Are Shortest Rationales the Best Explanations for Human Understanding?

• URL: http://arxiv.org/abs/2203.08788v1
• Date: Wed, 16 Mar 2022 17:52:07 GMT
• Title: Are Shortest Rationales the Best Explanations for Human Understanding?
• Authors: Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao 'Kenneth' Huang
• Abstract summary: We design a self-explaining model, LimitedInk, which allows users to extract rationales at any target length. Compared to existing baselines, LimitedInk achieves compatible end-task performance and human-annotated rationale agreement. We show rationales that are too short do not help humans predict labels better than randomly masked text.
• Score: 33.167653894653114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing self-explaining models typically favor extracting the shortest possible rationales - snippets of an input text "responsible for" corresponding output - to explain the model prediction, with the assumption that shorter rationales are more intuitive to humans. However, this assumption has yet to be validated. Is the shortest rationale indeed the most human-understandable? To answer this question, we design a self-explaining model, LimitedInk, which allows users to extract rationales at any target length. Compared to existing baselines, LimitedInk achieves compatible end-task performance and human-annotated rationale agreement, making it a suitable representation of the recent class of self-explaining models. We use LimitedInk to conduct a user study on the impact of rationale length, where we ask human judges to predict the sentiment label of documents based only on LimitedInk-generated rationales with different lengths. We show rationales that are too short do not help humans predict labels better than randomly masked text, suggesting the need for more careful design of the best human rationales.

Related papers

• Infinite Ends from Finite Samples: Open-Ended Goal Inference as Top-Down Bayesian Filtering of Bottom-Up Proposals [48.437581268398866]
  We introduce a sequential Monte Carlo model of open-ended goal inference. We validate this model in a goal inference task called Block Words. Our experiments highlight the importance of uniting top-down and bottom-up models for explaining the speed, accuracy, and generality of human theory-of-mind.
  arXiv  Detail & Related papers  (2024-07-23T18:04:40Z)
• RORA: Robust Free-Text Rationale Evaluation [52.98000150242775]
  We propose RORA, a Robust free-text Rationale evaluation against label leakage. RORA consistently outperforms existing approaches in evaluating human-written, synthetic, or model-generated rationales. We also show that RORA aligns well with human judgment, providing a more reliable and accurate measurement across diverse free-text rationales.
  arXiv  Detail & Related papers  (2024-02-28T19:46:21Z)
• How Ambiguous are the Rationales for Natural Language Reasoning? A Simple Approach to Handling Rationale Uncertainty [0.0]
  Rationales behind answers not only explain model decisions but boost language models to reason well on complex reasoning tasks. It is non-trivial to estimate the degree to which the rationales are faithful enough to encourage model performance. We propose how to deal with imperfect rationales causing aleatoric uncertainty.
  arXiv  Detail & Related papers  (2024-02-22T07:12:34Z)
• HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision [118.0818807474809]
  This work proposes a principled, probabilistic approach for training explainable multi-hop QA systems without rationale supervision. Our approach performs multi-hop reasoning by explicitly modeling rationales as sets, enabling the model to capture interactions between documents and sentences within a document.
  arXiv  Detail & Related papers  (2023-05-23T16:53:49Z)
• The Irrationality of Neural Rationale Models [6.159428088113691]
  We argue to the contrary, with both philosophical perspectives and empirical evidence suggesting that rationale models are, perhaps, less rational and interpretable than expected. We call for more rigorous and comprehensive evaluations of these models to ensure desired properties of interpretability are indeed achieved.
  arXiv  Detail & Related papers  (2021-10-14T17:22:10Z)
• Rationales for Sequential Predictions [117.93025782838123]
  Sequence models are a critical component of modern NLP systems, but their predictions are difficult to explain. We consider model explanations though rationales, subsets of context that can explain individual model predictions. We propose an efficient greedy algorithm to approximate this objective.
  arXiv  Detail & Related papers  (2021-09-14T01:25:15Z)
• Rationalization through Concepts [27.207067974031805]
  We present a novel self-interpretable model called ConRAT. Inspired by how human explanations for high-level decisions are often based on key concepts, ConRAT infers which ones are described in the document. Two regularizers drive ConRAT to build interpretable concepts.
  arXiv  Detail & Related papers  (2021-05-11T07:46:48Z)
• Invariant Rationalization [84.1861516092232]
  A typical rationalization criterion, i.e. maximum mutual information (MMI), finds the rationale that maximizes the prediction performance based only on the rationale. We introduce a game-theoretic invariant rationalization criterion where the rationales are constrained to enable the same predictor to be optimal across different environments. We show both theoretically and empirically that the proposed rationales can rule out spurious correlations, generalize better to different test scenarios, and align better with human judgments.
  arXiv  Detail & Related papers  (2020-03-22T00:50:27Z)

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.