method · first seen 12 Oct 2026
instruction tuning
Also: instruction fine-tuning
Fine-tuning language models on instruction-response pairs to follow user directions.
Mentions per week
PapersCodeDiscussion
Rank 138 on 2 Nov 2026 · 14 mentions in 28 days · 14 independent groups · papers · first seen 3 weeks ago · acceleration -0.82
Earliest sources
- The Format is the Filter: Scoring Format Fixes What an LLM Judge Can ExpressPapers · 12 Oct 2026 · Lovedeep Gondara, Jekaterina Novikova, Sagarika Suresh, Jack Ji, Jithin Pradeep
- Towards Efficient Threat Intelligence Instruction Tuning via Quality-Aware and Optimal Transport-Guided Data SelectionPapers · 14 Oct 2026 · Jiyu Tian, Mingchu Li, Xiangwei Chen, Liming Chen
- Wolof-Adapted Industry-Ready Open-Weight Language ModelsPapers · 14 Oct 2026 · Gwénolé Lecorvé, Delphine Charlet, Pierre Adam, Floriane Behanzin, Lionel Del…
- Cultural (In)Competence: Investigating Culture-Specific Stereotype Detection Capabilities of LLMsPapers · 15 Oct 2026 · Maximilian Spliethöver, Jannes Lötfering, Dominik Bachmann, Alexander Espig, W…
- The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned CounterpartsPapers · 20 Oct 2026 · Christophe Khalil, Aya Mourad
- Where Do LLMs Learn to Recommend AI?Papers · 21 Oct 2026 · Benaya Trabelsi, Jonathan Shaki, Sarit Kraus
Latest sources
- Query-based Submodular Data Selection for Efficient Instruction TuningPapers · 2 Nov 2026 · Zhenghao Zhao, Yasutomo Kawanishi, Huihuo Zheng, Michael E. Papka, Yan Yan
- TrafficInstruct: A Multi-Task Network Traffic Dataset and Benchmark for Instruction TuningPapers · 2 Nov 2026 · Zhengdao Li, Hui Wen, Zixuan Wan, Weifeng Zhang, Yan Wu, Benlong Wu, Nenghai Yu,…
- 3, 7, 14, 17, 42: Instruction Tuning Installs and Sharpens Number-Choice Heuristics in Language ModelsPapers · 26 Oct 2026 · Samar Ansari
- Synthetic Child-Adult Interactions Are Not Developmentally PlausiblePapers · 26 Oct 2026 · Bastian Bunzeck, Francesca Padovani
- "High-Quality" Data for Early-Stage Instruction Tuning: An Empirical Study of Data Quality MetricsPapers · 25 Oct 2026 · Vladimir Necula, David Gvadzabia, Sofia Serrano
- The Language of Instruction: Genre and Generative AIPapers · 23 Oct 2026 · James E. Dobson
- Task-Preserving Multilingual Instruction Tuning for Open-Ended QA in WMT 2026 MISTPapers · 21 Oct 2026 · Aleix Sant, Jordi Luque, Carlos Escolano
- Characterizing and Defending Utility-Hijacking in Instruction-Tuning Data SelectionPapers · 21 Oct 2026 · Yahao Ren, Jian Lou, Huadi Zheng, Jiawei Duan
- Where Do LLMs Learn to Recommend AI?Papers · 21 Oct 2026 · Benaya Trabelsi, Jonathan Shaki, Sarit Kraus
- The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned CounterpartsPapers · 20 Oct 2026 · Christophe Khalil, Aya Mourad
- Cultural (In)Competence: Investigating Culture-Specific Stereotype Detection Capabilities of LLMsPapers · 15 Oct 2026 · Maximilian Spliethöver, Jannes Lötfering, Dominik Bachmann, Alexander Espig, W…
- Wolof-Adapted Industry-Ready Open-Weight Language ModelsPapers · 14 Oct 2026 · Gwénolé Lecorvé, Delphine Charlet, Pierre Adam, Floriane Behanzin, Lionel Del…