Papers by Lizi Liao

Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery (2024.findings-acl)

Challenge:	EmpathyEar is an open-source, avatar-based multimodal empathetic chatbot . currently, ERG systems rely on text, sound, and vision .
Approach:	They propose an open-source, avatar-based multimodal empathetic chatbot to fill the gap in traditional text-only ERG systems.
Outcome:	The proposed system enables users to generate emotional responses to user queries . it can also generate avatars with talking faces and synchronized speeches .

Copied to clipboard

Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang

Thoughts to Target: Enhance Planning for Target-driven Conversation (2024.emnlp-main)

Challenge:	Current attempts at CID rely on pretrained Small Language Models (SLMs) this lacks the ability to label new intents and is a challenge for small language models.
Approach:	They propose to combine Large Language Models (LLMs) with pre-trained SLMs for CID to enhance the semantic comprehension of LLMs.
Outcome:	The proposed approach improves the semantic comprehension of LLMs and the operational agility of SLMs by realigning existing descriptors within the SLM’s feature space to correct cluster distortion and promote robust learning of representations.

Copied to clipboard

Zhonghua Zheng, Lizi Liao, Yang Deng, Ee-Peng Lim, Minlie Huang, Liqiang Nie

Conversation Disentanglement with Bi-Level Contrastive Learning (2022.findings-emnlp)

Challenge:	Empirical results demonstrate that our method significantly improves the planning ability of LLMs, especially in target-driven conversations.
Approach:	They propose a two-stage framework to improve the LLMs’ capability in planning conversations towards designated targets by distilling natural language plans from a target-driven conversation corpus and generating new plans with demonstration-guided in-context learning.
Outcome:	The proposed framework improves the ability of conversational models to plan towards designated targets and can be used to build extensive conversational AI.

Copied to clipboard

Chengyu Huang, Zheng Zhang, Hao Fei, Lizi Liao

A Survey of Ontology Expansion for Conversational Understanding (2024.emnlp-main)

Challenge:	Existing methods focus on pairwise utterance relations but pay inadequate attention to utterant-to-context relation modeling.
Approach:	They propose a general disentangle model based on bi-level contrastive learning that brings closer utterances in the same session while encouraging each utterrance to be near its clustered session prototypes in representation space.
Outcome:	The proposed model achieves state-of-the-art performance on both settings across public datasets.

Copied to clipboard

Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao

Natural Language Interfaces

Challenge:	Current methods for conversational understanding rely on static ontologies, limiting their ability to handle new and unforeseen user needs.
Approach:	They propose to review the state-of-the-art techniques in OnExp for conversational understanding and highlight emerging frontiers . they categorize existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp.
Outcome:	The proposed methods highlight several emerging frontiers in OnExp to improve agent performance in real-world scenarios and discuss their corresponding challenges.

Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement (2025.findings-acl)

Copied to clipboard

Xiaofeng Zhou, Heyan Huang, Lizi Liao

Beyond Semantic Similarity: Appraisal-Guided Chain-of-Thought Reasoning and Retrieval for Multimodal Emotional Support Conversations (2026.findings-acl)

Challenge:	Existing methods for enhancing small models struggle to yield substantial and lasting performance gains.
Approach:	They propose a Debate and Reflect framework that orchestrates multi-turn debates between smaller models and stronger teacher models.
Outcome:	The proposed framework outperforms existing methods by a large margin in smaller models.

Copied to clipboard

Yuqi Chu, Lizi Liao, Jinggui Liang, Boyang Li, Richang Hong

Reasoning

Challenge:	Existing retrieval-augmented generation paradigms rely on semantic similarity to retrieve historical dialogues that are surface analogous but therapeutically incongruent.
Approach:	They propose to use appraisal-guided reasoning chains to generate appraisal-based reasoning chains and apply a dual-signal verification mechanism to verify and correct them.
Outcome:	Extensive experiments on two ESC benchmarks show that the proposed model significantly outperforms state-of-the-art models.

Self-chats from Large Language Models Make Small Emotional Support Chatbot Better (2024.acl-long)

Copied to clipboard

Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie

PCQPR: Proactive Conversational Question Planning with Reflection (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations.
Approach:	They propose an iterative expansion framework to prompt large teacher model to curate an expansive emotion support dialogue dataset.
Outcome:	The proposed model outperforms the teacher model in some cases . the proposed model is based on an iterative expansion framework and is available on github.com/pandazzh2020/ExTES.

Copied to clipboard

Shasha Guo, Lizi Liao, Jing Zhang, Cuiping Li, Hong Chen

Natural Language Interfaces

Challenge:	Current CQG methods focus on immediate context without strategic consideration of the specified conversational outcome.
Approach:	They propose a method that uses a planning algorithm inspired by Monte Carlo Tree Search to generate contextually relevant questions.
Outcome:	The proposed approach surpasses existing methods in e-learning and customer service fields . it generates contextually appropriate questions strategically devised to reach a specified outcome .

One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialogues (2025.emnlp-main)

Copied to clipboard

Huy Quang Dao, Lizi Liao

Natural Language Interfaces

Challenge:	Existing methods for goal-oriented dialogues involve training separate models for specific combinations of objectives, leading to computational and scalability issues.
Approach:	They propose a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining.
Outcome:	The proposed method can adapt to varying objective preferences at inference time without retraining.

Experience as Source for Anticipation and Planning: Experiential Policy Learning for Target-driven Recommendation Dialogues (2024.findings-emnlp)

Copied to clipboard

Huy Dao, Yang Deng, Khanh-Huyen Bui, Dung Le, Lizi Liao

SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation (2024.findings-naacl)

Challenge:	Existing approaches to enhance dialogues lack the ability to anticipate user interactions . current approaches lack the capability to anticipate past interactions and to neglect past experiences .
Approach:	They propose a framework for enhancing dialogue anticipation with an experiential scoring function that estimates dialogue state potential using similar past interactions stored in long-term memory.
Outcome:	Experiments on two datasets show the framework is superior and effective . tree-structured EPL assesses past dialogue states with LLMs and MCTS .

Copied to clipboard

Shasha Guo, Lizi Liao, Jing Zhang, Yanling Wang, Cuiping Li, Hong Chen

Dialogue State Tracking with Incremental Reasoning (2021.tacl-1)

Challenge:	Existing methods have significantly boosted the performance of Knowledge Base Question Generation (KBQG) through pre-trained language models thanks to the richly endowed semantic knowledge.
Approach:	They propose a framework to Stimulate GPT-3.5 with Skeleton Heuristics to enhance KBQG by combining skeleton heuristic guidance with a soft prompting approach.
Outcome:	The proposed framework incorporates "skeleton heuristics" which provides more fine-grained guidance associated with each input to stimulate LLMs to generate optimal questions.

Copied to clipboard

Lizi Liao, Le Hong Long, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua

Planning Like Human: A Dual-process Framework for Dialogue Planning (2024.acl-long)

Challenge:	Empirical results show that our method outperforms the state-of-the-art methods in terms of joint belief accuracy.
Approach:	They propose to track dialogue states gradually with reasoning over dialogue turns using the back-end data.
Outcome:	Empirical results show that the proposed method outperforms state-of-the-art methods in terms of joint belief accuracy for a large-scale human–human dialogue dataset.

Copied to clipboard

Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, Bing Qin

DC-Instruct: An Effective Framework for Generative Multi-intent Spoken Language Understanding (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) operate in a reactive mode, often resulting in efficiency issues or suboptimal performance.
Approach:	They propose a dual-process dialogue planning framework that leverages the dual-process theory of human cognition and a deliberative Monte Carlo Tree Search mechanism to emulate human-like conversational dynamics.
Outcome:	The proposed framework outperforms existing methods in achieving high-quality dialogues and operational efficiency.

Copied to clipboard

Bowen Xing, Lizi Liao, Minlie Huang, Ivor Tsang

Reasoning

Challenge:	Existing prompt learning frameworks lack explicit modeling of dual-task dependencies and oversight of task-specific semantic differences among utterances.
Approach:	They propose a generative framework based on Dual-task Inter-dependent Instructions (DII) and Supervised Contrastive Instructions that leverages utterance semantics differences by guiding LLMs to determine whether a pair of utterrances share the same or similar labels.
Outcome:	The proposed framework outperforms existing models and state-of-the-art methods on public benchmark datasets and shows that it improves SLU reasoning.

Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering (2025.emnlp-main)

Copied to clipboard

Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Text Clustering

Challenge:	Existing taxonomy construction methods lack coherence and granularity . Existing approaches rely on manual or narrowly defined schemes .
Approach:	They propose a context-aware hierarchical taxonomy generation framework that integrates LLMs with dynamic clustering.
Outcome:	The proposed method outperforms existing methods in taxonomy coherence, granularity, and interpretability.

Colloquial Singaporean English Style Transfer with Fine-Grained Explainable Control (2025.acl-long)

Copied to clipboard

Jinggui Liang, Dung Vo, Yap Hong Xian, Hai Leong Chieu, Kian Ming A. Chai, Jing Jiang, Lizi Liao

Explainability & Interpretability in NLP

Challenge:	Existing methods for style transfer between Singlish and Standard English lack explainability and fine-grained control.
Approach:	They propose a multi-agent framework where large language models act as expert agents for each linguistic aspect.
Outcome:	The proposed model enables precise, interpretable transformations, advancing explainability in NLP for Singlish.

MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Models (2025.findings-acl)

Copied to clipboard

Yun Zhang, Xue Geng, Lizi Liao, Jintong Sun, Minghe Yu, Ge Yu

Reinforced Target-driven Conversational Promotion (2023.emnlp-main)

Challenge:	Existing methods combine quantization with parameter-efficient fine-tuning but fail to meet practical performance requirements.
Approach:	They propose a measure and moment approach to optimize objective function for superior fine-tuning results by scaling the update process through a gradient.
Outcome:	The proposed framework outperforms state-of-the-art methods on tasks like text generation, summarization, and understanding.

Copied to clipboard

Huy Dao, Lizi Liao, Dung Le, Yuxiang Nie

Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution (2025.findings-acl)

Challenge:	Existing conversational recommendation methods focus on acquiring user preferences while ignoring strategic planning for nudging users towards accepting a designated item.
Approach:	They propose a Reinforced Target-driven Conversational Promotion framework that integrates short-term and long-term planning via a balanced gating mechanism.
Outcome:	The proposed model outperforms state-of-the-art models on automatic metrics and human evaluation.

Copied to clipboard

Tao He, Hao Li, Jingchang Chen, Runxuan Liu, Yixin Cao, Lizi Liao, Zihao Zheng, Zheng Chu, Jiafeng Liang, Ming Liu, Bing Qin

Reasoning

Challenge:	OpenAI's O1 and subsequent projects like DeepSeek R1 have significantly advanced research on complex reasoning in LLMs.
Approach:	They analyze existing reasoning studies from the perspective of self-evolution and summarize O1-like works from open-source projects like DeepSeek R1 and Kimi-k1.5.
Outcome:	The proposed models are based on open-source models and pioneer advanced methodologies like Scaling Reinforcement Learning (RL).

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions (2023.emnlp-main)

Copied to clipboard

Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, Min Li

Learning Goal-oriented Dialogue Policy with opposite Agent Awareness (2020.aacl-main)

Challenge:	End-to-end task-oriented dialogue (EToD) can generate responses in an end-to end fashion without modular training, which attracts escalating popularity.
Approach:	They present a systematic review of EToD and propose a unified perspective to summarize existing approaches and recent trends.
Outcome:	The proposed approaches can generate responses in an end-to-end fashion without modular training, which attracts escalating popularity.

Copied to clipboard

Zheng Zhang, Lizi Liao, Xiaoyan Zhu, Tat-Seng Chua, Zitao Liu, Yan Huang, Minlie Huang

Reusable Experiences: Latent Routing and Modular Composition in LLMs (2026.acl-long)

Challenge:	Existing approaches for goal-oriented dialogue policy learning focus on the target agent policy and treat the opposite agent policy as part of the environment.
Approach:	They propose a framework for policy learning in goal-oriented dialogues that uses the opposite agent's policy estimation to improve the target agent by regarding it as part of the target policy.
Outcome:	The proposed framework shows superior performance over state-of-the-art models on cooperative and competitive dialogue tasks.

Copied to clipboard

Shuai Ling, Lizi Liao, Dongmei Jiang, Weili Guan

Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration (2023.findings-emnlp)

Challenge:	Existing approaches represent accumulated experience as explicit textual artifacts in prompts or implicitly within model weights via fine-tuning. Existing methods are limited by context windows and cannot internalize knowledge.
Approach:	They propose a framework that treats latent experiences as fundamental units for LLM specialization.
Outcome:	Experiments on multi-task NLP benchmarks show that this approach outperforms standard fine-tuning, yielding improved generalization through flexible skill reuse.

Copied to clipboard

Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, Tat-Seng Chua

Balancing Visual Context Understanding in Dialogue for Image Retrieval (2024.findings-emnlp)

Challenge:	Recent studies have shown that ChatGPT has limitations such as failing to ask clarifying questions to ambiguous queries or refusing problematic user requests.
Approach:	They propose a Proactive Chain-of-Thought prompting scheme which augments LLMs with the goal planning capability over descriptive reasoning chains to trigger proactivity.
Outcome:	The proposed scheme augments LLMs with the goal planning capability over descriptive reasoning chains to trigger the proactivity of LLM-based proactive dialogue systems.

Copied to clipboard

Zhaohui Wei, Lizi Liao, Xiaoyu Du, Xinguang Xiang

Multimodality

Challenge:	Existing methods neglect the nuanced nature of conversational context, causing a disconnect between dialogue context and visual content.
Approach:	They propose a framework to enhance the comprehension of dialogue history and improve cross-modal matching for image retrieval.
Outcome:	The proposed framework outperforms existing methods in dialogue-to-image retrieval tasks.

LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs (2026.findings-acl)

Copied to clipboard

Jinggui Liang, Lizi Liao

Actively Learn from LLMs with Uncertainty Propagation for Generalized Category Discovery (2024.naacl-long)

Challenge:	Existing security guardrails built from static datasets ignore each model’s unique safety profile and often force trade-offs between safety and utility.
Approach:	They propose a framework for learning model-specific guardrails tailored to each LLM’s vulnerabilities.
Outcome:	The proposed framework significantly outperforms baseline guardrails on multiple real-world LLMs, achieving superior robustness, adaptability, and generalization.

Copied to clipboard

Jinggui Liang, Lizi Liao, Hao Fei, Bobo Li, Jing Jiang

Challenge:	Generalized category discovery (GCD) is a crucial task in open-world computing, where new categories frequently emerge, necessitating models that can adapt and learn continually.
Approach:	They propose to integrate the feedback from LLMs into an active learning paradigm to simplify the labeling task and minimize the spread of inaccurate feedback.
Outcome:	The proposed approach significantly improves baseline models at a nominal average cost.

Mix-Initiative Response Generation with Dynamic Prefix Tuning (2024.naacl-long)

Copied to clipboard

Yuxiang Nie, Heyan Huang, Xian-Ling Mao, Lizi Liao

Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding (2024.acl-long)

Challenge:	Existing dialogue systems focus on training a holistic response generation model without any distinction between different initiatives.
Approach:	They propose a general mix-Initiative Dynamic Prefix Tuning framework to decouple different initiatives from the generation model.
Outcome:	The proposed framework outperforms baselines on two public dialogue datasets on human evaluations and automatic metrics.

Copied to clipboard

Zhihan Zhang, Yixin Cao, Chenchen Ye, Yunshan Ma, Lizi Liao, Tat-Seng Chua

Semi-supervised New Slot Discovery with Incremental Clustering (2022.findings-emnlp)

Challenge:	Existing research in complex event analysis has made significant strides but is constrained by inadequate natural language processing techniques.
Approach:	They propose a novel approach using Large Language Models to extract and analyze the event chain within TCE, characterized by their key points and timestamps.
Outcome:	The proposed model performs comparable to models with long context window and retrieval-augmented generation method in three distinct tasks .

Copied to clipboard

Yuxia Wu, Lizi Liao, Xueming Qian, Tat-Seng Chua

Responsible & Trustworthy NLP

Challenge:	Existing methods to discover new slots rely on unsupervised slot induction or domain adaptation, and are limited in transferring prior knowledge to new slots.
Approach:	They propose a Semi-supervised Incremental Clustering method to discover new slots with existing linguistic annotation models and limited known slot data.
Outcome:	The proposed method significantly outperforms state-of-the-art models on five public datasets.

DiaASQ: A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis (2023.findings-acl)

Copied to clipboard

Bobo Li, Hao Fei, Fei Li, Yuhan Wu, Jinsong Zhang, Shengqiong Wu, Jingye Li, Yijiang Liu, Lizi Liao, Tat-Seng Chua, Donghong Ji

Sentiment Analysis

Challenge:	a new task of conversational aspect-based sentiment analysis (DiaASQ) is designed to detect the quadruple of target-aspect-opinion-sentiment in a dialogue.
Approach:	They propose a task of conversational aspect-based sentiment quadruple analysis to detect the quadrangle of target-aspect-opinion-sentiment in a dialogue.
Outcome:	The proposed task is based on a high-quality dataset in Chinese and English . it improves the end-to-end quadruple prediction and integrates rich feature representations .

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

Copied to clipboard

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

Responsible & Trustworthy NLP

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.

ClusterPrompt: Cluster Semantic Enhanced Prompt Learning for New Intent Discovery (2023.findings-emnlp)

Copied to clipboard

Jinggui Liang, Lizi Liao

Low-Resource NLP

Challenge:	Existing methods for identifying new intent categories focus on relations between utterances and clusters, while neglecting the usage of semantics.
Approach:	They propose a method that leverages contrastive learning and label semantic alignment to learn meaningful representations of intent clusters.
Outcome:	The proposed method outperforms existing methods and suggests meaningful intent labels.

IntentionFrame: A Semi-Structured, Multi-Aspect Framework for Fine-Grained Conversational Intention Understanding (2025.emnlp-main)

Copied to clipboard

Jinggui Liang, Dung Vo, Lizi Liao