arXiv AI
Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Jun 17
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment.
Hugging Face Trending Papers
Aug 5
Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation process can also degrade alignment properties that were present in the source model.
arXiv AI
Sep 10
Compliance vs. Sensibility: On the Reasoning Controllability in Large Language Models
arXiv:2604.27251v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicite...
arXiv Machine Learning
Aug 6
Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning
arXiv:2608. 04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence.
arXiv AI
Jun 8
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
arXiv:2603. 26846v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical.
arXiv AI
Sep 17
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
The paper introduces "cunning questions"—non‑safety prompts that contain misleading premises or subtle inconsistencies—to train large language models (LLMs) to scrutinize underlying intent and assumptions. Experiments show that incorporating these questions improves robustness against out‑of‑distribution jailbreak attacks and enhances subsequent safety fine‑tuning, achieving a new state‑of‑the‑art reduction in mean ASR from 17.40% to 15.05% across nine backbone–benchmark combinations. The authors argue that this training fosters vigilance, enabling models to prioritize safety judgments before engaging in harmful planning.