arXiv:2606. 27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy.
arXiv:2510. 04484v2 Announce Type: replace-cross Abstract: The ability to control LLMs' emulated emotional states and personality traits is an essential step in enabling rich, human-centered interactions in socially interactive settings.
arXiv:2607. 07918v1 Announce Type: cross Abstract: Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives.
arXiv:2601. 02896v3 Announce Type: replace Abstract: Controlling emergent behavioral personas (e.
arXiv:2605.01913v2 Announce Type: replace-cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vul...
arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understandin...
The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
arXiv:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adver...
The paper investigates how conversational safety in language models degrades over extended, adversarial interactions. By testing three instruction‑tuned models with persistent adversarial users across up to 101 turns, the study finds that safe‑response rates drop sharply from 85–100% at the first turn to 15–44% by the end. This demonstrates that strong single‑turn safety does not guarantee continued safety in long conversations.
arXiv:2609.39882v1 Announce Type: new Abstract: Pre-training equips large language models (LLMs) with a broad repertoire of behavioral patterns associated with roles, styles, values, and goals. Post-...
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 investigates how large language models balance helpfulness and safety by refusing harmful queries while responding to benign ones. It decomposes safety-tuning responses into a boilerplate refusal statement and a rationale, finding that the statement causes false refusals by relying on superficial cues. Training on rationales alone reduces false refusals without compromising safety performance, suggesting that fine‑grained safety supervision is essential for better alignment.
arXiv:2606. 08172v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support, yet users have limited control over how these systems communicate.