LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions

• URL: http://arxiv.org/abs/2211.08671v1
• Date: Wed, 16 Nov 2022 04:59:08 GMT
• Title: LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractions
• Authors: Zhening Li, Gabriel Poesia, Omar Costilla-Reyes, Noah Goodman, Armando Solar-Lezama
• Abstract summary: Learning Mathematical Abstractions (LEMMA) is an algorithm that implements this idea for reinforcement learning agents in mathematical domains. We evaluate LEMMA on two mathematical reasoning tasks--equation solving and fraction simplification--in a step-by-step fashion.
• Score: 13.69691843677107
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans tame the complexity of mathematical reasoning by developing hierarchies of abstractions. With proper abstractions, solutions to hard problems can be expressed concisely, thus making them more likely to be found. In this paper, we propose Learning Mathematical Abstractions (LEMMA): an algorithm that implements this idea for reinforcement learning agents in mathematical domains. LEMMA augments Expert Iteration with an abstraction step, where solutions found so far are revisited and rewritten in terms of new higher-level actions, which then become available to solve new problems. We evaluate LEMMA on two mathematical reasoning tasks--equation solving and fraction simplification--in a step-by-step fashion. In these two domains, LEMMA improves the ability of an existing agent, both solving more problems and generalizing more effectively to harder problems than those seen during training.

Related papers

• LeanAgent: Lifelong Learning for Formal Theorem Proving [85.39415834798385]
  We present LeanAgent, a novel lifelong learning framework for formal theorem proving. LeanAgent continuously generalizes to and improves on ever-expanding mathematical knowledge. It successfully proves 155 theorems previously unproved formally by humans across 23 diverse Lean repositories.
  arXiv  Detail & Related papers  (2024-10-08T17:11:24Z)
• Give me a hint: Can LLMs take a hint to solve math problems? [0.5742190785269342]
  We propose giving "hints" to improve the language model's performance on advanced mathematical problems. We also test robustness to adversarial hints and demonstrate their sensitivity to them.
  arXiv  Detail & Related papers  (2024-10-08T11:09:31Z)
• Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning [30.40415945003794]
  We investigate the compositionality of large language models (LLMs) in mathematical reasoning. Since problems with logical flaws are quite rare in the real world, these represent "unseen" cases to LLMs. Our experiments show that while LLMs possess both components of requisite knowledge, they do not textbfspontaneously combine them to handle these novel cases.
  arXiv  Detail & Related papers  (2024-05-05T16:35:30Z)
• GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers [68.77382332826167]
  Large language models (LLMs) have achieved impressive performance across various mathematical reasoning benchmarks. One essential and frequently occurring evidence is that when the math questions are slightly changed, LLMs can behave incorrectly. This motivates us to evaluate the robustness of LLMs' math reasoning capability by testing a wide range of question variations.
  arXiv  Detail & Related papers  (2024-02-29T15:26:14Z)
• AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph [62.685920585838616]
  abstraction ability is essential in human intelligence, which remains under-explored in language models. We present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge.
  arXiv  Detail & Related papers  (2023-11-15T18:11:23Z)
• Faith and Fate: Limits of Transformers on Compositionality [109.79516190693415]
  We investigate the limits of transformer large language models across three representative compositional tasks. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. Our empirical findings suggest that transformer LLMs solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching.
  arXiv  Detail & Related papers  (2023-05-29T23:24:14Z)
• Peano: Learning Formal Mathematical Reasoning [35.086032962873226]
  General mathematical reasoning is computationally undecidable, but humans routinely solve new problems. We posit that central to both puzzles is the structure of procedural abstractions underlying mathematics. We explore this idea in a case study on 5 sections of beginning algebra on the Khan Academy platform.
  arXiv  Detail & Related papers  (2022-11-29T01:42:26Z)
• Learning to Reason With Relational Abstractions [65.89553417442049]
  We study how to build stronger reasoning capability in language models using the idea of relational abstractions. We find that models that are supplied with such sequences as prompts can solve tasks with a significantly higher accuracy.
  arXiv  Detail & Related papers  (2022-10-06T00:27:50Z)
• JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding [74.12405417718054]
  This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model(PLM) Unlike other standard NLP tasks, mathematical texts are difficult to understand, since they involve mathematical terminology, symbols and formulas in the problem statement. We design a novel curriculum pre-training approach for improving the learning of mathematical PLMs, consisting of both basic and advanced courses.
  arXiv  Detail & Related papers  (2022-06-13T17:03:52Z)
• A Theory of Abstraction in Reinforcement Learning [18.976500531441346]
  In this dissertation, I present a theory of abstraction in reinforcement learning. I first offer three desiderata for functions that carry out the process of abstraction. I then present a suite of new algorithms and analysis that clarify how agents can learn to abstract according to these desiderata.
  arXiv  Detail & Related papers  (2022-03-01T12:46:28Z)
• Contrastive Reinforcement Learning of Symbolic Reasoning Domains [0.0]
  Learning to solve symbolic problems is challenging for machine learning algorithms. Existing models either learn from human solutions or use hand-engineered features, making them expensive to apply in new domains. In this paper, we consider symbolic domains as simple environments where states and actions are given as unstructured text, and binary rewards indicate whether a problem is solved.
  arXiv  Detail & Related papers  (2021-06-16T21:46:07Z)

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.