A & B == B & A: Triggering Logical Reasoning Failures in Large Language Models

• URL: http://arxiv.org/abs/2401.00757v1
• Date: Mon, 1 Jan 2024 13:53:53 GMT
• Title: A & B == B & A: Triggering Logical Reasoning Failures in Large Language Models
• Authors: Yuxuan Wan, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He, Wenxiang Jiao, Michael R. Lyu
• Abstract summary: We introduce LogicAsker, an automatic approach that comprehensively evaluates and improves the logical reasoning abilities of LLMs. We evaluate LogicAsker on six widely deployed LLMs, including GPT-3, ChatGPT, GPT-4, Bard, Vicuna, and Guanaco. The results show that test cases from LogicAsker can find logical reasoning failures in different LLMs with a rate of 25% - 94%.
• Score: 65.86149763739141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in large language models (LLMs) have propelled Artificial Intelligence (AI) to new heights, enabling breakthroughs in various tasks such as writing assistance, code generation, and machine translation. A significant distinction of advanced LLMs, such as ChatGPT, is their demonstrated ability to "reason." However, evaluating the reasoning ability of LLMs remains a challenge as most existing evaluations focus on their accuracy on the downstream tasks rather than directly assessing their reasoning processes. Efforts have been made to develop benchmarks and metrics to assess reasoning in LLMs, but they suffer from data leakage or limited scope. In this paper, we introduce LogicAsker, an automatic approach that comprehensively evaluates and improves the logical reasoning abilities of LLMs under a set of atomic reasoning skills based on propositional and predicate logic. The results provide insights into LLMs' reasoning abilities and reveal the logical rules the LLMs did not learn well. We evaluate LogicAsker on six widely deployed LLMs, including GPT-3, ChatGPT, GPT-4, Bard, Vicuna, and Guanaco. The results show that test cases from LogicAsker can find logical reasoning failures in different LLMs with a rate of 25\% - 94\%. In addition, the test cases of LogicAsker can be further used to design demonstration examples for in-context learning, which effectively improves the logical reasoning ability of LLMs, e.g., 10\% for GPT-4. As far as we know, our work is the first to create prompts based on testing results to improve LLMs' formal reasoning ability effectively. All the code, data, and results will be released for reproduction and future research.

Related papers

• JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models [51.99046112135311]
  We introduce JustLogic, a synthetically generated deductive reasoning benchmark for rigorous evaluation of Large Language Models. JustLogic is highly complex, capable of generating a diverse range of linguistic patterns, vocabulary, and argument structures. Our experimental results reveal that most state-of-the-art (SOTA) LLMs perform significantly worse than the human average.
  arXiv  Detail & Related papers  (2025-01-24T15:49:10Z)
• Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models [9.689096888732642]
  We propose Logic-of-Thought (LoT) prompting which employs propositional logic to generate expanded logical information descriptions. LoT boosts the performance of various prompting methods with a striking margin across five logical reasoning tasks.
  arXiv  Detail & Related papers  (2024-09-26T04:59:45Z)
• Lost in the Logic: An Evaluation of Large Language Models' Reasoning Capabilities on LSAT Logic Games [0.0]
  I evaluate the performance of Large Language Models (LLMs) on the Law School Admissions Test (LSAT) I construct a dataset of logic games and their associated metadata, and extensively evaluate LLMs' performance in a Chain-of-Thought prompting setting. I analyze the types of logic games that models perform better or worse on, as well as the types of logical errors I observe from human annotation.
  arXiv  Detail & Related papers  (2024-09-23T21:37:40Z)
• Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents [3.5083201638203154]
  Logic-Enhanced Language Model Agents (LELMA) is a framework that integrates large language models with formal logic.<n>LeLMA employs autoformalization to translate reasoning into logic representations, which are then used to assess logical validity.<n>LeLMA achieves high accuracy in error detection and improves reasoning correctness via self-refinement.
  arXiv  Detail & Related papers  (2024-08-28T18:25:35Z)
• LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models [52.03659714625452]
  Recently developed large language models (LLMs) have been shown to perform remarkably well on a wide range of language understanding tasks. But, can they really "reason" over the natural language? This question has been receiving significant research attention and many reasoning skills such as commonsense, numerical, and qualitative have been studied.
  arXiv  Detail & Related papers  (2024-04-23T21:08:49Z)
• Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding [40.2816930342597]
  Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks. But they still struggle with some complicated reasoning tasks including logical reasoning. We propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW in this paper.
  arXiv  Detail & Related papers  (2024-04-04T08:38:03Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• 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)
• Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models [56.34029644009297]
  Large language models (LLMs) have demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems. LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning. We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model.
  arXiv  Detail & Related papers  (2023-10-02T01:00:50Z)
• Exploring Self-supervised Logic-enhanced Training for Large Language Models [59.227222647741094]
  In this paper, we make the first attempt to investigate the feasibility of incorporating logical knowledge through self-supervised post-training. We devise an auto-regressive objective variant of MERIt and integrate it with two LLM series, i.e., FLAN-T5 and LLaMA, with parameter size ranging from 3 billion to 13 billion. The results on two challenging logical reasoning benchmarks demonstrate the effectiveness of LogicLLM.
  arXiv  Detail & Related papers  (2023-05-23T06:13:10Z)

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.