Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation
Paper
•
2208.05309
•
Published
•
1
LLM Hallucination Detection Papers
Collection of LLM hallucination and evaluation papers that I've been exploring and implementing. Some of them have my comments and annotated doodles.
Note Some of my notes on the paper: https://huggingface.co/posts/santiviquez/138523411387083
LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models
Paper • 2305.13711 • Published • 2Note Some of my results from replicating this paper: https://huggingface.co/posts/santiviquez/229518612093214
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Paper • 2302.09664 • Published • 3Note Some of my notes on the paper: https://huggingface.co/posts/santiviquez/951407525332988
BARTScore: Evaluating Generated Text as Text Generation
Paper • 2106.11520 • Published • 1Note Some of my notes on the paper: https://huggingface.co/posts/santiviquez/809039256258115
Corrective Retrieval Augmented Generation
Paper • 2401.15884 • Published • 3Note Some of my notes on the paper: https://huggingface.co/posts/santiviquez/303238714777838
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Paper • 2303.08896 • Published • 4Note Some of my notes on the paper: https://huggingface.co/posts/santiviquez/745054200506765
INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
Paper • 2402.03744 • Published • 4Note Some of my notes on the paper: https://huggingface.co/posts/santiviquez/232227054095509
Fine-grained Hallucination Detection and Editing for Language Models
Paper • 2401.06855 • Published • 3Note Some of my notes on the paper: https://huggingface.co/posts/santiviquez/787276815476646
-
Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better
Paper • 2212.08597 • Published • 1 -
Language Models (Mostly) Know What They Know
Paper • 2207.05221 • Published • 1 -
A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection
Paper • 2310.06498 • Published • 1 -
On Hallucination and Predictive Uncertainty in Conditional Language Generation
Paper • 2103.15025 • Published • 1