Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People

• URL: http://arxiv.org/abs/2406.04278v1
• Date: Thu, 6 Jun 2024 17:26:00 GMT
• Title: Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People
• Authors: Dun-Ming Huang, Pol Van Rijn, Ilia Sucholutsky, Raja Marjieh, Nori Jacoby,
• Abstract summary: We propose an iterative method for simultaneously eliciting conversational tones and sentences. We show how our approach can be used to create an interpretable representation of relations between conversational tones in humans and GPT-4.
• Score: 20.95122915164433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversational tones -- the manners and attitudes in which speakers communicate -- are essential to effective communication. Amidst the increasing popularization of Large Language Models (LLMs) over recent years, it becomes necessary to characterize the divergences in their conversational tones relative to humans. However, existing investigations of conversational modalities rely on pre-existing taxonomies or text corpora, which suffer from experimenter bias and may not be representative of real-world distributions for the studies' psycholinguistic domains. Inspired by methods from cognitive science, we propose an iterative method for simultaneously eliciting conversational tones and sentences, where participants alternate between two tasks: (1) one participant identifies the tone of a given sentence and (2) a different participant generates a sentence based on that tone. We run 100 iterations of this process with human participants and GPT-4, then obtain a dataset of sentences and frequent conversational tones. In an additional experiment, humans and GPT-4 annotated all sentences with all tones. With data from 1,339 human participants, 33,370 human judgments, and 29,900 GPT-4 queries, we show how our approach can be used to create an interpretable geometric representation of relations between conversational tones in humans and GPT-4. This work demonstrates how combining ideas from machine learning and cognitive science can address challenges in human-computer interactions.

Related papers

• Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation [70.52558242336988]
  We focus on predicting engagement in dyadic interactions by scrutinizing verbal and non-verbal cues, aiming to detect signs of disinterest or confusion. In this work, we collect a dataset featuring 34 participants engaged in casual dyadic conversations, each providing self-reported engagement ratings at the end of each conversation. We introduce a novel fusion strategy using Large Language Models (LLMs) to integrate multiple behavior modalities into a multimodal transcript''
  arXiv  Detail & Related papers  (2024-09-13T18:28:12Z)
• Self-Directed Turing Test for Large Language Models [56.64615470513102]
  The Turing test examines whether AIs can exhibit human-like behaviour in natural language conversations. Traditional Turing tests adopt a rigid dialogue format where each participant sends only one message each time. This paper proposes the Self-Directed Turing Test, which extends the original test with a burst dialogue format.
  arXiv  Detail & Related papers  (2024-08-19T09:57:28Z)
• Learning to Communicate Functional States with Nonverbal Expressions for Improved Human-Robot Collaboration [3.5408317027307055]
  Collaborative robots must effectively communicate their internal state to humans to enable a smooth interaction. We propose a reinforcement learning algorithm based on noisy human feedback to produce accurately interpreted nonverbal auditory expressions.
  arXiv  Detail & Related papers  (2024-04-30T04:18:21Z)
• Multi-dimensional Evaluation of Empathetic Dialog Responses [4.580983642743026]
  We propose a multi-dimensional empathy evaluation framework to measure both emphexpressed intents from the speaker's perspective and emphperceived empathy from the listener's perspective. We find the two dimensions are inter-connected, while perceived empathy has high correlations with dialogue satisfaction levels.
  arXiv  Detail & Related papers  (2024-02-18T00:32:33Z)
• A Linguistic Comparison between Human and ChatGPT-Generated Conversations [9.022590646680095]
  The research employs Linguistic Inquiry and Word Count analysis, comparing ChatGPT-generated conversations with human conversations. Results show greater variability and authenticity in human dialogues, but ChatGPT excels in categories such as social processes, analytical style, cognition, attentional focus, and positive emotional tone.
  arXiv  Detail & Related papers  (2024-01-29T21:43:27Z)
• Interactive Conversational Head Generation [68.76774230274076]
  We introduce a new conversation head generation benchmark for synthesizing behaviors of a single interlocutor in a face-to-face conversation. The capability to automatically synthesize interlocutors which can participate in long and multi-turn conversations is vital and offer benefits for various applications.
  arXiv  Detail & Related papers  (2023-07-05T08:06:26Z)
• PLACES: Prompting Language Models for Social Conversation Synthesis [103.94325597273316]
  We use a small set of expert-written conversations as in-context examples to synthesize a social conversation dataset using prompting. We perform several thorough evaluations of our synthetic conversations compared to human-collected conversations.
  arXiv  Detail & Related papers  (2023-02-07T05:48:16Z)
• deep learning of segment-level feature representation for speech emotion recognition in conversations [9.432208348863336]
  We propose a conversational speech emotion recognition method to deal with capturing attentive contextual dependency and speaker-sensitive interactions. First, we use a pretrained VGGish model to extract segment-based audio representation in individual utterances. Second, an attentive bi-directional recurrent unit (GRU) models contextual-sensitive information and explores intra- and inter-speaker dependencies jointly.
  arXiv  Detail & Related papers  (2023-02-05T16:15:46Z)
• Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects [82.81964713263483]
  A popular approach to decompose the neural bases of language consists in correlating, across individuals, the brain responses to different stimuli. Here, we show that a model-based approach can reach equivalent results within subjects exposed to natural stimuli.
  arXiv  Detail & Related papers  (2021-10-12T15:30:21Z)
• 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)

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.