# Accountable and Explainable Methods for Complex Reasoning over Text

arXiv: https://arxiv.org/abs/2211.04946 · HTML: https://mlsanity.com/paper/2211.04946/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 306 references that are in the map.
- First posted on arXiv 9 Nov 2022.

## Builds on (most cited first, 30 of 30)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://mlsanity.com/paper/1704.05179/) (2017)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension](https://mlsanity.com/paper/2107.12708/) (2021)
- [A Survey on Stance Detection for Mis- and Disinformation Identification](https://mlsanity.com/paper/2103.00242/) (2021)
- [Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings](https://mlsanity.com/paper/2202.06671/) (2022)
- [How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation](https://mlsanity.com/paper/1802.00682/) (2018)
- [Attention Interpretability Across NLP Tasks](https://mlsanity.com/paper/1909.11218/) (2019)
- [Investigating the influence of noise and distractors on the interpretation of neural networks](https://mlsanity.com/paper/1611.07270/) (2016)
- [ProoFVer: Natural Logic Theorem Proving for Fact Verification](https://mlsanity.com/paper/2108.11357/) (2021)
- [A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives](https://mlsanity.com/paper/2102.12982/) (2021)
- [Order in the Court: Explainable AI Methods Prone to Disagreement](https://mlsanity.com/paper/2105.03287/) (2021)
- [A Survey on Explainability in Machine Reading Comprehension](https://mlsanity.com/paper/2010.00389/) (2020)
- [e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations](https://mlsanity.com/paper/2004.03744/) (2020)
- [FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales](https://mlsanity.com/paper/2207.00779/) (2022)
- [Towards Explainable Fact Checking](https://mlsanity.com/paper/2108.10274/) (2021)
- [Universal Adversarial Perturbation for Text Classification](https://mlsanity.com/paper/1910.04618/) (2019)
- [Semantics Preserving Adversarial Learning](https://mlsanity.com/paper/1903.03905/) (2019)
- [Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?](https://mlsanity.com/paper/2109.07102/) (2021)
- [Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers](https://mlsanity.com/paper/2208.03339/) (2022)

## Abstract (arXiv)

A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not provide explanations for their predictions. Among others, the potential harms associated with the lack of understanding of the models' rationales include privacy violations, adversarial manipulations, and unfair discrimination. As a result, the accountability and transparency of ML models have been posed as critical desiderata by works in policy and law, philosophy, and computer science. In computer science, the decision-making process of ML models has been studied by developing accountability and transparency methods. Accountability methods, such as adversarial attacks and diagnostic datasets, expose vulnerabilities of ML models that could lead to malicious manipulations or systematic faults in their predictions. Transparency methods explain the rationales behind models' predictions gaining the trust of relevant stakeholders and potentially uncovering mistakes and unfairness in models' decisions. To this end, transparency methods have to meet accountability requirements as well, e.g., being robust and faithful to the underlying rationales of a model. This thesis presents my research that expands our collective knowledge in the areas of accountability and transparency of ML models developed for complex reasoning tasks over text.