Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach:	They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome:	The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.

Copied to clipboard

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

Aligning Translation-Specific Understanding to General Understanding in Large Language Models (2024.emnlp-main)

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

Yichong Huang, Baohang Li, Xiaocheng Feng, Wenshuai Huo, Chengpeng Fu, Ting Liu, Bing Qin

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

Challenge:	Large Language models (LLMs) have remarkable abilities in understanding complex texts . however, understanding misalignment leads to LLMs mistakenly translating complex concepts .
Approach:	They propose a translation process that aligns the translation-specific understanding with the general understanding to improve translation quality and reduce translation literalness.
Outcome:	The proposed translation process improves translation quality and reduces translation literalness by -25% -51%.

Copied to clipboard

Xin Huang, Ting Zhang, Wen Zhao

Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction (2025.findings-naacl)

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

ShengbinYue ShengbinYue, Ting Huang, Zheng Jia, Siyuan Wang, Shujun Liu, Yun Song, Xuanjing Huang, Zhongyu Wei

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

Challenge:	Large Language Models (LLMs) have advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios.
Approach:	They propose a Multi-agent Legal Simulation Driver to generate synthetic data by simulating interactive legal scenarios.
Outcome:	The proposed framework ensures consistency of legal attributes between participants and introduces a supervisory mechanism to align participants’ characters and behaviors as well as addressing distractions.

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.

CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain? (2026.acl-long)

Copied to clipboard

Peiyu Li, Xiaobao Huang, Ting Hua, Nitesh V Chawla

Multimodality

Challenge:	Existing multimodal large language models cannot generate executable procedures . authors propose a new benchmark to assess procedural competence in multimodal models .
Approach:	They propose a new benchmark to assess procedural competence in multimodal large language models . they use a CrochetPARADE DSL representation to enable structural validation and functional evaluation .
Outcome:	The proposed model enables structural validation and functional evaluation via execution.

Task-oriented Dialogue System for Automatic Diagnosis (P18-2)

Copied to clipboard

Zhongyu Wei, Qianlong Liu, Baolin Peng, Huaixiao Tou, Ting Chen, Xuanjing Huang, Kam-fai Wong, Xiangying Dai

Natural Language Interfaces

Challenge:	Existing methods to identify phenotypes using electronic health records (EHRs) are expensive and difficult to transfer models from one disease to another.
Approach:	They propose a task-oriented dialogue system framework to make diagnosis for patients automatically, which can converse with patients to collect additional symptoms beyond their self-reports.
Outcome:	The proposed system can collect additional symptoms from conversation and improve disease identification accuracy.

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.

Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

Copied to clipboard

Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Challenge:	Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach:	They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome:	The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.

Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations (2023.findings-emnlp)

Copied to clipboard

Chengpeng Fu, Xiaocheng Feng, Yichong Huang, Wenshuai Huo, Hui Wang, Bing Qin, Ting Liu

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

Challenge:	Unsupervised neural machine translation methods have been observed to make particular errors in comparison to supervised machine translation, such as confusing nouns that pertain to the same semantic category.
Approach:	They propose a method that incorporates images at the word level to augment lexical mappings.
Outcome:	Experiments on a multi-lingual dataset show that the proposed method generates more accurate translations with only monolingual data.

Copied to clipboard

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

Length Controlled Generation for Black-box LLMs (2025.acl-long)

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

Yuxuan Gu, Wenjie Wang, Xiaocheng Feng, Weihong Zhong, Kun Zhu, Lei Huang, Ting Liu, Bing Qin, Tat-Seng Chua

Responsible & Trustworthy NLP

Challenge:	Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use.
Approach:	They propose an iterative sampling framework that regulates LLMs to generate length-constrained text without modifying the underlying parameters.
Outcome:	The proposed method achieves 100% success rates on Llama3.1 tasks with minimal additional computational overhead.

Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions (2025.findings-emnlp)

Copied to clipboard

Yue Qiu, Yujan Ting, Pei Dong, Terrence Chen, Weijing Huang

Question Answering

Challenge:	Reinforcement learning (RL) for large language models typically requires clear reward signals, which are often unavailable for open-ended (OE) questions where answer evaluation is ambiguous without scalable expert labeling.
Approach:	They propose a mixed-data approach to training large language models with varying reward clarity . they combine Multiple-choice questions (MCQs) with OE questions for which they use simpler, potentially noisy rewards such as Jaccard similarity or LLM-based evaluators.
Outcome:	The mixed-data approach improves medical question-answering performance across model scales.

LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models (2025.emnlp-industry)

Copied to clipboard

Hieu Tran, Junda Wang, Yujan Ting, Hong Yu, Weijing Huang, Terrence Chen

Ethical NLP

Challenge:	Large language models (LLMs) struggle with factual accuracy in knowledge-intensive domains like healthcare.
Approach:	They propose a framework for improving LLM factuality in medical question answering . RAFE, Fact-Check-then-RAG and Learning from Fact Check are components .
Outcome:	Experimental results show that LEAF outperforms Factcheck-GPT in detecting inaccuracies and corrects errors without labeling . the framework provides a scalable solution for industrial applications requiring high factuality scores.

SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation (2025.findings-acl)

Copied to clipboard

Ting Xu, Zhichao Huang, Jiankai Sun, Shanbo Cheng, Wai Lam

Machine Translation

Challenge:	SeqPO-SiMT is a new policy optimization framework for simultaneous machine translation that combines a tailored reward with a single step task.
Approach:	They propose a new policy optimization framework that defines the simultaneous machine translation task as a sequential decision making problem with a tailored reward.
Outcome:	The proposed framework outperforms the supervised fine-tuning model by 1.13 points while reducing the Average Lagging by 6.17 in the NEWSTEST2021 En Zh dataset.

Consistency Regularization for Cross-Lingual Fine-Tuning (2021.acl-long)

Copied to clipboard

Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use (2025.emnlp-main)

Challenge:	Experimental results show that consistency regularization improves cross-lingual fine-tuning . pre-trained cross-linguistic models can transfer task-specific supervision from one language to the other .
Approach:	They propose to improve cross-lingual fine-tuning with consistency regularization . they use example consistency regularized to penalize prediction sensitivity to four types of data augmentations .
Outcome:	The proposed method improves cross-lingual fine-tuning across tasks . it can be generalized to other target languages without additional training .

Copied to clipboard

Yirong Zeng, Xiao Ding, Yuxian Wang, Weiwen Liu, Yutai Hou, Wu Ning, Xu Huang, Duyu Tang, Dandan Tu, Bing Qin, Ting Liu

Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation (2023.acl-long)

Challenge:	Synthesizing tool-use data through real-world simulations is effective for enhancing large language models (LLMs) however, training gains decay as synthetic data increases, and the model struggles to benefit from more synthetic data.
Approach:	They propose an iterative reinforced fine-tuning strategy to improve LLMs with external tools to augment their capabilities.
Outcome:	The proposed method achieves 13.11% better performance than the same-size base model and outperforms larger open-source and closed-source models.

Copied to clipboard

Kaiyu Huang, Peng Li, Jin Ma, Ting Yao, Yang Liu

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

Challenge:	Existing studies focus on overcoming catastrophic forgetting on original language pairs while lacking encouragement to learn new knowledge from incremental learning.
Approach:	They propose a knowledge transfer method that can adapt original MNMT models to diverse incremental language pairs by flexibly introducing knowledge from external models into original models, which encourages the models to learn new language pairs.
Outcome:	The proposed method outperforms baselines on multiple languages while maintaining performance on original language pairs.

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.

FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging (2025.findings-emnlp)

Copied to clipboard

Zijian Li, Xiaocheng Feng, Huixin Liu, Yichong Huang, Ting Liu, Bing Qin