Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914714017071104 |
|---|---|
| author | Chang, Tyler A. Tomanek, Katrin Hoffmann, Jessica Thain, Nithum van Liemt, Erin Meier-Hellstern, Kathleen Dixon, Lucas |
| author_facet | Chang, Tyler A. Tomanek, Katrin Hoffmann, Jessica Thain, Nithum van Liemt, Erin Meier-Hellstern, Kathleen Dixon, Lucas |
| contents | We explore a strategy to handle controversial topics in LLM-based chatbots based on Wikipedia's Neutral Point of View (NPOV) principle: acknowledge the absence of a single true answer and surface multiple perspectives. We frame this as retrieval augmented generation, where perspectives are retrieved from a knowledge base and the LLM is tasked with generating a fluent and faithful response from the given perspectives. As a starting point, we use a deterministic retrieval system and then focus on common LLM failure modes that arise during this approach to text generation, namely hallucination and coverage errors. We propose and evaluate three methods to detect such errors based on (1) word-overlap, (2) salience, and (3) LLM-based classifiers. Our results demonstrate that LLM-based classifiers, even when trained only on synthetic errors, achieve high error detection performance, with ROC AUC scores of 95.3% for hallucination and 90.5% for coverage error detection on unambiguous error cases. We show that when no training data is available, our other methods still yield good results on hallucination (84.0%) and coverage error (85.2%) detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08904 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics Chang, Tyler A. Tomanek, Katrin Hoffmann, Jessica Thain, Nithum van Liemt, Erin Meier-Hellstern, Kathleen Dixon, Lucas Computation and Language We explore a strategy to handle controversial topics in LLM-based chatbots based on Wikipedia's Neutral Point of View (NPOV) principle: acknowledge the absence of a single true answer and surface multiple perspectives. We frame this as retrieval augmented generation, where perspectives are retrieved from a knowledge base and the LLM is tasked with generating a fluent and faithful response from the given perspectives. As a starting point, we use a deterministic retrieval system and then focus on common LLM failure modes that arise during this approach to text generation, namely hallucination and coverage errors. We propose and evaluate three methods to detect such errors based on (1) word-overlap, (2) salience, and (3) LLM-based classifiers. Our results demonstrate that LLM-based classifiers, even when trained only on synthetic errors, achieve high error detection performance, with ROC AUC scores of 95.3% for hallucination and 90.5% for coverage error detection on unambiguous error cases. We show that when no training data is available, our other methods still yield good results on hallucination (84.0%) and coverage error (85.2%) detection. |
| title | Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.08904 |