Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation — mentioned by sanxiyn

Thu, 06 Feb 2025 09:01:51 GMT

LLMs actually do have such hunch, they just don't utilize it. You can literally ask them "Would you do better if you started over?" and start over if answer is yes. This works. https://arxiv.org/abs/2410.02725

Paper and discussion history. A mention is not an endorsement.

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation · HackerPapers discussions

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation — mentioned by sanxiyn