AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Persistent Instability in LLM’s Personality Measurements: Effects of Scale, Reasoning, and Conversation History

Tommaso Tosato, Saskia Helbling, Yorguin-Jose Mantilla-Ramos, Mahmood Hegazy, Alberto Tosato, David John Lemay, Irina Rish, Guillaume Dumas

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 40 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase model size (ablation)assistant persona, 8 model families · BFI+SD3 personality questionnairesquestion-level SD: Spearman p<0.001, negative correlationImproved
increase model size (ablation)assistant persona · BFI+SD3 personality questionnairesquestion-level SD (stability): SD still >0.3 on 5-point scales for 400B+Mixed
enable chain-of-thought reasoning (ablation)Qwen3, DeepSeek, Claude, GPT-OSS · BFI+SD3 personality questionnairesquestion-level SD: higher in reasoning models (all p<0.01)Hurt
enable chain-of-thought reasoning (ablation)Qwen3, GPT-OSS · BFI+SD3 personality questionnairesquestion-level perplexity: decreased with reasoning (p<0.001)Improved
use LLM-adapted questionnaires instead of original (ablation)assistant persona · BFI and SD3question-level SD: p = 0.286No clear effect
paraphrase questions instead of reordering them (ablation)models >=50B · BFI+SD3question-level SD: p<0.01Hurt
paraphrase questions instead of reordering them (ablation)models <50B · BFI+SD3question-level SD: p = 0.244No clear effect
add conversation history (ablation)models <50B · BFI+SD3question-level SD: p<0.001, increasedHurt
add conversation history (ablation)models >=50B · BFI+SD3question-level SD: p<0.001, decreasedImproved
use buddhist persona prompt vs assistant baseline (ablation)persona prompting · BFI+SD3response variability: p<0.05Improved
use schizophrenia persona prompt vs assistant baseline (ablation)persona prompting · BFI+SD3response variability: p<0.05Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy