paper-with-me

홈 › Papers

Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain

2024-01-12 · Alexandra DeLucia, Mengjie Zhao, Yoshinori Maeda, Makoto Yoda, Keiichi Yamada, Hiromi Wakaki

While valuable datasets such as PersonaChat provide a foundation for training persona-grounded dialogue agents, they lack diversity in conversational and narrative settings, primarily existing in the "real" world. To develop dialogue agents with unique personas, models are trained to converse given a specific persona, but hand-crafting these persona can be time-consuming, thus methods exist to automatically extract persona information from existing character-specific dialogue. However, these persona-extraction models are also trained on datasets derived from PersonaChat and struggle to provide high-quality persona information from conversational settings that do not take place in the real world, such as the fantasy-focused dataset, LIGHT. Creating new data to train models on a specific setting is human-intensive, thus prohibitively expensive. To address both these issues, we introduce a natural language inference method for post-hoc adapting a trained persona extraction model to a new setting. We draw inspiration from the literature of dialog natural language inference (NLI), and devise NLI-reranking methods to extract structured persona information from dialogue. Compared to existing persona extraction models, our method returns higher-quality extracted persona and requires less human annotation.

📄 PDF Abstract BibTeX arXiv:2401.06742

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityNatural Language InferenceReranking

Similar Papers 제목 키워드 기반

Optimisation using Natural Language Processing: Personalized Tour Recommendation for Museums

2015-01-06 · Mayeul Mathias, Assema Moussa, Fen Zhou, Juan-Manuel Torres-Moreno 외

This paper proposes a new method to provide personalized tour recommendation for museum visits. It combines an optimization of preference criteria of visitors with an automatic extraction of artwork importance from museu…

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

2025-10-17 · Yizhuo Chen, Xin Liu, Ruijie Wang, Zheng Li 외 arxiv

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the pr…

Reinforcement Learning

Generating Persona Consistent Dialogues by Exploiting Natural Language Inference

2019-11-14 · Haoyu Song, Wei-Nan Zhang, Jingwen Hu, Ting Liu

Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natu…

DecoderDialogue GenerationNatural Language InferenceReinforcement Learning

Evaluating LLM Personalization via Semantic Constraint Verification

2026-06-15 · Xuran Li, Guanqin Zhang, Imran Razzak, Hakim Hacid 외 arxiv

Current evaluation paradigms for Large Language Model (LLM) personalization rely heavily on brittle surface-matching metrics or computationally expensive LLM-as-a-judge protocols, both of which lack interpretability. To …

Natural Language Inference

Learning from Natural Language Feedback for Personalized Question Answering

2025-08-14 · Alireza Salemi, Hamed Zamani arxiv

Personalization is crucial for enhancing both the effectiveness and user satisfaction of language technologies, particularly in information-seeking tasks like question answering. Current approaches for personalizing larg…

Reinforcement LearningResponse GenerationQuestion Answering