Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation

• URL: http://arxiv.org/abs/2608.28467v1
• Date: Fri, 28 Aug 2026 15:53:14 GMT
• Title: Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation
• Abstract summary: Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants.<n>Prior work often neglected mechanisms that only appear when biography visibility is toggled separately across training, inference, and evaluation.<n>We study this factorisation on a dataset of dialogues paired with speaker's biographies, varying whether the target and interlocutor speakers see each other's biographies.
• Score: 23.52338392175125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants, and who has access to whose biography can vary across training, inference, and evaluation. Prior work often neglected these aspects, obscuring mechanisms that only appear when biography visibility is toggled separately across training, inference, and evaluation, a three-stage factorisation that prior work has largely treated as a single factor. We study this factorisation on a dataset of dialogues paired with speaker's biographies, varying whether the target and interlocutor speakers see each other's biographies during training and inference, and using an LLM as a judge to perform author identification. We find that (i) training-time visibility, more than inference-time visibility, determines whether models express persona traits through dialogue or fall back on copying biographical text (a known problem/phenomenon in persona-based generation); (ii) models trained with interlocutor-biography visibility copy less target-biographical text than models trained without it, while changing visibility only at inference time has a less consistent effect; and (iii) under asymmetric disclosure, where only the interlocutor sees the target biography, target content leaks into interlocutor turns more often, and dialogues containing such traces are easier for the judge to identify, especially when interlocutor turns are visible. These results suggest that biography leakage into generated turns is an artefact of how interlocutor visibility is configured across training and inference, and separating the three stages is necessary.

Related papers

• PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation [118.49150310327475]
  PersonaShot is the first person-centric benchmark for narrative continuity in multi-shot video generation.<n>It contains approximately 1,000 multi-shot segments and 16 metrics spanning physical continuity, affective dynamics, and cinematic grammar.
  arXiv  Detail & Related papers  (2026-08-17T15:34:54Z)
• Do Visual Features Improve Other-Initiated Repair Detection? A Dyadic Multimodal Approach [8.813506953164778]
  Other-initiated Self-repair, or in short Other-initiated Repair, is an essential mechanism in conversational interaction.<n>This paper introduces a novel multimodal model for OIR detection and classification, incorporating a set of visual features drawn from conversation analysis.
  arXiv  Detail & Related papers  (2026-07-26T21:16:02Z)
• When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation [18.650805984660707]
  Endowing dialogue agents with persona information has proven to significantly improve the consistency and diversity of their generations.<n>While much focus has been placed on aligning dialogues with provided personas, the adaptation to the interlocutor's profile remains largely underexplored.<n>We investigate three key aspects: (1) a model's ability to align responses with both the provided persona and the interlocutor's; (2) its robustness when dealing with familiar versus unfamiliar interlocutors and topics, and (3) the impact of additional fine-tuning on specific persona-based dialogues.
  arXiv  Detail & Related papers  (2025-05-30T14:04:30Z)
• Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation [30.820334868031537]
  Personality Recognition in Conversation (PRC) aims to identify the personality traits of speakers through textual dialogue content. We propose Affective Natural Language Inference (Affective-NLI) for accurate and interpretable PRC.
  arXiv  Detail & Related papers  (2024-04-03T09:14:24Z)
• A Benchmark for Understanding and Generating Dialogue between Characters in Stories [75.29466820496913]
  We present the first study to explore whether machines can understand and generate dialogue in stories. We propose two new tasks including Masked Dialogue Generation and Dialogue Speaker Recognition. We show the difficulty of the proposed tasks by testing existing models with automatic and manual evaluation on DialStory.
  arXiv  Detail & Related papers  (2022-09-18T10:19:04Z)
• Self-supervised Speaker Recognition Training Using Human-Machine Dialogues [22.262550043863445]
  We investigate how to pretrain speaker recognition models by leveraging dialogues between customers and smart-speaker devices. We propose an effective rejection mechanism that selectively learns from dialogues based on their acoustic homogeneity. Experiments demonstrate that the proposed method provides significant performance improvements, superior to earlier work.
  arXiv  Detail & Related papers  (2022-02-07T19:44:54Z)
• Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition [17.428626029689653]
  We propose to represent the target subjects person-specific cognition in the form of a person-specific CNN architecture. Each person-specific CNN is explored by the Neural Architecture Search (NAS) and a novel adaptive loss function. Experimental results show that the produced graph representations are well associated with target subjects' personality traits.
  arXiv  Detail & Related papers  (2021-10-26T11:04:23Z)
• Probing Task-Oriented Dialogue Representation from Language Models [106.02947285212132]
  This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks. We fine-tune a feed-forward layer as the classifier probe on top of a fixed pre-trained language model with annotated labels in a supervised way.
  arXiv  Detail & Related papers  (2020-10-26T21:34:39Z)
• Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue [76.88174667929665]
  A multi-turn dialogue is composed of multiple utterances from two or more different speaker roles. In the existing retrieval-based multi-turn dialogue modeling, the pre-trained language models (PrLMs) as encoder represent the dialogues coarsely. We propose a novel model to fill such a gap by modeling the effective utterance-aware and speaker-aware representations entailed in a dialogue history.
  arXiv  Detail & Related papers  (2020-09-14T15:07:19Z)
• You Impress Me: Dialogue Generation via Mutual Persona Perception [62.89449096369027]
  The research in cognitive science suggests that understanding is an essential signal for a high-quality chit-chat conversation. Motivated by this, we propose P2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding.
  arXiv  Detail & Related papers  (2020-04-11T12:51:07Z)
• Disentangled Speech Embeddings using Cross-modal Self-supervision [119.94362407747437]
  We develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces and audio in video. We construct a two-stream architecture which: (1) shares low-level features common to both representations; and (2) provides a natural mechanism for explicitly disentangling these factors.
  arXiv  Detail & Related papers  (2020-02-20T14:13:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.