Genetic Approach to Mitigate Hallucination in Generative IR
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914931556745216 |
|---|---|
| author | Kulkarni, Hrishikesh Goharian, Nazli Frieder, Ophir MacAvaney, Sean |
| author_facet | Kulkarni, Hrishikesh Goharian, Nazli Frieder, Ophir MacAvaney, Sean |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00085 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Genetic Approach to Mitigate Hallucination in Generative IR Kulkarni, Hrishikesh Goharian, Nazli Frieder, Ophir MacAvaney, Sean Computation and Language Information Retrieval 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. |
| title | Genetic Approach to Mitigate Hallucination in Generative IR |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2409.00085 |