# An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction

arXiv: https://arxiv.org/abs/2005.00652 · HTML: https://mlsanity.com/paper/2005.00652/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2020.

## Built on by (most cited first, 30 of 69)

- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [MultiVerS: Improving scientific claim verification with weak supervision and full-document context](https://mlsanity.com/paper/2112.01640/) (2021)
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [Few-Shot Self-Rationalization with Natural Language Prompts](https://mlsanity.com/paper/2111.08284/) (2021)
- [Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification](https://mlsanity.com/paper/2303.08446/) (2023)
- [Prompting Contrastive Explanations for Commonsense Reasoning Tasks](https://mlsanity.com/paper/2106.06823/) (2021)
- [Can Rationalization Improve Robustness?](https://mlsanity.com/paper/2204.11790/) (2022)
- [Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2309.17050/) (2023)
- [UNIREX: A Unified Learning Framework for Language Model Rationale Extraction](https://mlsanity.com/paper/2112.08802/) (2021)
- [What to Learn, and How: Toward Effective Learning from Rationales](https://mlsanity.com/paper/2112.00071/) (2021)
- [CREST: A Joint Framework for Rationalization and Counterfactual Text Generation](https://mlsanity.com/paper/2305.17075/) (2023)
- [D-Separation for Causal Self-Explanation](https://mlsanity.com/paper/2309.13391/) (2023)
- [Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model](https://mlsanity.com/paper/2210.02498/) (2022)
- [Rationalization through Concepts](https://mlsanity.com/paper/2105.04837/) (2021)
- [SPECTRA: Sparse Structured Text Rationalization](https://mlsanity.com/paper/2109.04552/) (2021)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Towards Trustworthy Explanation: On Causal Rationalization](https://mlsanity.com/paper/2306.14115/) (2023)
- [Improving the Adversarial Robustness of NLP Models by Information Bottleneck](https://mlsanity.com/paper/2206.05511/) (2022)
- [COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks](https://mlsanity.com/paper/2305.06754/) (2023)
- [Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning](https://mlsanity.com/paper/2212.01060/) (2022)
- [Enhancing the Rationale-Input Alignment for Self-explaining Rationalization](https://mlsanity.com/paper/2312.04103/) (2023)
- [DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning](https://mlsanity.com/paper/2603.16459/) (2026)
- [Distribution Matching for Rationalization](https://mlsanity.com/paper/2106.00320/) (2021)
- [Decoupled Rationalization with Asymmetric Learning Rates: A Flexible Lipschitz Restraint](https://mlsanity.com/paper/2305.13599/) (2023)
- [A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective](https://mlsanity.com/paper/2309.13989/) (2023)
- [Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU](https://mlsanity.com/paper/2109.08259/) (2021)
- [MGR: Multi-generator Based Rationalization](https://mlsanity.com/paper/2305.04492/) (2023)
- [Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction](https://mlsanity.com/paper/2112.10424/) (2021)
- [Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension](https://mlsanity.com/paper/2109.06853/) (2021)

## Abstract (arXiv)

Decisions of complex language understanding models can be rationalized by limiting their inputs to a relevant subsequence of the original text. A rationale should be as concise as possible without significantly degrading task performance, but this balance can be difficult to achieve in practice. In this paper, we show that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective. Our fully unsupervised approach jointly learns an explainer that predicts sparse binary masks over sentences, and an end-task predictor that considers only the extracted rationale. Using IB, we derive a learning objective that allows direct control of mask sparsity levels through a tunable sparse prior. Experiments on ERASER benchmark tasks demonstrate significant gains over norm-minimization techniques for both task performance and agreement with human rationales. Furthermore, we find that in the semi-supervised setting, a modest amount of gold rationales (25% of training examples) closes the gap with a model that uses the full input.