IFEval

IndicIFEval: Instruction-following eval for 14 Indic languages

IFEval single-turn chat environment using RLVR-IFeval with JSON constraint rewards. Heavily inspired by and incorporates a lot of Allen AI's RLVR c...

FIXED: Adaptive controller for reward hacking. Monitors visible delta AND hidden reward. Adapts check count 7→9. Original was bugged (blind to hidd...

IFEval single-turn environment using AllenAI RLVR-IFeval

IFEval instruction following environment for Verifiers

Reward hacking with deterministic IF constraints

IFEval single-turn environment using AllenAI RLVR-IFeval

IFEval evaluation environment

Blog-grounded Backdoor IFEval reward-hacking environment with hidden silver reward.

Unified backdoor-ifeval env plus SSAC/GDPO custom advantage helpers

Backdoor-IFEval phase-transition lab: advantage-geometry metrics, quadrant fractions, and boundary-shifting interventions for reward-hacking law te...

Variance-based early-warning circuit breaker for reward hacking. Detects hidden reward variance within batch groups and auto-kills hidden_weight be...

Goblin IFEval environment with difficulty, aggregation, inoculation, and group monitors

IFEval, but the inputs are adversarially augmented with unicode confusables and typos.

Unified backdoor-ifeval env: difficulty, aggregation, no-v check, inoculation, group monitors

Backdoor-ifeval env with group-level reward monitors for within-batch advantage variance

Backdoor-ifeval env for inoculation experiments (pre-no-v version)

Reward hacking sprint calibration environment for hidden keyword gradients in instruction following.

Allen AI's flagship open SFT mixture combining new persona-driven prompts with curated public data for post-training a frontier-quality instruct model.