HalluCana: Fixing LLM Hallucination with A Canary Lookahead
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_ | 1866916517919064064 |
|---|---|
| author | Li, Tianyi Dayanik, Erenay Tyagi, Shubhi Pierleoni, Andrea |
| author_facet | Li, Tianyi Dayanik, Erenay Tyagi, Shubhi Pierleoni, Andrea |
| contents | In this paper, we present HalluCana, a canary lookahead to detect and correct factuality hallucinations of Large Language Models (LLMs) in long-form generation. HalluCana detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we exploit the internal factuality representation in the LLM hidden space, where we investigate various proxies to the LLMs' factuality self-assessment, and discuss its relation to the models' context familiarity from their pre-training. On biography generation, our method improves generation quality by up to 2.5x, while consuming over 6 times less compute. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07965 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HalluCana: Fixing LLM Hallucination with A Canary Lookahead Li, Tianyi Dayanik, Erenay Tyagi, Shubhi Pierleoni, Andrea Computation and Language In this paper, we present HalluCana, a canary lookahead to detect and correct factuality hallucinations of Large Language Models (LLMs) in long-form generation. HalluCana detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we exploit the internal factuality representation in the LLM hidden space, where we investigate various proxies to the LLMs' factuality self-assessment, and discuss its relation to the models' context familiarity from their pre-training. On biography generation, our method improves generation quality by up to 2.5x, while consuming over 6 times less compute. |
| title | HalluCana: Fixing LLM Hallucination with A Canary Lookahead |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.07965 |