NC-Bench: An LLM Benchmark for Evaluating Conversational Competence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moore, Robert J., An, Sungeun, Ahmed, Farhan, Gala, Jay Pankaj
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914377171468288
author Moore, Robert J.
An, Sungeun
Ahmed, Farhan
Gala, Jay Pankaj
author_facet Moore, Robert J.
An, Sungeun
Ahmed, Farhan
Gala, Jay Pankaj
contents The Natural Conversation Benchmark (NC-Bench) introduces a new approach to evaluating the general conversational competence of large language models (LLMs). Unlike prior benchmarks that focus on the content of model behavior, NC-Bench focuses on the form and structure of natural conversation. Grounded in the IBM Natural Conversation Framework (NCF), NC-Bench comprises three distinct sets: (1) the basic set evaluates fundamental sequence management practices, such as answering inquiries, repairing responses, and closing conversational pairs; (2) the retrieval-augmented generation (RAG) set applies the same sequence management patterns as the first set but incorporates information-seeking via RAG; (3) the complex request set extends to requests involving more intricate sequence management patterns. Each set tests a model's ability to produce contextually appropriate conversational actions in response to characteristic interaction patterns. Initial evaluations across six open-source models and 14 interaction patterns show that models perform well on basic answering tasks, struggle more with repair tasks (especially repeat), have mixed performance on closing sequences, and find complex multi-turn requests most challenging. By operationalizing fundamental principles of human conversation, NC-Bench provides a lightweight, extensible, and theory-grounded framework for assessing and improving the conversational abilities of LLMs beyond topical or task-specific benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06426
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle NC-Bench: An LLM Benchmark for Evaluating Conversational Competence
Moore, Robert J.
An, Sungeun
Ahmed, Farhan
Gala, Jay Pankaj
Computation and Language
Artificial Intelligence
The Natural Conversation Benchmark (NC-Bench) introduces a new approach to evaluating the general conversational competence of large language models (LLMs). Unlike prior benchmarks that focus on the content of model behavior, NC-Bench focuses on the form and structure of natural conversation. Grounded in the IBM Natural Conversation Framework (NCF), NC-Bench comprises three distinct sets: (1) the basic set evaluates fundamental sequence management practices, such as answering inquiries, repairing responses, and closing conversational pairs; (2) the retrieval-augmented generation (RAG) set applies the same sequence management patterns as the first set but incorporates information-seeking via RAG; (3) the complex request set extends to requests involving more intricate sequence management patterns. Each set tests a model's ability to produce contextually appropriate conversational actions in response to characteristic interaction patterns. Initial evaluations across six open-source models and 14 interaction patterns show that models perform well on basic answering tasks, struggle more with repair tasks (especially repeat), have mixed performance on closing sequences, and find complex multi-turn requests most challenging. By operationalizing fundamental principles of human conversation, NC-Bench provides a lightweight, extensible, and theory-grounded framework for assessing and improving the conversational abilities of LLMs beyond topical or task-specific benchmarks.
title NC-Bench: An LLM Benchmark for Evaluating Conversational Competence
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.06426