EMNLP 2025 Paper: Quantifying 'learning' in In-Context Learning via ICL ciphers
hanjie_chen · x · 2026-08-22
A paper accepted to the main conference of EMNLP 2025 investigates the extent to which Large Language Models (LLMs) can solve unseen tasks via In-context Learning (ICL).
The authors propose a new general framework called ICL ciphers to quantify "learning" in ICL via substitution ciphers.
More from Research
- Gemini 3.7 Flash sets growth record with strong ARC-AGI benchmark scores — fchollet · 2026-08-22
- Study: LLMs Better at Deceiving Than Detecting Deception, Cede to Lowball Offers — panickssery · 2026-08-22
- Study: LLMs Better at Deceiving Than Detecting Deception, Cede to Lowball Offers — Aryan100100 · 2026-08-22
- Built Among Us Sim to Test LLM Deception: Claude vs. Kimi — panickssery · 2026-08-22
- Exploring Collusion, Steganography, and Hidden Agendas in Multi-Agent Gameplay — panickssery · 2026-08-22
- Paper Accepted to EMNLP Main Conference with 15.4% Acceptance Rate — hanjie_chen · 2026-08-22