Genetic Approach to Mitigate Hallucination in Generative IR

bibtex workshop paper to appear

Authors: Hrishikesh Kulkarni, Nazli Goharian, Ophir Frieder, Sean MacAvaney

Appearing in: The Second Workshop on Generative Information Retrieval (GENIR@SIGIR 2024)

Abstract:

Generative language models hallucinate. That is, at times, they generate factually flawed responses. These inaccuracies are particularly insidious because the responses are fluent and well-articulated. We focus on the task of Grounded Answer Generation (part of Generative IR), which aims to produce direct answers to a user's question based on results retrieved from a search engine. We address hallucination by adapting an existing genetic generation approach with a new 'balanced fitness function' consisting of a cross-encoder model for relevance and an n-gram overlap metric to promote grounding. Our balanced fitness function approach quadruples the grounded answer generation accuracy while maintaining high relevance to the user query across datasets and different evaluation models.

BibTeX @inproceedings{kulkarni:genir2024-gauge, author = {Kulkarni, Hrishikesh and Goharian, Nazli and Frieder, Ophir and MacAvaney, Sean}, title = {Genetic Approach to Mitigate Hallucination in Generative IR}, booktitle = {The Second Workshop on Generative Information Retrieval}, year = {2024} }