Re:Deep Dive into G-Eval: How LLMs Evaluate Themselves
by kirchoni on Wednesday November 05, 2025 @10:50AM
(#45824222)
Interesting overview, though I still wonder how stable G-Eval really is across different model families. Auto-CoT helps with consistency, but I’ve seen drift even between API versions of the same model.
[ Parent
| on HN ]
Re:Deep Dive into G-Eval: How LLMs Evaluate Themselves
by zlatkov on Wednesday November 05, 2025 @10:56AM
(#45824302)
That's true. Even small API or model version updates can shift evaluation behavior. G-Eval helps reduce that variance, but it doesn’t eliminate it completely. I think long-term stability will probably require some combination of fixed reference models and calibration datasets.