LM Playschool Workshop on Oct 28: How Dialogue Interaction Improves Language Models
PMinervini · x · 2026-09-30
The LM Playschool Workshop runs October 28, focused on improving language models through learning from dialogue interaction.
- Joyce Chai (University of Michigan, ACL Fellow) gives an invited talk on language learning through social and embodied experience, presenting an interactive learning paradigm where teacher demonstrations, corrective feedback, and active student trials enable efficient word learning in models.
- Abdellah Fourtassi (Aix-Marseille University) speaks on how children's turn-taking, contingent responses, and multimodal behavior reshape the evidence available for learning, eliciting adapted input, feedback, alignment, and repair.
The retweeter suggests testing related work on their Playpen environment.
More from Research
- CLM ships Day 1 support for Pi-agent via one npm install — RulinShao · 2026-09-30
- Scaffolded DNA Computer Does 100-bit Addition Without Electricity, Published in Nature — jiqizhixin · 2026-09-30
- Daily probes across 34 LLM APIs catch DeepSeek reasoner's silent 10x token spike — Electrical_Rip892 · 2026-09-30
- Preprint: stop using PCA on LLM item embeddings — EGA recovers structure 97.6-100% of the time — GolinoHudson · 2026-09-30
- Benchmark scores move 39 points on harness alone — a 28-min guide to building your own evals — ghumare64 · 2026-09-30
- Forcing Gemma 4B to output unseen Simple Wikipedia bigrams makes it typo constantly — cephaloform · 2026-09-30