Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
- URL: http://arxiv.org/abs/2404.07382v2
- Date: Sun, 21 Jul 2024 00:10:34 GMT
- Title: Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
- Authors: Chenyang An, Zhibo Chen, Qihao Ye, Emily First, Letian Peng, Jiayun Zhang, Zihan Wang, Sorin Lerner, Jingbo Shang,
- Abstract summary: We demonstrate the benefit of training models that additionally learn from failed search paths.
Facing the lack of such trial-and-error data in existing open-source theorem-proving datasets, we curate a dataset on intuitionistic propositional logic theorems.
We compare our model trained on relatively short trial-and-error information (TrialMaster) with models trained only on the correct paths and discover that the former solves more unseen theorems with lower trial searches.
- Score: 41.23045212775232
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent advances in Automated Theorem Proving have shown the effectiveness of leveraging a (large) language model that generates tactics (i.e. proof steps) to search through proof states. The current model, while trained solely on successful proof paths, faces a discrepancy at the inference stage, as it must sample and try various tactics at each proof state until finding success, unlike its training which does not incorporate learning from failed attempts. Intuitively, a tactic that leads to a failed search path would indicate that similar tactics should receive less attention during the following trials. In this paper, we demonstrate the benefit of training models that additionally learn from failed search paths. Facing the lack of such trial-and-error data in existing open-source theorem-proving datasets, we curate a dataset on intuitionistic propositional logic theorems and formalize it in Lean, such that we can reliably check the correctness of proofs. We compare our model trained on relatively short trial-and-error information (TrialMaster) with models trained only on the correct paths and discover that the former solves more unseen theorems with lower trial searches.
Related papers
- Lean-STaR: Learning to Interleave Thinking and Proving [53.923617816215774]
We present Lean-STaR, a framework for training language models to produce informal thoughts prior to each step of a proof.
Lean-STaR achieves state-of-the-art results on the miniF2F-test benchmark within the Lean theorem proving environment.
arXiv Detail & Related papers (2024-07-14T01:43:07Z) - Proving Theorems Recursively [80.42431358105482]
We propose POETRY, which proves theorems in a level-by-level manner.
Unlike previous step-by-step methods, POETRY searches for a sketch of the proof at each level.
We observe a substantial increase in the maximum proof length found by POETRY, from 10 to 26.
arXiv Detail & Related papers (2024-05-23T10:35:08Z) - MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data [85.50740598523818]
MUSTARD is a framework that masters uniform synthesis of theorem and proof data of high quality and diversity.
We present a theorem-and-proof benchmark MUSTARDSAUCE with 5,866 valid data points.
We perform extensive analysis and demonstrate that MUSTARD generates validated high-quality step-by-step data.
arXiv Detail & Related papers (2024-02-14T05:57:58Z) - Enhancing Neural Theorem Proving through Data Augmentation and Dynamic
Sampling Method [1.8130068086063336]
We introduce DS-Prover, a novel dynamic sampling method for theorem proving.
We augment the training dataset by decomposing simplification and rewrite tactics with multiple premises into tactics with single premises.
We achieve a state-of-the-art performance (Pass@1) of 14.2% on the ProofNet dataset and a performance of 29.8% on MiniF2F.
arXiv Detail & Related papers (2023-12-20T09:55:21Z) - A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning.
Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
arXiv Detail & Related papers (2023-11-14T07:13:10Z) - Generating Natural Language Proofs with Verifier-Guided Search [74.9614610172561]
We present a novel stepwise method NLProofS (Natural Language Proof Search)
NLProofS learns to generate relevant steps conditioning on the hypothesis.
It achieves state-of-the-art performance on EntailmentBank and RuleTaker.
arXiv Detail & Related papers (2022-05-25T02:22:30Z) - Proving Theorems using Incremental Learning and Hindsight Experience
Replay [45.277067974919106]
We propose a general incremental learning algorithm for training domain specific provers for first-order logic without equality.
We adapt hindsight experience replay to theorem proving, so as to be able to learn even when no proof can be found.
We show that provers trained this way can match and sometimes surpass state-of-the-art traditional provers on the TPTP dataset.
arXiv Detail & Related papers (2021-12-20T16:40:26Z) - "Adversarial Examples" for Proof-of-Learning [32.438181794551035]
Jia et al. proposed a new concept/mechanism named proof-of-learning (PoL)
PoL allows a prover to demonstrate ownership of a machine learning model by proving integrity of the training procedure.
We show that PoL is vulnerable to "adrialversa examples"
arXiv Detail & Related papers (2021-08-21T07:56:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.