Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Do Androids Know They're Only Dreaming of Electric Sheep?

About

We design probes trained on the internal representations of a transformer language model to predict its hallucinatory behavior on three grounded generation tasks. To train the probes, we annotate for span-level hallucination on both sampled (organic) and manually edited (synthetic) reference outputs. Our probes are narrowly trained and we find that they are sensitive to their training domain: they generalize poorly from one task to another or from synthetic to organic hallucinations. However, on in-domain data, they can reliably detect hallucinations at many transformer layers, achieving 95% of their peak performance as early as layer 4. Here, probing proves accurate for evaluating hallucination, outperforming several contemporary baselines and even surpassing an expert human annotator in response-level detection F1. Similarly, on span-level labeling, probes are on par or better than the expert annotator on two out of three generation tasks. Overall, we find that probing is a feasible and efficient alternative to language model hallucination evaluation when model states are available.

Sky CH-Wang, Benjamin Van Durme, Jason Eisner, Chris Kedzie• 2023

Related benchmarks

TaskDatasetResultRank
Hallucination DetectionTriviaQA--
625
Uncertainty QuantificationAggregated Experimental Datasets (XSum, SamSum, CNN, WMT19, MedQUAD, TruthfulQA, CoQA, SciQ, TriviaQA, MMLU, GSM8k) (test)
Mean Rank3.09
88
Claim Verification9-dataset aggregate retrieval-free setting (test)
ROC-AUC75
70
Selective GenerationGSM8K
ROC-AUC88.5
66
Mathematical ReasoningGSM8K
PRR0.71
66
Selective GenerationCoQA
ROC-AUC74.6
66
Selective GenerationMMLU
ROC-AUC0.945
66
Machine TranslationWMT 19
PRR64
66
Selective Generationcnn
ROC-AUC72.1
66
Selective GenerationWMT19
ROC-AUC0.831
66
Showing 10 of 52 rows

Other info

Code

Follow for update