AI ethics evidence index Search
Source-linked daily record
Evidence record 5287 · automatically gathered

Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective

Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak teacher's blind spots. Understanding such failures requires going beyond aggregate accuracy, since weak-to-strong errors depend not only on whether the strong model disagrees with its teacher, but also on how confidence and uncertainty are distributed across examples. In this work, we analyze weak-to-strong alignment through a b

Record details

Published: 28 April 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · 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.

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance

arXiv · 28 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Applications of the Transformer Architecture in AI-Assisted English Reading Comprehension

arXiv · 26 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

A Gated Hybrid Contrastive Collaborative Filtering Recommendation

arXiv · 29 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models

arXiv · 25 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Quantifying and Mitigating Self-Preference Bias of LLM Judges

arXiv · 24 April 2026

Shared topic: Bias & fairness · Shared topic: Safety & alignment

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment

arXiv · 1 May 2026

How to cite this record

ethics.ai (28 April 2026), “Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective,” evidence record 5287, https://ethics.ai/record/5287 (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.