Search Results for author:
Found 17 papers, 12 papers with code
Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning
Questions involving commonsense reasoning about everyday situations often admit many $\textit{possible}$ or $\textit{plausible}$ answers.
Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions
Multiple-choice question answering (MCQA) is a key competence of performant transformer language models that is tested by mainstream benchmarks.
The Art of Saying No: Contextual Noncompliance in Language Models
Chat-based language models are designed to be helpful, yet they should not comply with every user request.
The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
In this paper, we present the surprising conclusion that current pretrained language models often generalize relatively well from easy to hard data, even performing as well as oracle models finetuned on hard data.
Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals
Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the input (e. g., the hypothesis in NLI) and the label; consequently, models trained only on those outperform chance.
Editing Common Sense in Transformers
However, these editing methods have only been evaluated on statements about encyclopedic knowledge with a single correct answer.
Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy
For example, both normalization and prompting methods for reducing SFC can be ineffective or even detrimental to task performance for some LMs.
Self-Refine: Iterative Refinement with Self-Feedback
Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes
We show that decomposition is an effective form of probing QA systems as well as a promising approach to explanation generation.
Reframing Human-AI Collaboration for Generating Free-Text Explanations
We create a pipeline that combines GPT-3 with a supervised filter that incorporates binary acceptability judgments from humans in the loop.
Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning
Transformer-based language model approaches to automated story generation currently provide state-of-the-art results.
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing
Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated textual explanations.
Measuring Association Between Labels and Free-Text Rationales
In interpretable NLP, we require faithful rationales that reflect the model's decision-making process for an explained instance.
Learning to Faithfully Rationalize by Construction
In NLP this often entails extracting snippets of an input text `responsible for' corresponding model output; when such a snippet comprises tokens that indeed informed the model's prediction, it is a faithful explanation.
Attention is not not Explanation
We show that even when reliable adversarial distributions can be found, they don't perform well on the simple diagnostic, indicating that prior work does not disprove the usefulness of attention mechanisms for explainability.
Clinical Concept Extraction for Document-Level Coding
The text of clinical notes can be a valuable source of patient information and clinical assessments.
Explainable Prediction of Medical Codes from Clinical Text
Our method aggregates information across the document using a convolutional neural network, and uses an attention mechanism to select the most relevant segments for each of the thousands of possible codes.
Ranked #11 on
Medical Code Prediction
on MIMIC-III
