pith. sign in

arxiv: 2508.06482 · v2 · pith:X32UB375new · submitted 2025-08-08 · 💻 cs.CL · cs.AI· cs.LG

Post-training for Efficient Communication via Convention Formation

classification 💻 cs.CL cs.AIcs.LG
keywords conventionformationbehaviordevelopfocusedhumansllmspost-training
0
0 comments X
read the original abstract

Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contrast, prior work shows that LLMs do not naturally show this behavior. We develop a post-training process to develop this ability through targeted fine-tuning on heuristically identified demonstrations of convention formation. We evaluate with two new benchmarks focused on this capability. First, we design a focused, cognitively-motivated interaction benchmark that consistently elicits strong convention formation trends in humans. Second, we create a new document-grounded reference completion task that reflects in-the-wild convention formation behavior. Our studies show significantly improved convention formation abilities in post-trained LLMs across the two evaluation methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LVLMs and Humans Ground Differently in Referential Communication

    cs.CL 2026-01 unverdicted novelty 7.0

    LVLMs and humans build common ground differently in referential tasks, with LVLMs failing to enable smooth interactive communication in a new corpus of 356 dialogues.