pith. sign in

Safe rlhf: Safe reinforcement learning from human feedback

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

2 Pith papers citing it

citation-role summary

other 1

citation-polarity summary

fields

cs.CL 1 cs.CR 1

years

2026 1 2024 1

verdicts

UNVERDICTED 2

roles

other 1

polarities

unclear 1

representative citing papers

InternLM2 Technical Report

cs.CL · 2024-03-26 · unverdicted · novelty 5.0

InternLM2 is a new open-source LLM that outperforms prior versions on 30 benchmarks and long-context tasks through scaled pre-training to 32k tokens and a conditional online RLHF alignment strategy.

citing papers explorer

Showing 2 of 2 citing papers.

  • MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks cs.CR · 2026-05-10 · unverdicted · none · ref 9

    MT-JailBench is a modular benchmark that standardizes evaluation of multi-turn jailbreaks to identify key success drivers and enable stronger combined attacks.

  • InternLM2 Technical Report cs.CL · 2024-03-26 · unverdicted · none · ref 31

    InternLM2 is a new open-source LLM that outperforms prior versions on 30 benchmarks and long-context tasks through scaled pre-training to 32k tokens and a conditional online RLHF alignment strategy.