Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Villa, Danielle, Chang, Maria, Murugesan, Keerthiram, Uceda-Sosa, Rosario, Ramamurthy, Karthikeyan Natesan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915192546263040
author Villa, Danielle
Chang, Maria
Murugesan, Keerthiram
Uceda-Sosa, Rosario
Ramamurthy, Karthikeyan Natesan
author_facet Villa, Danielle
Chang, Maria
Murugesan, Keerthiram
Uceda-Sosa, Rosario
Ramamurthy, Karthikeyan Natesan
contents Large Language Models (LLMs) are often asked to explain their outputs to enhance accuracy and transparency. However, evidence suggests that these explanations can misrepresent the models' true reasoning processes. One effective way to identify inaccuracies or omissions in these explanations is through consistency checking, which typically involves asking follow-up questions. This paper introduces, cross-examiner, a new method for generating follow-up questions based on a model's explanation of an initial question. Our method combines symbolic information extraction with language model-driven question generation, resulting in better follow-up questions than those produced by LLMs alone. Additionally, this approach is more flexible than other methods and can generate a wider variety of follow-up questions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations
Villa, Danielle
Chang, Maria
Murugesan, Keerthiram
Uceda-Sosa, Rosario
Ramamurthy, Karthikeyan Natesan
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) are often asked to explain their outputs to enhance accuracy and transparency. However, evidence suggests that these explanations can misrepresent the models' true reasoning processes. One effective way to identify inaccuracies or omissions in these explanations is through consistency checking, which typically involves asking follow-up questions. This paper introduces, cross-examiner, a new method for generating follow-up questions based on a model's explanation of an initial question. Our method combines symbolic information extraction with language model-driven question generation, resulting in better follow-up questions than those produced by LLMs alone. Additionally, this approach is more flexible than other methods and can generate a wider variety of follow-up questions.
title Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.08815