DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data · HackerPapers discussions

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data — mentioned by dvrp

Wed, 30 Apr 2025 09:27:28 GMT

seems like it's not a new 671 B behemoth, just the V3 MoE engine with long-context RoPE + FA2, retargeted at theorem proving. see [1,2]: [1]: https://arxiv.org/abs/2405.14333 [2]: https://arxiv.org/abs/2408.08152

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

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data — mentioned by binarymax

Sat, 29 Mar 2025 23:02:28 GMT

They talk about some examples in their research. > “Specifically, we initialized the DeepSeek-Prover using the DeepSeekMath-Base 7B model (Shao et al., 2024). Initially, the model struggled to convert informal math problems into formal statements. To address this, we fine-tuned the DeepSeek-Prover model using the MMA dataset (Jiang et al., 2023), which comprises formal statements from Lean 4’s mathlib2 that were back-translated into natural language problem descriptions by GPT-4. We then instructed the model to translate these natural language problems into formal statements in Lean 4 using a…

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

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data — HN submission

Mon, 14 Oct 2024 15:44:04 GMT

DeepSeek: Advancing theorem proving in LLMs through large-scale synthetic data

186 points; 54 discussion replies on HN. Paper and source history. A submission is not an endorsement.

DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data — HN submission

Sun, 26 May 2024 07:31:49 GMT

Advancing Theorem Proving in LLMs Through Large-Scale Synthetic Data

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