How Interpretable are Reasoning Explanations from Prompting Large Language Models?

• URL: http://arxiv.org/abs/2402.11863v3
• Date: Mon, 1 Apr 2024 08:33:11 GMT
• Title: How Interpretable are Reasoning Explanations from Prompting Large Language Models?
• Authors: Wei Jie Yeo, Ranjan Satapathy, Rick Siow Mong Goh, Erik Cambria,
• Abstract summary: We present a comprehensive and multifaceted evaluation of interpretability, examining not only faithfulness but also robustness and utility across commonsense reasoning benchmarks. In addition, we introduce a simple interpretability alignment technique termed Self-Entailment-Alignment Chain-of-thought, that yields more than 70% improvements across multiple dimensions of interpretability.
• Score: 34.4659592398593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prompt Engineering has garnered significant attention for enhancing the performance of large language models across a multitude of tasks. Techniques such as the Chain-of-Thought not only bolster task performance but also delineate a clear trajectory of reasoning steps, offering a tangible form of explanation for the audience. Prior works on interpretability assess the reasoning chains yielded by Chain-of-Thought solely along a singular axis, namely faithfulness. We present a comprehensive and multifaceted evaluation of interpretability, examining not only faithfulness but also robustness and utility across multiple commonsense reasoning benchmarks. Likewise, our investigation is not confined to a single prompting technique; it expansively covers a multitude of prevalent prompting techniques employed in large language models, thereby ensuring a wide-ranging and exhaustive evaluation. In addition, we introduce a simple interpretability alignment technique, termed Self-Entailment-Alignment Chain-of-thought, that yields more than 70\% improvements across multiple dimensions of interpretability. Code is available at https://github.com/SenticNet/CoT_interpretability

Related papers

• Pattern-Aware Chain-of-Thought Prompting in Large Language Models [26.641713417293538]
  Chain-of-thought (CoT) prompting can guide language models to engage in complex multi-step reasoning. We show that the underlying reasoning patterns play a more crucial role in such tasks. We propose Pattern-Aware CoT, a prompting method that considers the diversity of demonstration patterns.
  arXiv  Detail & Related papers  (2024-04-23T07:50:00Z)
• Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents [80.5213198675411]
  Large language models (LLMs) have dramatically enhanced the field of language intelligence. LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. Recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents.
  arXiv  Detail & Related papers  (2023-11-20T14:30:55Z)
• Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts [1.8175282137722093]
  Chain-of-Thought (CoT) methods empower Large Language Models (LLMs) to solve complex tasks in a step-by-step manner. The ability to deliver multi-step reasoning remains limited to English because of the imbalance in the distribution of pre-training data. We propose Cross-lingual Tree-of-Thoughts (Cross-ToT), a method for aligning Cross-lingual CoT reasoning across languages.
  arXiv  Detail & Related papers  (2023-11-14T11:49:43Z)
• Explanation Selection Using Unlabeled Data for Chain-of-Thought Prompting [80.9896041501715]
  Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance. This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion.
  arXiv  Detail & Related papers  (2023-02-09T18:02:34Z)
• Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango [11.344587937052697]
  This work initiates the preliminary steps towards a deeper understanding of reasoning mechanisms in large language models. Our work centers around querying the model while controlling for all but one of the components in a prompt: symbols, patterns, and text. We posit that text imbues patterns with commonsense knowledge and meaning.
  arXiv  Detail & Related papers  (2022-09-16T02:54:00Z)
• Rationale-Augmented Ensembles in Language Models [53.45015291520658]
  We reconsider rationale-augmented prompting for few-shot in-context learning. We identify rationale sampling in the output space as the key component to robustly improve performance. We demonstrate that rationale-augmented ensembles achieve more accurate and interpretable results than existing prompting approaches.
  arXiv  Detail & Related papers  (2022-07-02T06:20:57Z)
• Chain of Thought Prompting Elicits Reasoning in Large Language Models [56.811278668446825]
  This paper explores the ability of language models to generate a coherent chain of thought. Experiments show that inducing a chain of thought via prompting can enable sufficiently large language models to better perform reasoning tasks.
  arXiv  Detail & Related papers  (2022-01-28T02:33:07Z)
• PROMPT WAYWARDNESS: The Curious Case of Discretized Interpretation of Continuous Prompts [99.03864962014431]
  Fine-tuning continuous prompts for target tasks has emerged as a compact alternative to full model fine-tuning. In practice, we observe a "wayward" behavior between the task solved by continuous prompts and their nearest neighbor.
  arXiv  Detail & Related papers  (2021-12-15T18:55:05Z)
• Probing as Quantifying the Inductive Bias of Pre-trained Representations [99.93552997506438]
  We present a novel framework for probing where the goal is to evaluate the inductive bias of representations for a particular task. We apply our framework to a series of token-, arc-, and sentence-level tasks.
  arXiv  Detail & Related papers  (2021-10-15T22:01:16Z)
• It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning [4.200736775540874]
  We design a simple approach to commonsense reasoning which trains a linear classifier with weights of multi-head attention as features. The method performs competitively with recent supervised and unsupervised approaches for commonsense reasoning. Most of the performance is given by the same small subset of attention heads for all studied languages.
  arXiv  Detail & Related papers  (2021-06-22T21:25:43Z)

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.