AI ethics evidence index Search
Source-linked daily record
Evidence record 4596 · automatically gathered

Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs

While recent self-training approaches have reduced reliance on human-labeled data for aligning LLMs, they still face critical limitations: (i) sensitivity to synthetic data quality, leading to instability and bias amplification in iterative training; (ii) ineffective optimization due to a diminishing gap between positive and negative responses over successive training iterations. In this paper, we propose Team-based self-Play with dual Adaptive Weighting (TPAW), a novel self-play algorithm desig

Record details

Published: 11 May 2026
Source: arXiv
Category: Research
Topics: Bias & fairness
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

Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI

arXiv · 11 May 2026

Shared topic: Bias & fairness

StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs

arXiv · 11 May 2026

Shared topic: Bias & fairness

DuetFair: Coupling Inter- and Intra-Subgroup Robustness for Fair Medical Image Segmentation

arXiv · 11 May 2026

Shared topic: Bias & fairness

Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems

arXiv · 11 May 2026

Shared topic: Bias & fairness

Preparing Students for AI-Powered Materials Discovery: A Workflow-Aligned Framework for AI Literacy, Equity, and Scientific Judgment

arXiv · 10 May 2026

Shared topic: Bias & fairness

When to Ask a Question: Understanding Communication Strategies in Generative AI Tools

arXiv · 11 May 2026

How to cite this record

ethics.ai (11 May 2026), “Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs,” evidence record 4596, https://ethics.ai/record/4596 (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.