arXiv AI
Explaining Intrinsic Moral Self-Correction with Mechanistic Interpretability
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 20
Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
arXiv:2510. 12229v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have been shown to internalize human-like biases during finetuning, yet the mechanisms by which these biases manifest remain unclear.
arXiv AI
Jun 16
Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning
arXiv:2606. 15507v1 Announce Type: new Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it.
arXiv AI
Sep 1
TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback
arXiv:2608.28610v1 Announce Type: new Abstract: Existing LLM moral evaluations typically present models with isolated moral vignettes and elicit a single-shot decision, neglecting a factor known to p...
arXiv AI
Sep 4
Representational alignment yields generalizable safety in language models
The paper argues that aligning large language models (LLMs) at the level of latent representations—specifically by matching their internal categorization of moral concepts to human prototype-based judgments—improves safety. Current alignment methods that focus on observable responses fail to preserve fine-grained moral categorization, leaving models vulnerable to adversarial rephrasings. By optimizing representational similarity, the authors demonstrate that LLMs can maintain more robust moral categorization and exhibit better adversarial robustness across multiple benchmarks and model sizes.
arXiv AI
Jun 12
LLMs Can Better Capture Human Judgments--With the Right Prompts
arXiv:2606. 12754v1 Announce Type: cross Abstract: Are large language models (LLMs) bad at capturing human judgment?
arXiv AI
Aug 14
Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).