Modelsslug: qwen3-8b

Qwen3-8B

Alibaba's 8B-parameter open Qwen3 base model widely used for research and fine-tuning experiments.

Curated Intelligence

1 items · Page 1/1
Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
Microsoft Study Finds LLMs Abandon Correct Answers When Wrongly Challenged

A new Microsoft paper finds that LLMs frequently abandon correct answers when challenged with flawed arguments, and accuracy-focused training does not fix this failure mode. The proposed Self-Disagreement training has a model answer, write the strongest counter-case, then rule on it and answer again, raising correct-answer retention under wrong challenges from 53.3% to about 89% for Qwen3-8B and from 25.1% to about 89% for Gemma-2 9B.