Enhancing LLM-Based Human-Robot Interaction with Nuances for Diversity Awareness
- URL: http://arxiv.org/abs/2406.17531v1
- Date: Tue, 25 Jun 2024 13:15:36 GMT
- Title: Enhancing LLM-Based Human-Robot Interaction with Nuances for Diversity Awareness
- Authors: Lucrezia Grassi, Carmine Tommaso Recchiuto, Antonio Sgorbissa,
- Abstract summary: This paper presents a system for diversity-aware autonomous conversation leveraging the capabilities of large language models (LLMs)
The system adapts to diverse populations and individuals, considering factors like background, personality, age, gender, and culture.
To assess the system's performance, we conducted both controlled and real-world experiments, measuring a wide range of performance indicators.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents a system for diversity-aware autonomous conversation leveraging the capabilities of large language models (LLMs). The system adapts to diverse populations and individuals, considering factors like background, personality, age, gender, and culture. The conversation flow is guided by the structure of the system's pre-established knowledge base, while LLMs are tasked with various functions, including generating diversity-aware sentences. Achieving diversity-awareness involves providing carefully crafted prompts to the models, incorporating comprehensive information about users, conversation history, contextual details, and specific guidelines. To assess the system's performance, we conducted both controlled and real-world experiments, measuring a wide range of performance indicators.
Related papers
- PersLLM: A Personified Training Approach for Large Language Models [63.75008885222351]
We propose PersLLM, integrating psychology-grounded principles of personality: social practice, consistency, and dynamic development.
We incorporate personality traits directly into the model parameters, enhancing the model's resistance to induction, promoting consistency, and supporting the dynamic evolution of personality.
arXiv Detail & Related papers (2024-07-17T08:13:22Z) - POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models [28.072184039405784]
We present POEM, a visual analytics system to facilitate efficient prompt engineering for large language models (LLMs)
The system enables users to explore the interaction patterns across modalities at varying levels of detail for a comprehensive understanding of the multimodal knowledge elicited by various prompts.
arXiv Detail & Related papers (2024-06-06T08:21:30Z) - RoleInteract: Evaluating the Social Interaction of Role-Playing Agents [85.6641890712617]
We introduce the first benchmark designed to evaluate the sociality of role-playing conversational agents at both individual and group levels of social interactions.
The benchmark is constructed from a variety of sources and covers a wide range of 500 characters and over 6,000 question prompts.
We find that agents excelling in individual level does not imply their proficiency in group level.
arXiv Detail & Related papers (2024-03-20T15:38:36Z) - DIALIGHT: Lightweight Multilingual Development and Evaluation of
Task-Oriented Dialogue Systems with Large Language Models [76.79929883963275]
DIALIGHT is a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems.
It features a secure, user-friendly web interface for fine-grained human evaluation at both local utterance level and global dialogue level.
Our evaluations reveal that while PLM fine-tuning leads to higher accuracy and coherence, LLM-based systems excel in producing diverse and likeable responses.
arXiv Detail & Related papers (2024-01-04T11:27:48Z) - RoleEval: A Bilingual Role Evaluation Benchmark for Large Language
Models [44.105939096171454]
This paper introduces RoleEval, a benchmark designed to assess the memorization, utilization, and reasoning capabilities of role knowledge.
RoleEval comprises RoleEval-Global and RoleEval-Chinese, with 6,000 Chinese-English parallel multiple-choice questions.
arXiv Detail & Related papers (2023-12-26T17:40:55Z) - Improving Diversity of Demographic Representation in Large Language
Models via Collective-Critiques and Self-Voting [19.79214899011072]
This paper formalizes diversity of representation in generative large language models.
We present evaluation datasets and propose metrics to measure diversity in generated responses along people and culture axes.
We find that LLMs understand the notion of diversity, and that they can reason and critique their own responses for that goal.
arXiv Detail & Related papers (2023-10-25T10:17:17Z) - A Systematic Study of Performance Disparities in Multilingual
Task-Oriented Dialogue Systems [68.76102493999134]
We take stock of and empirically analyse task performance disparities that exist between multilingual task-oriented dialogue systems.
We prove the existence of the adaptation and intrinsic biases in current ToD systems.
Our analyses offer practical tips on how to approach ToD data collection and system development for new languages.
arXiv Detail & Related papers (2023-10-19T16:41:44Z) - Empowering Private Tutoring by Chaining Large Language Models [87.76985829144834]
This work explores the development of a full-fledged intelligent tutoring system powered by state-of-the-art large language models (LLMs)
The system is into three inter-connected core processes-interaction, reflection, and reaction.
Each process is implemented by chaining LLM-powered tools along with dynamically updated memory modules.
arXiv Detail & Related papers (2023-09-15T02:42:03Z) - Evaluating the Evaluation of Diversity in Natural Language Generation [43.05127848086264]
We propose a framework for evaluating diversity metrics in natural language generation systems.
Our framework can advance the understanding of different diversity metrics, an essential step on the road towards better NLG systems.
arXiv Detail & Related papers (2020-04-06T20:44:10Z) - Attention over Parameters for Dialogue Systems [69.48852519856331]
We learn a dialogue system that independently parameterizes different dialogue skills, and learns to select and combine each of them through Attention over Parameters (AoP)
The experimental results show that this approach achieves competitive performance on a combined dataset of MultiWOZ, In-Car Assistant, and Persona-Chat.
arXiv Detail & Related papers (2020-01-07T03:10:42Z)
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.