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.
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: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: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:2603. 26846v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical.
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.
The paper introduces CoT-Interpretability Alignment (CIA), a metric that quantifies how well a large language model’s chain-of-thought (CoT) explanations match its internal reasoning processes. Evaluated on two-hop question answering, hint intervention, and integer multiplication across three LLMs, the study finds limited alignment (44.8–75.9%) and demonstrates that post‑training with a reward combining task accuracy and parametric faithfulness can substantially improve CoT faithfulness without sacrificing accuracy. The authors provide a framework for auditing CoT faithfulness and a pathway to making explicit reasoning more trustworthy, with code and data publicly available.
arXiv:2607. 22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks.
arXiv:2605.30381v2 Announce Type: replace-cross Abstract: When a language model is fine-tuned to produce systematically incorrect responses, does this training leave a structured, linearly recoverabl...
arXiv:2502. 15543v4 Announce Type: replace-cross Abstract: Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence.
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
arXiv:2605. 24960v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) faithfulness, i.