trends.barnas.net

method · first seen 8 Oct 2026

post-training

Also: RLHF-style fine-tuning, domain-specialized large language model fine-tuning, reinforcement learning fine-tuning of language models

Stage of model development applying fine-tuning and alignment after pretraining to improve behavior.

Mentions per week

0319 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Rank 187 on 11 Nov 2026 · 8 mentions in 28 days · 8 independent groups · papers → code → discussion · first seen 5 weeks ago · acceleration +0.00

Earliest sources

Latest sources

Mentioned together with

social bias in large language modelsretrieval-augmented generationsign language translationdirect preference optimizationtraining data detectionknowledge distillationrecursive self-improvementlow-rank adaptationgroup-relative baseline subtractionpruning