onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Researchers introduced onPanda, an interactive tool for annotating LLM alignment data and agent trajectories that uses token-level correction as its core interaction, letting annotators locate the first inappropriate token in a model response and pick a substitute. The tool targets efficient annotation of on-policy alignment data for LLMs and agents.

We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while reading a model response, the annotator locates the first inappropriate token and either picks a substitute from the mode