Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations

• URL: http://arxiv.org/abs/2211.07517v1
• Date: Mon, 14 Nov 2022 16:46:14 GMT
• Title: Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations
• Authors: Swarnadeep Saha, Peter Hase, Nazneen Rajani, Mohit Bansal
• Abstract summary: We study the connection between explainability and sample hardness. We compare human-written explanations with those generated by GPT-3. We also find that hardness of the in-context examples impacts the quality of GPT-3 explanations.
• Score: 82.12092864529605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work on explainable NLP has shown that few-shot prompting can enable large pretrained language models (LLMs) to generate grammatical and factual natural language explanations for data labels. In this work, we study the connection between explainability and sample hardness by investigating the following research question - "Are LLMs and humans equally good at explaining data labels for both easy and hard samples?" We answer this question by first collecting human-written explanations in the form of generalizable commonsense rules on the task of Winograd Schema Challenge (Winogrande dataset). We compare these explanations with those generated by GPT-3 while varying the hardness of the test samples as well as the in-context samples. We observe that (1) GPT-3 explanations are as grammatical as human explanations regardless of the hardness of the test samples, (2) for easy examples, GPT-3 generates highly supportive explanations but human explanations are more generalizable, and (3) for hard examples, human explanations are significantly better than GPT-3 explanations both in terms of label-supportiveness and generalizability judgements. We also find that hardness of the in-context examples impacts the quality of GPT-3 explanations. Finally, we show that the supportiveness and generalizability aspects of human explanations are also impacted by sample hardness, although by a much smaller margin than models. Supporting code and data are available at https://github.com/swarnaHub/ExplanationHardness

Related papers

• Scenarios and Approaches for Situated Natural Language Explanations [18.022428746019582]
  We collect a benchmarking dataset, Situation-Based Explanation. This dataset contains 100 explanandums. For each "explanandum paired with an audience" situation, we include a human-written explanation. We examine three categories of prompting methods: rule-based prompting, meta-prompting, and in-context learning prompting.
  arXiv  Detail & Related papers  (2024-06-07T15:56:32Z)
• Verifying Relational Explanations: A Probabilistic Approach [2.113770213797994]
  We develop an approach where we assess the uncertainty in explanations generated by GNNExplainer. We learn a factor graph model to quantify uncertainty in an explanation. Our results on several datasets show that our approach can help verify explanations from GNNExplainer.
  arXiv  Detail & Related papers  (2024-01-05T08:14:51Z)
• Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA [7.141288053123662]
  Natural language explanation in visual question answer (VQA-NLE) aims to explain the decision-making process of models by generating natural language sentences to increase users' trust in the black-box systems. Existing post-hoc explanations are not always aligned with human logical inference, suffering from the issues on: 1) Deductive unsatisfiability, the generated explanations do not logically lead to the answer; 2) Factual inconsistency, the model falsifies its counterfactual explanation for answers without considering the facts in images; and 3) Semantic perturbation insensitivity, the model can not recognize the semantic changes caused by small perturbations
  arXiv  Detail & Related papers  (2023-12-21T05:51:55Z)
• ExaRanker: Explanation-Augmented Neural Ranker [67.4894325619275]
  In this work, we show that neural rankers also benefit from explanations. We use LLMs such as GPT-3.5 to augment retrieval datasets with explanations. Our model, dubbed ExaRanker, finetuned on a few thousand examples with synthetic explanations performs on par with models finetuned on 3x more examples without explanations.
  arXiv  Detail & Related papers  (2023-01-25T11:03:04Z)
• The Unreliability of Explanations in Few-Shot In-Context Learning [50.77996380021221]
  We focus on two NLP tasks that involve reasoning over text, namely question answering and natural language inference. We show that explanations judged as good by humans--those that are logically consistent with the input--usually indicate more accurate predictions. We present a framework for calibrating model predictions based on the reliability of the explanations.
  arXiv  Detail & Related papers  (2022-05-06T17:57:58Z)
• Reframing Human-AI Collaboration for Generating Free-Text Explanations [46.29832336779188]
  We consider the task of generating free-text explanations using a small number of human-written examples. We find that crowdworkers often prefer explanations generated by GPT-3 to crowdsourced human-written explanations. We create a pipeline that combines GPT-3 with a supervised filter that incorporates humans-in-the-loop via binary acceptability judgments.
  arXiv  Detail & Related papers  (2021-12-16T07:31:37Z)
• Prompting Contrastive Explanations for Commonsense Reasoning Tasks [74.7346558082693]
  Large pretrained language models (PLMs) can achieve near-human performance on commonsense reasoning tasks. We show how to use these same models to generate human-interpretable evidence.
  arXiv  Detail & Related papers  (2021-06-12T17:06:13Z)
• Parameterized Explainer for Graph Neural Network [49.79917262156429]
  We propose PGExplainer, a parameterized explainer for Graph Neural Networks (GNNs) Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification.
  arXiv  Detail & Related papers  (2020-11-09T17:15:03Z)

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.