AI ethics evidence index Search
Source-linked daily record
Evidence record 4110 · automatically gathered

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment

The alignment of Large Language Models (LLMs) for complex reasoning heavily relies on Reinforcement Learning with Verifiable Rewards (RLVR). However, standard algorithms like GRPO apply sequence-level rewards uniformly to all tokens, creating a severe credit-assignment bottleneck. While on-policy self-distillation attempts to resolve this by conditioning a self-teacher on privileged contexts, direct exposure to raw oracle solutions often induces over-conditioned teacher distributions, implicit a

Record details

Published: 18 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Safety & alignment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Also mentions Meta · Shared topic: Regulation

Meta-Aligner: Bidirectional Preference-Policy Optimization for Multi-Objective LLMs Alignment

arXiv · 27 April 2026

Also mentions Meta · Shared topic: Regulation

LWiAI Podcast #252 - GPT 5.6, Grok 4.5, Nemotron-Labs-Diffusion, AI 2040

Last Week in AI · 21 July 2026

Also mentions Meta · Shared topic: Regulation

Algorithmic Constitutionalism

arXiv · 16 May 2026

Also mentions Meta · Shared topic: Safety & alignment

BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH

arXiv · 13 April 2026

Also mentions Meta · Shared topic: Safety & alignment

Meta-Transfer Learning for mmWave Beam Alignment

arXiv · 1 July 2026

Also mentions Meta · Shared topic: Safety & alignment

A systematic review of toxicity in large language models: definitions, datasets, detectors, detoxification methods and challenges

Artificial Intelligence Review · 2 July 2026

How to cite this record

ethics.ai (18 May 2026), “AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment,” evidence record 4110, https://ethics.ai/record/4110 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.