arXiv:2607. 24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem.
arXiv:2607. 26389v1 Announce Type: cross Abstract: Fine-tuning a language model on data containing a narrow flaw, such as insecure code or incorrect mathematical answers, can cause broad misalignment through a mechanism that remains debated.
arXiv:2607. 07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them.
The paper introduces the Core Sentiment Inventory (CSI), a new personality trait evaluation tool for large language models (LLMs) that addresses reliability and validity issues found in existing methods like the Big Five Inventory (BFI). CSI is designed specifically for LLMs, supports both English and Chinese, and provides detailed psychological portraits of model behavior. Experiments show that CSI captures nuanced behavioral patterns, improves reliability, and correlates strongly (above 0.85) with real-world LLM outputs.
arXiv:2608.11025v2 Announce Type: replace Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A...
arXiv:2607. 26853v1 Announce Type: cross Abstract: Human personality theories characterize traits not as isolated attributes captured by a single score, but as stable individual tendencies expressed through the interplay among persons, situations, and behaviors.
Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies.
arXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property...
The study investigates how different prompt components affect language model responses in psychometric tests. By crossing five distinct baseline personas with five variants of each prompt element—persona wording, task instruction, item wording, and option symbol—the authors measure response shifts using the 1‑Wasserstein distance. Their analysis of 13 small open‑weight language models on the Big Five Inventory and Short Dark Triad reveals that task instruction and option symbol changes often cause more variation than paraphrasing the persona or item, with prompt artifacts explaining over 50% of the variation for many items.
The paper introduces TSS (Triple-Stream Stress probe), a diagnostic framework that splits text into lexical, morpho-syntactic, and psycholinguistic style channels to analyze mental health NLP classifiers. Across four English datasets, TSS uncovers a lexical interference effect where adding lexical features harms performance on human-labeled data but not on auto-labeled data, and proposes the Degree of Divergence (DoD) statistic to audit label-source bias. The study demonstrates that style features largely remain effective even after masking content words, emphasizing that shortcut learning is label-source specific rather than clinically relevant.
arXiv:2603. 13891v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation and hiring.
arXiv:2608. 10385v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assessor framing affects judgment reliability and downstream system comparison.
arXiv:2607. 13162v1 Announce Type: cross Abstract: What a language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or resists is not revealed by prompting alone.