question
active
question:how-do-character-traits-develop-over-the-course-of-an-lm-interactionHow do character traits develop over the course of an LM interaction?
Core empirical question motivating Section 5 on stationary and reflective traits.
Source paper
extracted_from(2024) · Francis Rhys Ward · Zejia Yang · Alex Jackson · Randy A. Brown +6
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Empirical question answered through experiments on model size, fine-tuning, and prompting.
- Finding replicated across multiple experiments.
- The paper's central contribution: a formal behaviourist framework for attributing character traits to LMs based on input-output behaviour.
- Conceptual open question about formalizing the persona abstraction beyond the trait level
- Driving hypothesis for robustness experiments in Section 3.2
- Do LLM minds always persist through entire conversations despite radical behavioral changes?question0.766Diachronic aspect of the individuation problem about persistence through token-time
- Character training induces convergence in trait preferences across different initial modelsclaim0.752Claim supported by Spearman correlation increase from 0.44 to 0.87 across three models after loving persona training
- Understanding how LMs learn linguistic behaviours may offer insights into fundamental properties of languagehypothesis0.752Forward-looking hypothesis linking LM mechanism analysis to linguistic theory