Search Results for author:
Found 27 papers, 18 papers with code
Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting
We find that text-based explanations lead to significant over-reliance, which is alleviated by combining them with saliency maps.
iLLuMinaTE: An LLM-XAI Framework Leveraging Social Science Explanation Theories Towards Actionable Student Performance Feedback
iLLuMinaTE navigates three main stages - causal connection, explanation selection, and explanation presentation - with variations drawing from eight social science theories (e. g. Abnormal Conditions, Pearl's Model of Explanation, Necessity and Robustness Selection, Contrastive Explanation).
The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
In this work, we introduce Correlational Explanatory Faithfulness (CEF), a metric that can be used in faithfulness tests based on input interventions.
Identifying Linear Relational Concepts in Large Language Models
Transformer language models (LMs) have been shown to represent concepts as directions in the latent space of hidden activations.
Using Natural Language Explanations to Improve Robustness of In-context Learning
Recent studies demonstrated that large language models (LLMs) can excel in many tasks via in-context learning (ICL).
KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language Explanations
While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among generated NLEs.
Faithfulness Tests for Natural Language Explanations
Explanations of neural models aim to reveal a model's decision-making process for its predictions.
SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations
Models that generate natural language explanations (NLEs) for their predictions have recently gained increasing interest.
Atomic Inference for NLI with Generated Facts as Atoms
With recent advances, neural models can achieve human-level performance on various natural language tasks.
Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns
Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods.
Rationalizing Predictions by Adversarial Information Calibration
One form of explanation for a prediction is an extractive rationale, i. e., a subset of features of an instance that lead the model to give its prediction on that instance.
Explaining Chest X-ray Pathologies in Natural Language
Most deep learning algorithms lack explanations for their predictions, which limits their deployment in clinical practice.
Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations in a Label-Abundant Setup
A potential solution is the few-shot out-of-domain transfer of NLEs from a parent task with many NLEs to a child task.
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations.
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks.
Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration
We use an adversarial-based technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features.
The Gap on GAP: Tackling the Problem of Differing Data Distributions in Bias-Measuring Datasets
For example, if the feminine subset of a gender-bias-measuring coreference resolution dataset contains sentences with a longer average distance between the pronoun and the correct candidate, an RNN-based model may perform worse on this subset due to long-term dependencies.
Does the Objective Matter? Comparing Training Objectives for Pronoun Resolution
Overall, four categories of training and evaluation objectives have been introduced.
Explaining Deep Neural Networks
The first direction consists of feature-based post-hoc explanatory methods, that is, methods that aim to explain an already trained and fixed model (post-hoc), and that provide explanations in terms of input features, such as tokens for text and superpixels for images (feature-based).
The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets
For neural models to garner widespread public trust and ensure fairness, we must have human-intelligible explanations for their predictions.
e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning.
Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations
To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions.
Can I Trust the Explainer? Verifying Post-hoc Explanatory Methods
We aim for this framework to provide a publicly available, off-the-shelf evaluation when the feature-selection perspective on explanations is needed.
WikiCREM: A Large Unsupervised Corpus for Coreference Resolution
We use a language-model-based approach for pronoun resolution in combination with our WikiCREM dataset.
A Surprisingly Robust Trick for the Winograd Schema Challenge
The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning.
A Surprisingly Robust Trick for Winograd Schema Challenge
The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning.
Ranked #13 on
Natural Language Inference
on WNLI
e-SNLI: Natural Language Inference with Natural Language Explanations
In order for machine learning to garner widespread public adoption, models must be able to provide interpretable and robust explanations for their decisions, as well as learn from human-provided explanations at train time.
Ranked #1 on
Natural Language Inference
on e-SNLI
