datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
bayesian-llm-safety-inference
Bayesian Latent Safety-Trait Dataset
Summary
This dataset supports Bayesian latent-trait analysis of language-model safety behavior.
It contains 90 benchmark-derived roots, three matched prompt variants per root, responses
from four target models over five runs, two independent LLM ratings per response, and one
human rating for a stratified 540-response calibration subset.
The three dimensions are harmful compliance, sycophancy, and agentic protocol violation.… See the full description on the dataset page: https://huggingface.co/datasets/Charly-X/bayesian-llm-safety-inference.p2-etf-bayesian-nonparametric-hdp-resultsrepro-on-regret-bounds-of-thompson-sampling-for-bayesian-optimization-traces
Agent traces
Agent sessions published from a Trackio Logbook.
bayesian-coherence-lm
Bayesian Coherence of LMs — Prompt Sets
Prompt sets for measuring the Bayesian-coherence of language models via the
incoherence certificate |log R| (local) and the cross-lingual/transitive cycle
ratio |log cycle| (global). A model's prompts induce an implicit joint
distribution over entities and relations; a model is coherent on a quartet iff
its loop of conditional inferences multiplies back to 1 (log R = 0).
Code: https://github.com/suchirsalhan/bayesian-coherence-lm… See the full description on the dataset page: https://huggingface.co/datasets/suchirsalhan/bayesian-coherence-lm.Bayesian_WSSbayesian-data-100-pergemma-bayesian-training-preference-descriptiongemma-bayesian-trainingMAS3301-Bayesian-Statisticbayesian-social-deduction
Bayesian Social Deduction Dataset
Project Page | Arxiv | Github
Dataset Description
This dataset contains a collection of game logs from Avalon social deduction games, generated for the "Bayesian Social Deduction with Graph-Informed Language Models" paper. The dataset includes games played by various agents, including humans, and different AI models, providing a rich resource for analyzing strategic communication, deception, and cooperation.
The dataset is organized into… See the full description on the dataset page: https://huggingface.co/datasets/shahabrahimirad/bayesian-social-deduction.bayesian-data-training-alternategemma-bayesian-training-preference-description-random-questions-ablationgemma-bayesian-10-interactionsgemma-bayesian-training-random-questions-ablation