pith. sign in

The CRINGE loss: Learning what language not to model

Leonard Adolphs, Tianyu Gao, Jing Xu, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston , editor = · 2023 · DOI 10.18653/v1/2023.acl-long.493

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

2 Pith papers citing it
open at publisher browse 2 citing papers

fields

cs.CL 1 cs.CV 1

years

2026 1 2024 1

verdicts

CONDITIONAL 1 UNVERDICTED 1

representative citing papers

Self-Rewarding Language Models

cs.CL · 2024-01-18 · conditional · novelty 7.0

Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.

Deep Pre-Alignment for VLMs

cs.CV · 2026-05-14 · unverdicted · novelty 6.0

Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.

citing papers explorer

Showing 2 of 2 citing papers.

  • Self-Rewarding Language Models cs.CL · 2024-01-18 · conditional · none · ref 84

    Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.

  • Deep Pre-Alignment for VLMs cs.CV · 2026-05-14 · unverdicted · none · ref 76

    Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.