benchmark · first seen 4 Oct 2026
instruction following evaluation
Also: IFEval, instruction following benchmark
Benchmark measuring whether language models follow verifiable formatting and content instructions in prompts.
Mentions per week
PapersCodeDiscussion
Earliest sources
- When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction FollowingPapers · 4 Oct 2026 · Qishi Zhan, Seoyeon Jang, Zihan Dong, Minxuan Hu, Ziheng Chen, Tonghui Qu
- sk-bench: A Native-First Benchmark for Evaluating Large Language Models in SlovakPapers · 6 Oct 2026 · Marek Šuppa, Ivan Vykopal, Andrej Ridzik, Kristián Sopkovič, Natália Kňaže…
- Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered StudyPapers · 9 Oct 2026 · Sangdo Han, Moonsoo Kim
- LIFT: Scoped Constraints for Evaluating and Training Instruction FollowingPapers · 20 Oct 2026 · Eran Goldstein, Yuval Belfer, Yonatan Belinkov, Daniel Gissin
Latest sources
- LIFT: Scoped Constraints for Evaluating and Training Instruction FollowingPapers · 20 Oct 2026 · Eran Goldstein, Yuval Belfer, Yonatan Belinkov, Daniel Gissin
- Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered StudyPapers · 9 Oct 2026 · Sangdo Han, Moonsoo Kim
- sk-bench: A Native-First Benchmark for Evaluating Large Language Models in SlovakPapers · 6 Oct 2026 · Marek Šuppa, Ivan Vykopal, Andrej Ridzik, Kristián Sopkovič, Natália Kňaže…
- When Verifiable Counts Depend on Wording: Auditing Wording Robustness in Instruction FollowingPapers · 4 Oct 2026 · Qishi Zhan, Seoyeon Jang, Zihan Dong, Minxuan Hu, Ziheng Chen, Tonghui Qu