arXiv AI
Benevolent Bias in Multi-Turn Human-Agent Dialogue
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 14
Unmasking Conversational Bias in AI Multiagent Systems
arXiv:2501. 14844v3 Announce Type: replace-cross Abstract: Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings.
arXiv AI
Jun 19
DeFrame: Debiasing Large Language Models Against Framing Effects
arXiv:2602. 04306v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial.
arXiv AI
Sep 15
How User-AI Mistreatment Occurs and Matters in Conversational Systems?
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...
arXiv AI
Oct 15
Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment
arXiv:2610.15961v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now...
arXiv Computation and Language
Sep 17
DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions
arXiv:2609.18649v1 Announce Type: new Abstract: Warning: This paper contains examples of stereotypes and social bias. LLMs are increasingly used in interactive settings by the general public, making...
arXiv AI
Sep 24
Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures
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.