Pith. sign in

REVIEW 6 cited by

Exploring the Personality Traits of LLMs through Latent Features Steering

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.10863 v2 pith:J7GAXWBU submitted 2024-10-07 cs.CL cs.AI

Shu Yang , Shenzhe Zhu , Liang Liu , Lijie Hu , Mengdi Li , Di Wang This is my paper
classification cs.CLcs.AI
keywords llmspersonalityfactorsmodeltraitsfeatureslatentmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown that LLMs can exhibit distinct and consistent personalities, the mechanisms through which these models encode and express specific personality traits remain poorly understood. To address this, we investigate how various factors, such as cultural norms and environmental stressors, encoded within LLMs, shape their personality traits, guided by the theoretical framework of social determinism. Inspired by related work on LLM interpretability, we propose a training-free approach to modify the model's behavior by extracting and steering latent features corresponding to factors within the model, thereby eliminating the need for retraining. Furthermore, we analyze the implications of these factors for model safety, focusing on their impact through the lens of personality.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

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

  1. AISPA: User-Centric System Prompt Auditing for Large Language Model Applications

    cs.AI 2026-07 conditional novelty 6.5 of 10

    A human-in-the-loop audit of system prompts from 88 commercial AI products finds protective instructions nearly universal yet incomplete, with ~40% of products containing at least one user-harmful directive.

  2. COMPKE: Complex Question Answering under Knowledge Editing

    cs.CL 2025-06 conditional novelty 6.0 of 10

    COMPKE is a new benchmark with 11,924 complex questions that tests knowledge editing through one-to-many relations and logical operations, where existing editing methods often fail.

  3. Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons

    cs.CL 2025-06 reject novelty 6.0 of 10

    Cross-lingual privacy leakage in LLMs is driven by a mix of language-universal and language-specific neurons, and deactivating those neurons lowers measured leakage by 23.3% to 31.6%.

  4. The Compositional Architecture of Regret in Large Language Models

    cs.CL 2025-06 reject novelty 5.0 of 10

    The paper claims that regret in LLMs is encoded by interacting neuron groups detectable in the final hidden layer, using new S-CDI, RDS, and GIC metrics.

  5. Supernova Event Dataset: Interpreting Large Language Models' Personality through Critical Event Analysis

    cs.CL 2025-06 reject novelty 5.0 of 10

    LLMs asked to rank critical events in articles show different, consistent event-selection styles that the authors label as personality traits using an LLM judge.

  6. Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images

    cs.AI 2025-06 reject novelty 4.0 of 10

    SHE lowers behavioral hallucination scores by about 10 percent by detecting low visual-textual similarity and projecting out the hallucinated direction in embedding space.

Pith tools