When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems

• URL: http://arxiv.org/abs/2410.13029v1
• Date: Wed, 16 Oct 2024 20:40:50 GMT
• Title: When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems
• Authors: Asir Saadat, Tasmia Binte Sogir, Md Taukir Azam Chowdhury, Syem Aziz,
• Abstract summary: Large language models (LLMs) are increasingly relied upon to solve complex mathematical word problems. They may generate inaccurate results when presented with unanswerable questions, raising concerns about their potential harm. In this paper, we investigate whether GPTs can appropriately respond to unanswerable math word problems by applying prompts typically used in solvable mathematical scenarios.
• Score: 0.6249768559720122
• License:
• Abstract: Large language models (LLMs) are increasingly relied upon to solve complex mathematical word problems. However, being susceptible to hallucination, they may generate inaccurate results when presented with unanswerable questions, raising concerns about their potential harm. While GPT models are now widely used and trusted, the exploration of how they can effectively abstain from answering unanswerable math problems and the enhancement of their abstention capabilities has not been rigorously investigated. In this paper, we investigate whether GPTs can appropriately respond to unanswerable math word problems by applying prompts typically used in solvable mathematical scenarios. Our experiments utilize the Unanswerable Word Math Problem (UWMP) dataset, directly leveraging GPT model APIs. Evaluation metrics are introduced, which integrate three key factors: abstention, correctness and confidence. Our findings reveal critical gaps in GPT models and the hallucination it suffers from for unsolvable problems, highlighting the need for improved models capable of better managing uncertainty and complex reasoning in math word problem-solving contexts.

Related papers

• MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs [80.96119560172224]
  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.
  arXiv  Detail & Related papers  (2024-10-17T12:48:14Z)
• Large Language Models Are Unconscious of Unreasonability in Math Problems [28.534372555982856]
  We study the behavior of large language models (LLMs) when faced with unreasonable math problems. Experiments show that LLMs are able to detect unreasonable errors, but still fail in generating non-hallucinatory content.
  arXiv  Detail & Related papers  (2024-03-28T12:04:28Z)
• Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem [58.3723958800254]
  Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. They are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP)
  arXiv  Detail & Related papers  (2024-03-06T09:06:34Z)
• Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models [15.65204261844768]
  We propose a new approach named Problem Elaboration Prompting (PEP) to enhance the mathematical capacities of large language models (LLMs) PEP decomposes and elucidates the problem context before reasoning, therefore enhancing the context modeling and parsing efficiency.
  arXiv  Detail & Related papers  (2024-02-24T08:40:30Z)
• 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)
• Extending the Frontier of ChatGPT: Code Generation and Debugging [0.0]
  ChatGPT, developed by OpenAI, has ushered in a new era by utilizing artificial intelligence (AI) to tackle diverse problem domains. This research paper delves into the efficacy of ChatGPT in solving programming problems, examining both the correctness and the efficiency of its solution in terms of time and memory complexity. The research reveals a commendable overall success rate of 71.875%, denoting the proportion of problems for which ChatGPT was able to provide correct solutions.
  arXiv  Detail & Related papers  (2023-07-17T06:06:58Z)
• Evaluating Language Models for Mathematics through Interactions [116.67206980096513]
  We introduce CheckMate, a prototype platform for humans to interact with and evaluate large language models (LLMs) We conduct a study with CheckMate to evaluate three language models (InstructGPT, ChatGPT, and GPT-4) as assistants in proving undergraduate-level mathematics. We derive a taxonomy of human behaviours and uncover that despite a generally positive correlation, there are notable instances of divergence between correctness and perceived helpfulness.
  arXiv  Detail & Related papers  (2023-06-02T17:12:25Z)
• Solving Math Word Problems by Combining Language Models With Symbolic Solvers [28.010617102877923]
  Large language models (LLMs) can be combined with external tools to perform complex reasoning and calculation. We propose an approach that combines an LLM that can incrementally formalize word problems as a set of variables and equations with an external symbolic solver. Our approach achieves comparable accuracy to the original PAL on the GSM8K benchmark of math word problems and outperforms PAL by an absolute 20% on ALGEBRA.
  arXiv  Detail & Related papers  (2023-04-16T04:16:06Z)
• UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression [127.68780714438103]
  Two main geometry problems: calculation and proving, are usually treated as two specific tasks. We construct a large-scale Unified Geometry problem benchmark, UniGeo, which contains 4,998 calculation problems and 9,543 proving problems. We also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously.
  arXiv  Detail & Related papers  (2022-12-06T04:37:51Z)
• A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models [81.15974174627785]
  We study the behavior of language models in terms of robustness and sensitivity to direct interventions in the input space. Our analysis shows that robustness does not appear to continuously improve as a function of size, but the GPT-3 Davinci models (175B) achieve a dramatic improvement in both robustness and sensitivity compared to all other GPT variants.
  arXiv  Detail & Related papers  (2022-10-21T15:12:37Z)
• Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning [150.17907456113537]
  We present Tabular Math Word Problems (TabMWP), a new dataset containing 38,431 grade-level problems that require mathematical reasoning. We evaluate different pre-trained models on TabMWP, including the GPT-3 model in a few-shot setting. We propose a novel approach, PromptPG, which utilizes policy gradient to learn to select in-context examples from a small amount of training data.
  arXiv  Detail & Related papers  (2022-09-29T08:01:04Z)

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.