MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

• URL: http://arxiv.org/abs/2410.13502v2
• Date: Mon, 21 Oct 2024 15:58:30 GMT
• Title: MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
• Authors: Andreas Opedal, Haruki Shirakami, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan,
• Abstract summary: Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to problems that are more complex than the ones on which they have been trained. We present a framework for evaluating LLMs on problems with arbitrarily complex arithmetic proofs, called MathGAP.
• Score: 80.96119560172224
• License:
• Abstract: Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to problems that are more complex than the ones on which they have been trained. Empirical investigations of such questions are impeded by two major flaws of current evaluations: (i) much of the evaluation data is contaminated, in the sense that it has already been seen during training, and (ii) benchmark datasets do not capture how problem proofs may be arbitrarily complex in various ways. As a step towards addressing these issues, we present a framework for evaluating LLMs on problems with arbitrarily complex arithmetic proofs, called MathGAP. MathGAP generates problems that follow fixed proof specifications -- along with chain-of-thought reasoning annotations -- enabling systematic studies on generalization with respect to arithmetic proof complexity. We apply MathGAP to analyze how in-context learning interacts with generalization to problems that have more complex proofs. We find that among the models tested, most show a significant decrease in performance as proofs get deeper and wider. This effect is more pronounced in complex, nonlinear proof structures, which are challenging even for GPT-4o. Surprisingly, providing in-context examples from the same distribution as the test set is not always beneficial for performance. In particular, zero-shot prompting as well as demonstrating a diverse range of examples that are less complex than the test data sometimes yield similar or higher accuracies.

Related papers

• LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning [23.987059076950622]
  We present a novel approach, called LogicPro, to enhance Large Language Models (LLMs) complex Logical reasoning through Program Examples. We do this effectively by simply utilizing widely available algorithmic problems and their code solutions. Our approach achieves significant improvements in multiple models for the BBH$27$, GSM8K, HellSwag, Logicqa, Reclor, and RTE datasets.
  arXiv  Detail & Related papers  (2024-09-19T17:30:45Z)
• Chain of Thoughtlessness? An Analysis of CoT in Planning [17.329365493094542]
  Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. This paper presents a case study of chain of thought on problems from Blocksworld, a classical planning domain. We find meaningful performance improvements from chain of thought prompts when those prompts are exceedingly specific to their problem class.
  arXiv  Detail & Related papers  (2024-05-08T02:48:28Z)
• 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)
• CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities [25.857946070979576]
  Concept and Hint-Annotated Math Problems (CHAMP) consists of high school math competition problems annotated with concepts. This benchmark is difficult, with the best model only scoring 58.1% in standard settings. We find that models often arrive at the correct final answer through wrong reasoning steps.
  arXiv  Detail & Related papers  (2024-01-13T03:18:16Z)
• Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples [36.63316546586304]
  Large language models (LLMs) possess some abstract deductive reasoning ability given chain-of-thought prompts. We test on a broad set of deduction rules and measure their ability to generalize to more complex proofs from simpler demonstrations. Experiments on four LLMs of various sizes and training objectives show that they are able to generalize to compositional proofs.
  arXiv  Detail & Related papers  (2023-05-24T15:55:51Z)
• Successive Prompting for Decomposing Complex Questions [50.00659445976735]
  Recent works leverage the capabilities of large language models (LMs) to perform complex question answering in a few-shot setting. We introduce Successive Prompting'', where we iteratively break down a complex task into a simple task, solve it, and then repeat the process until we get the final solution. Our best model (with successive prompting) achieves an improvement of 5% absolute F1 on a few-shot version of the DROP dataset.
  arXiv  Detail & Related papers  (2022-12-08T06:03:38Z)
• Shortcomings of Question Answering Based Factuality Frameworks for Error Localization [51.01957350348377]
  We show that question answering (QA)-based factuality metrics fail to correctly identify error spans in generated summaries. Our analysis reveals a major reason for such poor localization: questions generated by the QG module often inherit errors from non-factual summaries which are then propagated further into downstream modules. Our experiments conclusively show that there exist fundamental issues with localization using the QA framework which cannot be fixed solely by stronger QA and QG models.
  arXiv  Detail & Related papers  (2022-10-13T05:23:38Z)
• Amortized Inference for Causal Structure Learning [72.84105256353801]
  Learning causal structure poses a search problem that typically involves evaluating structures using a score or independence test. We train a variational inference model to predict the causal structure from observational/interventional data. Our models exhibit robust generalization capabilities under substantial distribution shift.
  arXiv  Detail & Related papers  (2022-05-25T17:37:08Z)
• Formal Mathematics Statement Curriculum Learning [64.45821687940946]
  We show that at same compute budget, expert iteration, by which we mean proof search interleaved with learning, dramatically outperforms proof search only. We also observe that when applied to a collection of formal statements of sufficiently varied difficulty, expert iteration is capable of finding and solving a curriculum of increasingly difficult problems.
  arXiv  Detail & Related papers  (2022-02-03T00:17:00Z)
• A tetrachotomy of ontology-mediated queries with a covering axiom [1.749935196721634]
  Our concern is the problem of efficiently determining the data complexity of answering queries mediated by description and their optimal rewritings to standard database queries. We focus on Boolean conjunctive-mediated queries called disjunctive sirups (or d-sirups) Some d-sirups only have exponential-size resolution features, some only double-exponential-size positive existential existential-rewritings and single-exprecursive datalog rewritings.
  arXiv  Detail & Related papers  (2020-06-07T14:47:07Z)

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.