Unverified50% confidenceFactExact time
The research team conducted fine-tuning experiments on two models, Qwen3.5-9B and Gemma4-12B-it.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
Sources
Related Entities
Related Claims
UnverifiedIn the sleeper-agent backdoor scenario, the research team fine-tuned gemma-2-2b, Qwen2.5-1.5B and Qwen2.5-7B respectively on a poisoned instruction-following dataset to build model organisms.77% similarUnverifiedThe Jeff project distilled and fine-tuned two base models, Qwen3.5 and Gemma 4, into decision models with 0.8B and 2B parameters respectively.76% similarUnverifiedOn Gemma-2-9B and Qwen3-14B, the researchers successfully switched the facts read by the model by modifying early internal activation vectors while keeping the written instructions unchanged.76% similarUnverifiedTEFM was tested on multiple mainstream large language models including Qwen3, Gemma-2, and Phi-4, achieving consistent performance improvements and demonstrating its model-agnostic nature.73% similarUnverifiedThe author used the Qwen3-1.7B model for both generation and attribution analysis tasks.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102030API
curl https://kongchang.com/api/v1/knowledge/claims/1102030MCP
get_claim(id=1102030)