abstention
AbstentionBenchAbstentionBench is a benchmark for the holistic evaluation of abstention capabilities in frontier LLMs.Nemotron-RL-QA-Abstention-v1Nemotron-RL-QA-Abstention-v1
License: cc-by-4.0
Language: en
Task Categories: reinforcement-learning, question-answering, text-generation
Tags: abstention, question-answering, hotpotqa, software-engineering, health, law, rl, rlvr
Configs: default train split at data/train.jsonl
Domain: multi-domain question answering, abstention
Modality: text
Capability Breakdown: Abstention-aware factoid question answering [100%]
Source: Hybrid: Automated, Manually Collected, Synthetic
Size Bin: <10K… See the full description on the dataset page: https://huggingface.co/datasets/nvidia/Nemotron-RL-QA-Abstention-v1.compression-aware-abstention-data
Compression-Aware Abstention — labeled datasets
Compression-labeled training and evaluation data for "Compression-Aware
Abstention" (GroundLM @ EMNLP 2026). Derived from MuSiQue 2-hop QA
(CC BY 4.0, Trivedi et al., TACL 2022).
Each record pairs a MuSiQue example with a KV-cache compressor's per-token
survival mask at one of six retention ratios, plus the label that mask implies.
Fields
Field
Meaning
id
MuSiQue example id (2hop__*)
ratio
Target… See the full description on the dataset page: https://huggingface.co/datasets/moalikhoda/compression-aware-abstention-data.glm52-datagen-r11-114-qa-abstention-v2-traceseh-abstention-wide-instrument-calibration
abstention-wide-instrument-calibration -- aggregate exhaust
Aggregate-only: every file committed under this experiment's analysis-committed/ tree (dose-response tables, direction fits, gate AUROCs, manifests, and any other analysis artifact), copied byte-for-byte. No source question text, aliases, or per-row generation text -- analysis-committed/ never carries those.
HF repo: professorsynapse/eh-abstention-wide-instrument-calibration
Provenance
Experiment:… See the full description on the dataset page: https://huggingface.co/datasets/professorsynapse/eh-abstention-wide-instrument-calibration.eh-no-abstention-prompt-gated-replication
no-abstention-prompt-gated-replication -- aggregate exhaust
Aggregate-only: every file committed under this experiment's analysis-committed/ tree (dose-response tables, direction fits, gate AUROCs, manifests, and any other analysis artifact), copied byte-for-byte. No source question text, aliases, or per-row generation text -- analysis-committed/ never carries those.
HF repo: professorsynapse/eh-no-abstention-prompt-gated-replication
Provenance
Experiment:… See the full description on the dataset page: https://huggingface.co/datasets/professorsynapse/eh-no-abstention-prompt-gated-replication.