Papers by Yuexian Hou

19 papers
LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification (2024.lrec-main)

Copied to clipboard

Challenge: Experimental results show that our model exceeds the baseline models due to the lack of cognitive ability.
Approach: They propose a LLM-Augmented Unsupervised Contrastive Learning Framework which introduces a cognition-enabled Large Language Model (LLM) for efficient data augmentation and presents corresponding contrastive learning strategies.
Outcome: The proposed model exceeds baseline models on six datasets.
CR-GIS: Improving Conversational Recommendation via Goal-aware Interest Sequence Modeling (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to determine a goal item by sequentially tracking users’ interests ignore the rich goal-aware implicit interest sequence patterns in a dialog.
Approach: They propose to model goal-aware implicit user interest sequence patterns in a dialog and a hierarchical Star Transformer to guide multi-turn utterances generation.
Outcome: The proposed framework achieves more accurate recommendations with more fluent and coherent dialog utterances.
A Position-aware Bidirectional Attention Network for Aspect-level Sentiment Analysis (C18-1)

Copied to clipboard

Challenge: Existing approaches to model aspect-level sentiment analysis neglect the position information of aspect terms.
Approach: They propose a position-aware bidirectional attention network (PBAN) that mutually models the relation between aspect terms and sentences by employing bidirectional mechanism.
Outcome: The proposed model can distinguish sentiment polarity of aspect terms in sentences . it can also model relation between aspect terms and sentences based on position information .
MORPHEUS: Modeling Role from Personalized Dialogue History by Exploring and Utilizing Latent Space (2024.emnlp-main)

Copied to clipboard

Challenge: Personalized Dialogue Generation relies on external role data, which can be scarce and raise privacy concerns.
Approach: They propose a framework to extract role information from dialogue history . they use persona codebook to represent roles in latent space and posterior distribution of role information .
Outcome: The proposed framework can generalize across roles, even for unseen roles.
Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense Persona (2023.acl-long)

Copied to clipboard

Challenge: Existing personalized dialogue agents model persona profiles from sparse or dense persona descriptions and dialogue histories.
Approach: They propose a model that clusters dense persona descriptions into sparse categories and generates personalized responses from dialogue histories.
Outcome: The proposed model improves on Chinese and English datasets.
TopKG: Target-oriented Dialog via Global Planning on Knowledge Graph (2022.coling-1)

Copied to clipboard

Challenge: Existing target-oriented dialogs take a local and greedy strategy for response generation, where global planning is absent.
Approach: They propose a global planning method for target-oriented dialog on a commonsense knowledge graph to adjust local response generation towards the global target.
Outcome: The proposed method can reach the target with a higher success rate, fewer turns, and more coherent responses.
Dynamic Personality in LLM Agents: A Framework for Evolutionary Modeling and Behavioral Analysis in the Prisoner’s Dilemma (2025.findings-acl)

Copied to clipboard

Challenge: Current models rely on static personality traits but lack natural selection processes and direct psychological metrics, failing to accurately capture authentic dynamic personality variations.
Approach: They propose a framework that uses game payoffs as environmental feedback to drive adaptive personality evolution and analyze correlations between personality metrics and behavior.
Outcome: The proposed framework reveals new behavioral patterns of agents and evaluates personality-behavior relationships, advancing agent-based social simulations and human-AI symbiosis research.
REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation (2026.acl-long)

Copied to clipboard

Challenge: Empathy relies on the cognitive capacity to relate to similar past experiences. Existing methods prioritize semantic similarity over emotion characteristics, leading to unempathetic responses.
Approach: They propose a framework that integrates four Emotion Attributes into the retrieval process to ensure explicit emotional alignment.
Outcome: Empirical results show that REG significantly outperforms baselines, offering a robust solution for empathetic generation.
Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to quantify and quantify social biases in Large Language Models (LLMs) focus on explicit bias, with little attention to implicit bias.
Approach: They propose a self-reflection-based evaluation framework that measures implicit bias and evaluates explicit bias by prompting LLMs to analyze their own generated content.
Outcome: The proposed framework compares explicit and implicit biases in large language models . it demonstrates that explicit bias manifests as mild stereotypes, while implicit bias exhibits strong stereotypes.
MTGP: Multi-turn Target-oriented Dialogue Guided by Generative Global Path with Flexible Turns (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches focus on global planning, which plans toward the target before the conversation.
Approach: They propose to generate a global path as a natural language sentence instead of a sequence of nodes.
Outcome: The proposed method has fewer turns, more coherent semantics, and higher success rate than baselines.
ECC: Synergizing Emotion, Cause and Commonsense for Empathetic Dialogue Generation (2025.coling-main)

Copied to clipboard

Challenge: Empathy improves human-machine dialogue systems by enhancing the user's experience.
Approach: They propose a framework that leverages specialized encoders to capture the key features of emotion, cause, and commonsense and collaboratively models these through a Conditional Variational Auto-Encoder.
Outcome: Empirical results show that the framework outperforms baseline models and offers a robust solution for empathetic dialogue generation.
RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to combat character hallucination are vulnerable to attack . large language models (LLMs) are capable of generating responses inconsistent with intended personas .
Approach: They propose a novel defence strategy that generates supplemental context through narration to mitigate role-query conflicts and improve query generalization.
Outcome: The proposed defence strategy outperforms refusal-based strategies in character hallucinations and query generalization.
Causal Intervention for Mitigating Name Bias in Machine Reading Comprehension (2023.findings-acl)

Copied to clipboard

Challenge: Existing MRC models may overuse name information to make predictions, causing name bias .
Approach: They propose a Causal Interventional paradigm for MRC to mitigate name bias by analyzing pre-trained knowledge and context representations.
Outcome: The proposed model is robust to names and performs competitively on the original SQuAD.
Emotion Recognition in Conversation via Dynamic Personality (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches to ERC focus on conversational contexts, but focus on static personality.
Approach: They propose a model that considers the dynamic personality of speakers during conversations.
Outcome: The proposed model outperforms existing models on three benchmark conversational datasets.
CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs (2021.emnlp-main)

Copied to clipboard

Challenge: Existing conversational recommender systems (CRS) do not track the deep shift of user interest in conversations due to the complex of high-order and incomplete paths.
Approach: They propose a conversational context-based reinforcement learning model which does explicit multi-hop reasoning on KGs with a contextual context-driven reinforcement learning framework.
Outcome: Extensive experiments show that CRFR improves on paths of interest shift in knowledge graphs (KGs) .
Guiding Dialogue Agents to Complex Semantic Targets by Dynamically Completing Knowledge Graph (2023.findings-acl)

Copied to clipboard

Challenge: Existing knowledge graphs are incomplete in tracking complex semantic relations of the target-oriented dialogue.
Approach: They combine methods of knowledge retrieval and relationship prediction to construct a context-related dynamic KG and a metric to evaluate the tracked path automatically.
Outcome: The proposed method can control the agent more logically and smoothly toward the complex target.
Aligning Recommendation and Conversation via Dual Imitation (2022.emnlp-main)

Copied to clipboard

Challenge: Existing conversational recommendation systems ignore the advantage of user interest shift in connecting recommendation and conversation, leading to an ineffective loose coupling structure.
Approach: They propose a dual imitation to explicitly align recommendation and conversation paths . they propose to generate high-quality responses with accurate recommendations and coherent explanations .
Outcome: The proposed model outperforms the state-of-the-art models on recommendation and conversation performance with automatic, human, and novel explainability metrics.
Mining Effective Features Using Quantum Entropy for Humor Recognition (2023.findings-eacl)

Copied to clipboard

Challenge: Existing studies on humor recognition do not understand the mechanisms that generate humor.
Approach: They propose to use quantum entropy to represent the semantic uncertainty of the setup and punchline as features for humor recognition.
Outcome: The proposed features are more effective than baselines for recognizing humorous and non-humorous texts on the SemEval2021 task 7 dataset.
A Comparative Study of Explicit and Implicit Gender Biases in Large Language Models via Self-evaluation (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies on the explicit and implicit biases in large language models (LLMs) focus on either explicit or implicit bias.
Approach: They propose a self-evaluation-based two-stage measurement of explicit and implicit biases within large language models grounded in social psychology.
Outcome: The proposed model is based on two stages of self-evaluation on state-of-the-art LLMs to measure explicit bias toward social targets, where bias is less likely to be self-recognized by the LLM.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations