pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.CR 1

years

2026 1 2024 1

representative citing papers

Adaptive Instruction Composition for Automated LLM Red-Teaming

cs.CR · 2026-04-22 · unverdicted · novelty 7.0

Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.

citing papers explorer

Showing 2 of 2 citing papers.

  • ORPO: Monolithic Preference Optimization without Reference Model cs.CL · 2024-03-12 · conditional · none · ref 105

    ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.

  • Adaptive Instruction Composition for Automated LLM Red-Teaming cs.CR · 2026-04-22 · unverdicted · none · ref 16

    Adaptive Instruction Composition uses a neural contextual bandit with RL to adaptively combine crowdsourced texts, generating more effective and diverse LLM jailbreaks than random or prior adaptive methods on Harmbench.