Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs · HackerPapers discussions

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs — mentioned by Der_Einzige

Sun, 04 May 2025 17:35:06 GMT

Related to this, our min_p paper was ranked #18 out of 12000 submission at ICLR and got an oral: https://iclr.cc/virtual/2025/oral/31888 Our poster was popular: poster: https://iclr.cc/media/PosterPDFs/ICLR%202025/30358.png?t=174... oral presentation (watch me roast yoshua bengio on this topic and then have him be the first questioner, 2nd speaker starting around 19:30 min mark. My slides for the presentation are there too and really funny.): https://iclr.cc/virtual/2025/session/31936 paper: https://arxiv.org/abs/2407.01082 As one of the min_p authors, I can confirm that Top N sigma is…

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

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs — HN submission

Tue, 11 Feb 2025 18:12:21 GMT

Turning Up the Heat: Min-P Sampling for Creative and Coherent LLM Outputs

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs — mentioned by Der_Einzige

Mon, 03 Feb 2025 18:31:16 GMT

You and the OP talk a lot of smack about logprobs but we show that using them in even the simple case of dynamic truncation of your cutoff point (min_p sampler vs static top_p/top_k) leads to extreme performance improvements (especially on small models) and unlocks very high temperature sampling (for more creativity/less slop/better synthetic data-gen): https://arxiv.org/abs/2407.01082 [1]. Indeed, ultra high temperature sampling in its own right should be studied. I can do top_k = 2 and temperature = system.maxint and get decent results which are extraordinarily creative (with increasing…

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

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs — mentioned by NitpickLawyer

Sat, 26 Oct 2024 09:19:17 GMT

Is this [1] the paper you're referring to? Unless I'm reading Table2 (page7 - pdf version) wrong, on math, min_p is shown to score worse than top_p. For temp 0.7 it scores 1 point lower than top_p. And from temps 1.0 and up, while scoring higher than top_p for the same temp, it scores way lower (6points and up) than top_p at 0.7. So overall, if you want accurate answers (and for math you kinda do), min_p is worse overall? Unless I miss-understand something. I agree with the authors that if you want a tradeoff between accuracy and diversity, min_p might help, but if you're looking for precise…

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

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs — HN submission

Fri, 23 Aug 2024 22:52:44 GMT

Higher Temperatures and Min_p Sampling

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs — HN submission

Thu, 22 Aug 2024 06:45:57 GMT

Min P Sampling: Balancing Creativity and Coherence at High Temperature

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.