# Supervised Seeded Iterated Learning for Interactive Language Learning

arXiv: https://arxiv.org/abs/2010.02975 · HTML: https://mlsanity.com/paper/2010.02975/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [Multi-label Iterated Learning for Image Classification with Label Ambiguity](https://mlsanity.com/paper/2111.12172/) (2021)
- [Eliciting the Priors of Large Language Models using Iterated In-Context Learning](https://mlsanity.com/paper/2406.01860/) (2024)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction](https://mlsanity.com/paper/2510.20411/) (2025)
- [Streaming Self-Training via Domain-Agnostic Unlabeled Images](https://mlsanity.com/paper/2104.03309/) (2021)
- [Word frequency-rank relationship in tagged texts](https://mlsanity.com/paper/2102.10992/) (2021)

## Abstract (arXiv)

Language drift has been one of the major obstacles to train language models through interaction. When word-based conversational agents are trained towards completing a task, they tend to invent their language rather than leveraging natural language. In recent literature, two general methods partially counter this phenomenon: Supervised Selfplay (S2P) and Seeded Iterated Learning (SIL). While S2P jointly trains interactive and supervised losses to counter the drift, SIL changes the training dynamics to prevent language drift from occurring. In this paper, we first highlight their respective weaknesses, i.e., late-stage training collapses and higher negative likelihood when evaluated on human corpus. Given these observations, we introduce Supervised Seeded Iterated Learning to combine both methods to minimize their respective weaknesses. We then show the effectiveness of algo in the language-drift translation game.