Papers by Zhiyu Chen

S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)

Challenge:	Existing approaches to CQA involve training new models from scratch . existing approaches are expensive and often not feasible .
Approach:	They propose to use QA feedback to supervise the rewriting model with reinforcement learning.
Outcome:	The proposed model can improve QA performance over baselines for extractive and retrieval QA.

Copied to clipboard

Feng Jiang, Zhiyu Lin, Yiyang Liu, Liumeng Xue, Fan Bu, Yuhao Du, Xiangying Chen, Benyou Wang, Haizhou Li

TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance Detection (2026.acl-long)

Challenge:	Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits.
Approach:	They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression.
Outcome:	The proposed system enables more natural, robust, and human-aligned speech agents.

Copied to clipboard

Fuqiang Niu, Zini Chen, Zhiyu Xie, Hu Huang, Qing Liao, Qianlong Wang, Genan Dai, Bowen Zhang

Sentiment Analysis

Challenge:	Existing benchmarks for political user-level stance detection rely on noisy heuristics or distant supervision.
Approach:	They propose a large-scale, expert-annotated benchmark for political user-level stance detection with explicit social network structure that integrates user content and followee signals.
Outcome:	The proposed framework outperforms baselines in terms of quality and reliability.

InstructPTS: Instruction-Tuning LLMs for Product Title Summarization (2023.emnlp-industry)

Copied to clipboard

Besnik Fetahu, Zhiyu Chen, Oleg Rokhlenko, Shervin Malmasi

Summarization

Challenge:	E-commerce product catalogs contain billions of items with lengthy titles . this leads to a gap between how customers refer to these unnatural titles - and how they are used .
Approach:	They propose a novel approach to product title summarization that uses a fine-tuned instruction strategy to train a highly accurate model.
Outcome:	The proposed approach can generate more accurate product title summaries with an improvement of over 14 and 8 BLEU and ROUGE points.

Preference Learning Unlocks LLMs’ Psycho-Counseling Skills (2026.findings-acl)

Copied to clipboard

Mian Zhang, Shaun M. Eack, Zhiyu Chen

REIC: RAG-Enhanced Intent Classification at Scale (2025.emnlp-industry)

Challenge:	Current LLMs struggle to consistently provide effective responses to client speeches due to the lack of supervision from high-quality real psycho-counseling data.
Approach:	They propose to use a dataset to evaluate therapists' responses to client speeches using a set of professional and comprehensive principles to evaluate their responses.
Outcome:	The proposed model achieves an impressive win rate of 87% against GPT-4o.

Copied to clipboard

Ziji Zhang, Michael Yang, Zhiyu Chen, Yingying Zhuang, Shu-Ting Pi, Qun Liu, Rajashekar Maragoud, Vy Nguyen, Anurag Beniwal

KPatch: Knowledge Patch to Pre-trained Language Model for Zero-Shot Stance Detection on Social Media (2024.lrec-main)

Challenge:	Accurate intent classification is critical for efficient routing in customer service . however, as companies expand their product lines, intent classification faces scalability challenges .
Approach:	They propose a retrieval-augmented generation Enhanced Intent Classification approach which leverages retrieval augmented generation to integrate relevant knowledge into a model.
Outcome:	The proposed approach outperforms fine-tuning, zero-shot, and few-shot methods on real-world datasets.

Copied to clipboard

Shuohao Lin, Wei Chen, Yunpeng Gao, Zhishu Jiang, Mengqi Liao, Zhiyu Zhang, Shuyuan Zhao, Huaiyu Wan

Semantic Text Processing

Challenge:	Existing knowledge injection methods fail to understand the semantics of tweets .
Approach:	They propose a method to flexibly inject knowledge into a pre-trained language model and adaptively expand tweets context.
Outcome:	The proposed method is based on two training stages to flexibly inject knowledge into the pre-trained language model and adaptively expand tweets context.

CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy (2025.naacl-long)

Copied to clipboard

Mian Zhang, Xianjun Yang, Xinlu Zhang, Travis Labrum, Jamie C. Chiu, Shaun M. Eack, Fei Fang, William Yang Wang, Zhiyu Chen

Large Language Models as Zero-shot Dialogue State Tracker through Function Calling (2024.acl-long)

Challenge:	Existing research has explored mental health condition classifications, empathetic conversations, and chatbots designed for simple discourse structures.
Approach:	They propose a benchmark for systematic evaluation of cognitive behavioral therapy assistance using Large Language Models (LLMs).
Outcome:	The proposed benchmark includes three levels of tasks covering key aspects of cognitive behavioral therapy that could be enhanced through AI assistance.

Copied to clipboard

Zekun Li, Zhiyu Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Dong, Adithya Sagar, Xifeng Yan, Paul Crook

Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers (2024.acl-long)

Challenge:	Large language models (LLMs) are increasingly prevalent in conversational systems due to their advanced understanding and generative capabilities in general contexts.
Approach:	They propose a method for solving dialogue state tracking (DST) with large language models through function calling.
Outcome:	The proposed approach improves zero-shot DST, allowing adaptation to diverse domains without extensive data collection or model tuning.

Copied to clipboard

Lütfi Kerem Senel, Besnik Fetahu, Davis Yoshida, Zhiyu Chen, Giuseppe Castellucci, Nikhita Vedula, Jason Ingyu Choi, Shervin Malmasi

Challenge:	Large Language Models (LLMs) have given rise to generative recommenders . however, improving the generated content through user feedback is prohibitively expensive .
Approach:	They propose a generative explore-exploit method that exploits items with high engagement and actively explores hidden population preferences to improve recommendation quality.
Outcome:	The proposed approach exploits items with high engagement and actively explores hidden population preferences to improve recommendation quality.

Answering Unanswered Questions through Semantic Reformulations in Spoken QA (2023.acl-industry)

Copied to clipboard

Pedro Faustini, Zhiyu Chen, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi

ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks (2025.acl-long)

Challenge:	Question Answering (QA) is a longstanding NLP task, and voice assistants like Alexa have made Spoken QA ubiquitous.
Approach:	They propose a model that uses linguistically-grounded operations to rewrite questions to facilitate answering.
Outcome:	The proposed model improves answer rates on 1M unanswered questions from a leading voice assistant.

Copied to clipboard

Yu Lin, Ruining Yang, Yunlong Mao, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyu Chen, Bing Duan, Sheng Zhong

Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers (2026.findings-acl)

Challenge:	Recent studies show that obfuscation techniques for MLaaS are susceptible to embedding inversion attacks (EIAs).
Approach:	They propose a model obfuscation framework that protects client inputs from embedding inversion attacks by obliviously obbing models.
Outcome:	The proposed framework outperforms existing works in utility by 10% with a nearly 80% resistance rate against embedding inversion attacks.

Copied to clipboard

Kaiyu He, Mian Zhang, Peilin Wu, Xinya Du, Zhiyu Chen

PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check (2021.acl-long)

Challenge:	Large Language Models struggle with the "curse of two-hop reasoning" in compositional tasks.
Approach:	They propose to form a "Generalization Circuit" during a prolonged "grokking" phase . they argue that grokkking is the process of integrating memorized atomic facts into an easy-acquire reasoning path.
Outcome:	The proposed model is superior to non-grokked models, but it requires a large computational cost . the study shows that grokking is not the sudden acquisition of a new reasoning paradigm .

Copied to clipboard

Li Huang, Junjie Li, Weiwei Jiang, Zhiyu Zhang, Minchuan Chen, Shaojun Wang, Jing Xiao

Syntactic Text Processing

Challenge:	False gram and phonological errors make Chinese spelling check difficult . a novel end-to-end trainable model outperforms existing methods .
Approach:	They propose a trainable Chinese spelling check model that integrates phonological and visual information into a pre-trained language model.
Outcome:	The proposed model outperforms existing state-of-the-art models on three benchmarks.

PATIENT-𝜓: Using Large Language Models to Simulate Patients for Training Mental Health Professionals (2024.emnlp-main)

Copied to clipboard

Ruiyi Wang, Stephanie Milani, Jamie Chiu, Jiayin Zhi, Shaun Eack, Travis Labrum, Samuel Murphy, Nev Jones, Kate Hardy, Hong Shen, Fei Fang, Zhiyu Chen

ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering (2022.emnlp-main)

Challenge:	Mental illness remains one of the most critical public health issues.
Approach:	They propose a patient simulation framework for cognitive behavior therapy training that uses large language models to act as a simulated therapy patient.
Outcome:	The proposed framework improves the skill acquisition and confidence of mental health trainees beyond textbooks, videos, and role-play with non-patients.

Copied to clipboard

Zhiyu Chen, Shiyang Li, Charese Smiley, Zhiqiang Ma, Sameena Shah, William Yang Wang

UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions (2025.findings-acl)

Challenge:	Recent advances in large pre-trained language models have brought the NLP field into a new era.
Approach:	They propose a large-scale dataset to study the chain of numerical reasoning in conversational question answering.
Outcome:	The proposed dataset should push forward the exploration of real-world, complex reasoning tasks as the next research focus.

Copied to clipboard

Xunzhi Wang, Zhuowei Zhang, Gaonan Chen, Qiongyu Li, Bitong Luo, Zhixin Han, Haotian Wang, Zhiyu Li, Hang Gao, Mengting Hu

Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branching (2025.acl-long)

Challenge:	Existing methods for benchmarking the uncertainty of large language models face challenges . existing methods require internal model access, additional training, or high computational costs .
Approach:	They propose a new benchmark for evaluating the uncertainty of large language models based on confidence intervals . UBench encompasses 11,978 multiple choice questions spanning knowledge, language, understanding, and reasoning capabilities.
Outcome:	The proposed method outperforms existing methods for benchmarking the uncertainty of large language models.

Copied to clipboard

Xiangci Li, Zhiyu Chen, Jason Ingyu Choi, Nikhita Vedula, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi

Dialogue Systems & Conversational Agents

Challenge:	Prior human-annotated CPS datasets are small in size and lack integration with real-world product search systems.
Approach:	They propose a method to generate target-oriented shopping conversations without human annotations by using large language models.
Outcome:	The proposed method achieves highly natural and coherent conversations from three shopping domains and significantly improves on human evaluations and downstream tasks.

Multimodal Procedural Planning via Dual Text-Image Prompting (2024.findings-emnlp)

Copied to clipboard

Yujie Lu, Pan Lu, Zhiyu Chen, Wanrong Zhu, Xin Wang, William Yang Wang

How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection (N19-1)

Challenge:	Embodied agents have demonstrated performance in following instructions informed by texts and images . however, the potential of models providing useful guidelines for humans to complete tasks remains underexplored .
Approach:	They propose a multimodal procedural planning task that generates paired text-image plans . this task provides more complementary and informative guidance than unimodal plans a . authors propose modality prompting methods that leverage zero-shot reasoning ability .
Outcome:	The proposed method improves the interaction in dual modalities and provides more information than unimodal plans.

Copied to clipboard

Wenhu Chen, Yu Su, Yilin Shen, Zhiyu Chen, Xifeng Yan, William Yang Wang

Information Extraction & Text Mining

Challenge:	Using a pre-defined vocabulary is a common approach to selecting text inputs . however, using a large vocabulary is not economical, as it limits the model's applicability on computation-or memoryconstrained scenarios.
Approach:	They propose a more sophisticated variational vocabulary dropout to perform vocabulary selection . they propose two new metrics to measure area under accuracy-vocab curve and Vocab Size under X% accuracy drop .
Outcome:	The proposed framework outperforms the baselines on the vocabulary selection problem on multiple NLP classification tasks.

LLM-Based Dialogue Labeling for Multiturn Adaptive RAG (2025.emnlp-industry)

Copied to clipboard

Zhiyu Chen, Biancen Xie, Sidarth Srinivasan, Manikandarajan Ramanathan, Rajashekar Maragoud, Qun Liu

Global Textual Relation Embedding for Relational Understanding (P19-1)

Challenge:	Retrieval-Augmented Generation (RAG) models integrate large language models with external knowledge retrieval . however, building multi-turn RAG-based chatbots for real-world customer service requires additional complexities.
Approach:	They propose methods to automatically generate labels for adaptive retrieval components using real customer-agent dialogue data.
Outcome:	The proposed method generates labels for components using real customer-agent dialogue data.

Copied to clipboard

Zhiyu Chen, Hanwen Zha, Honglei Liu, Wenhu Chen, Xifeng Yan, Yu Su

Representation Learning

Challenge:	Existing methods to learn textual relation embeddings are lacking in large open-domain corpora.
Approach:	They propose to learn a general-purpose embedding of textual relations using a large dataset from Freebase.
Outcome:	The proposed embedding can facilitate downstream tasks requiring relational understanding of the text.

Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Copied to clipboard

Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang

ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization (2026.findings-eacl)

Challenge:	Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach:	They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome:	Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.

Copied to clipboard

Sunzhu Li, Zhiyu Lin, Jiale Zhao, Shuling Yang, Chen Wei

A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning (2025.acl-long)

Challenge:	Large Reasoning Models (LRMs) are powerful but still suffer from inefficient and off-target reasoning.
Approach:	They propose a training-free framework that automatically optimizes Large Reasoning Models' reasoning by generating think-prefixes that evolve driven by a taxonomy of reasoning behaviors.
Outcome:	The proposed framework significantly improves accuracy-length trade-off for efficient reasoning, drastically improves safety and improves instruction following.

Copied to clipboard

Zhiyu Zhang, Wei Chen, Youfang Lin, Huaiyu Wan

Structured Data in NLP

Challenge:	Existing Continual Learning (CL)-based Temporal Knowledge Graph Reasoning methods are incomplete and reorganize historical facts without preserving historical knowledge.
Approach:	They propose a method which generates and adaptively replays historical entity distributions from the whole historical context.
Outcome:	The proposed method outperforms baselines in reasoning and mitigating forgetting.

Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting (2023.findings-emnlp)

Copied to clipboard

Zhiyu Chen, Yujie Lu, William Wang

CloneMem: Benchmarking Long-Term Memory for AI Clones (2026.acl-long)

Challenge:	Existing systems for mental health support are shallow and heuristic, e.g., analyzing emotions and generating comforting responses.
Approach:	They propose to use cognitive distortion detection to perform diagnosis on the patient’s speech via three stages: subjectivity assessment to separate the facts and the thoughts; contrastive reasoning to elicit the reasoning processes supporting and contradicting the thoughts and schema analysis to summarize the cognition schemas.
Outcome:	The proposed system improves on ChatGPT for cognitive distortion detection while generating high-quality rationales approved by human experts.

Copied to clipboard

Sen Hu, Zhiyu Zhang, Yuxiang Wei, Xueran Han, Zhenheng Tang, Ronghao Chen, Huacan Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing memory benchmarks rely on user–agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories.
Approach:	They propose a benchmark for evaluating long-term memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years.
Outcome:	Experiments show that existing memory benchmarks struggle in this setting, highlighting open challenges for life-grounded personalized AI.

Text2Mem: A Unified Memory Operation Language for Memory Operating System (2026.findings-acl)

Copied to clipboard

Leo Wang, Lihai Yang, Boyu Chen, Kerun Xu, Gongyi Zou, Bo Tang, Feiyu Xiong, Siheng Chen, Zhiyu li

Challenge:	Existing memory frameworks lack a formal, executable specification for memory control.
Approach:	They propose a unified memory operation language that standardizes translation of natural-language instructions into reliable execution.
Outcome:	The proposed language standardizes translation of natural-language instructions into reliable execution.

MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition (2023.findings-emnlp)

Copied to clipboard

Besnik Fetahu, Zhiyu Chen, Sudipta Kar, Oleg Rokhlenko, Shervin Malmasi

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) is a core task in Natural Language Processing.
Approach:	They present a dataset for fine-grained Named Entity Recognition covering 33 entity classes across 12 languages in monolingual and multilingual settings.
Outcome:	The proposed dataset covers 33 entity classes across 12 languages in monolingual and multilingual settings.

KETOD: Knowledge-Enriched Task-Oriented Dialogue (2022.findings-naacl)

Copied to clipboard

Zhiyu Chen, Bing Liu, Seungwhan Moon, Chinnadhurai Sankar, Paul Crook, William Yang Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing studies treat task-oriented dialogue and chit-chat as separate domains . a new dataset is created to integrate both types of dialogue into a single system .
Approach:	They propose to integrate task-oriented dialogue and knowledge-grounded chit-chat into a single model by using a dataset.
Outcome:	The proposed models improve the performance of knowledge-enriched dialogues while maintaining a competitive task-oriented dialog performance.

Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data (2024.lrec-main)

Copied to clipboard

Parth Patwa, Simone Filice, Zhiyu Chen, Giuseppe Castellucci, Oleg Rokhlenko, Shervin Malmasi

LMR-BENCH: Evaluating LLM Agent’s Ability on Reproducing Language Modeling Research (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks.
Approach:	They propose to make Large Language Models (LLMs) operating in 0-shot or few-shot settings as efficient as 0- shot text classifiers by leveraging a small number of samples.
Outcome:	The proposed model is able to perform better on multiple datasets than existing models on 0-shot or few-shot settings.

Copied to clipboard

Shuo Yan, Ruochen Li, Ziming Luo, Zimu Wang, Daoyang Li, Liqiang Jing, Kaiyu He, Peilin Wu, Juntong Ni, George Michalopoulos, Yue Zhang, Ziyang Zhang, Mian Zhang, Zhiyu Chen, Xinya Du

FinQA: A Dataset of Numerical Reasoning over Financial Data (2021.emnlp-main)

Challenge:	Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery, but their capability in reproducing code from research papers remains underexplored.
Approach:	They propose to evaluate LLM agents' ability to reproduce scientific research papers by analyzing code reproduction tasks from 23 research papers published in top-tier NLP venues.
Outcome:	The proposed benchmark systematically evaluates the capability of large language model (LLM) agents on code reproduction from Language Modeling Research.

Copied to clipboard

Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan Routledge, William Yang Wang

Reasoning

Challenge:	Popular, large, pre-trained models fall far short of expert humans in acquiring finance knowledge and in complex multi-step numerical reasoning on that knowledge.
Approach:	They propose a large-scale dataset with Question-Answering pairs over financial reports written by financial experts to facilitate analytical progress.
Outcome:	The proposed dataset is the first of its kind and is available on github.

NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism (2024.acl-long)

Copied to clipboard

Miao Li, Ming-Bin Chen, Bo Tang, ShengbinHou ShengbinHou, Pengyu Wang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Keming Mao, Cheng Peng, Yi Luo

Semantic Text Processing

Challenge:	a novel evaluation framework assesses the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Approach:	They propose to use a benchmark dataset to assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Outcome:	The proposed evaluation framework is based on a dataset of 1,267 test samples in 24 news domains.

Logic2Text: High-Fidelity Natural Language Generation from Logical Forms (2020.findings-emnlp)

Copied to clipboard

Zhiyu Chen, Wenhu Chen, Hanwen Zha, Xiyou Zhou, Yunkai Zhang, Sairam Sundaresan, William Yang Wang

GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning (2025.acl-long)

Challenge:	Recent studies on Natural Language Generation (NLG) from structured data focus on surface descriptions of simple record sequences, for example, attribute-value pairs of fixed or very limited schema.
Approach:	They propose to use a large-scale dataset to generate NLG from logical forms to obtain controllable and faithful generations from structured data.
Outcome:	The proposed model can describe interesting facts from logical inferences across records, but it is difficult to produce such fidelity.

Copied to clipboard

Qingchen Yu, Zifan Zheng, Ding Chen, Simin Niu, Bo Tang, Feiyu Xiong, Zhiyu Li

Reasoning

Challenge:	Existing evaluation methods for large language models rely on static benchmarks and standardized evaluation protocols.
Approach:	They propose an adaptive evaluation framework that integrates dynamic domain knowledge modeling with progressive reasoning assessment to improve evaluation fidelity.
Outcome:	Empirical results show that the framework distinguishes LLMs in terms of domain knowledge coverage and reasoning chain completeness.

Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography (2026.acl-industry)

Copied to clipboard

Sudharshan Balaji, Zhiyu Liu, Zhengyuan Jiang, Shuo Lei, Yimin Chen, Yang Xiao, Shone O. Almeida, Mathew Joseph Karivelil, Christopher Malanga, Ning Wang

Information Extraction & Text Mining

Challenge:	CCTA reports provide an assessment of coronary disease severity to guide patient management.
Approach:	They propose a pipeline that decouples structuring from classification by an LLM-based parser . CCTA-RADS is the largest publicly available dataset of CCDA reports .
Outcome:	The proposed approach improves the F1-score by 6%-13% compared with direct methods.

Logical Natural Language Generation from Open-Domain Tables (2020.acl-main)

Copied to clipboard

Wenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen, William Yang Wang

NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions (2021.findings-emnlp)

Challenge:	Existing studies on neural natural language generation focus on surface-level realizations with limited emphasis on logical inference.
Approach:	They propose a task where a model is tasked with generating natural language statements that can be logically entailed by facts in an open-domain semi-structured table.
Outcome:	The proposed task is based on the existing TabFact dataset with a wide range of logical/symbolic inferences.

Copied to clipboard

Zhiyu Chen, Honglei Liu, Hu Xu, Seungwhan Moon, Hao Zhou, Bing Liu

IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction (2025.findings-acl)

Challenge:	Existing conversational systems are agent-centric, which assumes the user utterances will closely follow the system ontology.
Approach:	They build a dataset that maps user preferences to an ontology and model user preferences as estimated distributions over the system ontologies.
Outcome:	The proposed system can be used to push existing research from agent-centric to user-centric.

Copied to clipboard

Kaiyu He, Mian Zhang, Shuo Yan, Peilin Wu, Zhiyu Chen

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty (2025.emnlp-main)

Challenge:	RULEARN is a benchmark to assess the rule-learning abilities of large language models (LLMs) in interactive environments.
Approach:	They propose a framework that integrates the process of Induction, Deduction, and Abduction.
Outcome:	The proposed framework improves on the baseline and human-like rule learning in real-world scenarios.

Copied to clipboard

Peilin Wu, Mian Zhang, Xinlu Zhang, Xinya Du, Zhiyu Chen

Green & Sustainable NLP

Challenge:	Recent advances in Large Language Models (LLMs) have propelled their use in informationintensive tasks such as question answering and knowledge synthesis.
Approach:	They propose a reinforcement learning-based training method that incorporates confidence thresholds to reward high-certainty search decisions.
Outcome:	The proposed method outperforms baseline models on seven QA benchmarks and demonstrates that it is more efficient than existing methods.

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Hao Liu, Zhengren Wang, Xi Chen, Zhiyu Li, Feiyu Xiong, Qinhan Yu, Wentao Zhang

Few-Shot NLG with Pre-Trained Language Model (2020.acl-main)

Challenge:	Traditional retrieval systems focus on lexical or semantic similarity rather than logical relevance.
Approach:	They propose a new RAG framework that augments retrieval with logical reasoning . hopRAG uses a retrieve-reason-prune mechanism to explore multi-hop neighbors .
Outcome:	The proposed framework outperforms conventional retrieval systems and state-of-the-art benchmarks on multi-hop QA tasks.

Copied to clipboard

Zhiyu Chen, Harini Eavani, Wenhu Chen, Yinyin Liu, William Yang Wang

Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Search (2023.acl-industry)

Challenge:	Neural-based approaches to natural language generation are data-hungry and difficult to adopt in real-world applications.
Approach:	They propose a task of few-shot natural language generation from structured data or knowledge to generate coherent sentences from input data and language modeling to compose coherent sentences.
Outcome:	The proposed approach outperforms the strongest baseline approach by over 8.0 BLEU points improvement.

Copied to clipboard

Zhiyu Chen, Jason Choi, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi

Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems (2026.acl-long)

Challenge:	Frequently Asked Question (FAQ) retrieval aims at retrieving question-answer pairs for a given user query.
Approach:	They propose to use an intent classifier to predict whether a query is looking for an FAQ and a reformulation model to rewrite the query into a natural question to improve retrieval performance.
Outcome:	The proposed method improves 12% on Hit@1 on retrieving ground-truth FAQs while reducing latency by 95% compared to baseline systems.

Copied to clipboard

Jihao Zhao, Ding Chen, Zhaoxin Fan, Kerun Xu, Mengting Hu, Bo Tang, Feiyu Xiong, Zhiyu li

Identifying High Consideration E-Commerce Search Queries (2024.emnlp-industry)

Challenge:	Existing personalized dialogue systems struggle to reconcile unbounded interactions with finite context constraints.
Approach:	They propose a framework that utilizes a globally maintained PersonaTree as the carrier of long-term user profiling.
Outcome:	The proposed framework outperforms existing systems in suppressing contextual noise and persona inconsistency.

Copied to clipboard

Zhiyu Chen, Jason Ingyu Choi, Besnik Fetahu, Shervin Malmasi

HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processing (2021.eacl-demos)

Challenge:	Identifying high consideration queries is essential for e-commerce sites to better serve user needs . ecommerce sites can create or serve customized content for specific queries .
Approach:	They propose an engagement-based Query Ranking approach to identify potential engagement levels with query-related shopping knowledge content during product search.
Outcome:	The proposed method outperforms human-selected queries in terms of customer impact . human evaluation shows a precision of 96% for HC queries identified by the model .

Copied to clipboard

Xiyou Zhou, Zhiyu Chen, Xiaoyong Jin, William Yang Wang