Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models
Submission Type: Regular Long Paper
Submission Track: Question Answering
Submission Track 2: Resources and Evaluation
Keywords: Reasoning, Large Language Model, Benchmark, Problem Solving
TL;DR: We propose a challenging benchmark dataset for reasoning consisting of questions from JEE Advanced exam and analyse the weaknesses of GPT-4 on our benchmark.
Abstract: The performance of large language models (LLMs) on existing reasoning benchmarks has significantly improved over the past years. In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs. We curate 515 challenging pre-engineering mathematics, physics and chemistry problems from the highly competitive IIT JEE-Advanced exam. Long-horizon reasoning on top of deep in-domain knowledge is essential for solving problems in this benchmark. Our evaluation on various open-source and proprietary models reveals that the highest performance, even after using techniques like self-consistency, self-refinement and chain-of-thought prompting, is less than 40%. The typical failure modes of GPT-4, the best model, are errors in algebraic manipulation, difficulty in grounding abstract concepts into mathematical equations accurately and failure in retrieving relevant domain-specific concepts. We also observe that by mere prompting, GPT-4 is unable to assess risk introduced by negative marking for incorrect answers. For this, we develop a post-hoc confidence-thresholding method over self-consistency, which enables effective response selection. We hope that our challenging benchmark will guide future re-search in problem-solving using LLMs.
Submission Number: 4005
Loading