rrf
Datasets
All datasets matching “rrf”rrflux-gameaic-rrf-mediarrfa-data
Data Card: Agentic Circuit Breaker Training Data
Dataset Description
This repository contains processed training data for Agentic Circuit Breakers — LoRA adapters trained via Representation Rerouting (RR) to defend against tool-flip attacks in agentic LLMs.
Dataset Summary
Component
Description
Format
ds_*.jsonl
Harmful set (Ds) — Successful tool-flip attacks
JSONL
dr_*.jsonl
Retain set (Dr) — Benign tool-calling behavior
JSONL
eval_*.jsonl… See the full description on the dataset page: https://huggingface.co/datasets/memo-ozdincer/rrfa-data.savant_rrf1msmarco-bm25-rrf-scoredThis is the triplet-50 subset of sentence-transformers/msmarco-bm25, scored using tomaarsen/reranker-msmarco-ModernBERT-base-lambdaloss.
The negatives are re-sorted using reciprocal rank fusion (rrf). A second set of scores has been added from naver/splade-v3 in
the splade_labels column for additional distillation.
A typical use case for this would be teacher scores for MSE (and/or KLdiv) distillation when training a splade-v3 model.
The label column are the reranker scores with… See the full description on the dataset page: https://huggingface.co/datasets/dleemiller/msmarco-bm25-rrf-scored.MRCONSO_RRF_UMLS