Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification

Soumya Sanyal, Tianyi Xiao, Jiacheng Liu, Wenya Wang, Xiang Ren

Abstract

While Large Language Models (LLMs) are often associated with "hallucinations," recent research suggests they may actually surpass human performance in complex, multi-hop reasoning over extended contexts. Conversely, humans maintain an edge in simple deductive tasks involving basic logic and negations. This paper explores this "reasoning gap" and introduces an open-source model designed to verify the logical consistency of AI-generated explanations.

Introduction: The Challenge of Entailment Verification

Most Natural Language Inference (NLI) research focuses on short, single-sentence premises. However, real-world comprehension often requires connecting information across multiple sentences—a process known as Entailment Verification (EV). As we increasingly rely on LLMs to generate "Chain-of-Thought" (CoT) rationales, the need for robust verification tools becomes paramount. While humans face cognitive limitations in processing large volumes of information (the "magic number 4"), LLMs often struggle with fundamental logical consistency. This study quantifies these differences and proposes a framework for better reasoning verification.

Methodology and Reasoning Taxonomy

The researchers benchmarked human performance against state-of-the-art LLMs, including GPT-4, GPT-3.5, and Flan-T5. To better understand the performance differences, they categorized reasoning into four distinct types:

  1. Simple Deductive (R1): Single-step logic involving negations or synonyms.
  2. Complex Deductive (R2): Multi-step reasoning across a broader context.
  3. Missing Knowledge (R3): Tasks requiring external facts or commonsense.
  4. Missing Localized Knowledge (R4): Tasks requiring context-specific information not explicitly in the text.
Examples of reasoning types and human vs. AI performance gaps.

Beyond benchmarking, the authors developed a Flan-T5-xxl model using a ranking objective. Unlike standard binary classification, this approach teaches the model to identify which hypothesis is more supported by a premise, leading to a more flexible and generalizable decision boundary.

Dataset Analysis

The study utilized an EV benchmark compiled from 10 datasets across three primary domains: NLI (WaNLI, FEVER, ANLI), Contextual QA (Cosmos QA, SocialIQA, DREAM, BoolQ, RACE), and Rationales (Entailer, ECQA). The datasets were selected based on specific desirable properties, such as multi-sentence premises and the requirement for commonsense knowledge.

Comparison of dataset properties across NLI, Contextual QA, and Rationale domains.

Key Insights: The Human-Machine Gap

The research revealed two primary gaps in reasoning capabilities:

  • The Memory Gap: Humans are "limited capacity" processors, struggling to maintain multiple logical threads across long paragraphs. LLMs, acting as powerful context processors, excel in these multi-step scenarios.
  • The Logic Gap: LLMs remain brittle when faced with simple logic. Basic negations or word substitutions that are trivial for humans can frequently cause models to fail.

Furthermore, the study found that Ranking > Classification. In domains like commonsense QA where answers are nuanced, training models to rank hypotheses is more effective than hard binary labels.

Results and Performance

The experimental results highlight the strengths of specialized open-source models:

  • GPT-4 vs. Humans: GPT-4 outperformed humans on datasets requiring complex reasoning (e.g., ANLI, CosQA), while humans remained superior in simple deductive tasks (R1).
  • Model Performance: The finetuned Flan-T5 + Rank model achieved a macro-F1 of 0.78, significantly outperforming GPT-3.5 (0.68) and matching GPT-4 (0.79).
  • Verification Benefits: Implementing a verifier to filter CoT rationales improved final answer accuracy by an average of 6% across multiple-choice datasets, with even higher gains for weaker base models like UL2.

Conclusion and Future Directions

While the proposed verification framework shows promise, limitations remain. The conversion of Q&A pairs into hypotheses relies on external models that may introduce errors. Future work should explore decoder-only architectures and incorporate more nuanced scoring mechanisms that consider a wider array of logical markers. Addressing these challenges will be critical as we move toward more reliable and interpretable AI reasoning systems.

Summary updated

Abstract

Making inferences in text comprehension to understand the meaning is essential in language processing. This work studies the entailment verification (EV) problem of complex, multi-sentence premises requiring a system to make multiple inferences implicitly. Modern applications of EV in detecting inconsistent model-generated rationales require complex multi-hop reasoning. However, current textual inference datasets mostly contain short-sentence premises that partially focus on this. To address this, we compile an EV benchmark that includes datasets from three NLP domains (NLI, contextual QA, and rationales) containing multi-sentence premises. On benchmarking humans and LLMs, we find that LLMs are better than humans in multi-hop reasoning across extended contexts, while humans perform better in simple deductive reasoning tasks. We also finetune a Flan-T5 model for EV using two training objectives to obtain a strong open-source model that outperforms GPT-3.5 and rivals GPT-4. Finally, we use our finetuned model to filter out inconsistent model-generated rationales in self-consistency decoding, resulting in a 6% accuracy improvement on average across three MCQ datasets.
BibTeX
@inproceedings{sanyal2024are,
  author = {Soumya Sanyal and Tianyi Xiao and Jiacheng Liu and Wenya Wang and Xiang Ren},
  title = {{Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification}},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  year = {2024},
  doi = {10.18653/v1/2024.findings-acl.618},
}
Figure