Sarah Wiegreffe
23 papers · 2018–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
🗺️ Taxonomy Completionist (40) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(11)
👥
Mega-Team · Squad
🧬
Topic Evolution
🏆
Keyword Champion
(2)
📈
Trend Setter
🗃️
Keyword Collector
(107)
❓
The Questioner
(2)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(22)
Core AI
(19)
Natural Language Processing
(14)
Machine Learning
(13)
Applications
(8)
Core Methods
(8)
Deep Learning
(6)
Learning Types · Machine Learning
(5)
Learning Paradigms
(4)
Resources & Methods
(4)
Generation
(3)
Architectures
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Optimization & Theory
(2)
Keywords
large language model
(5)
language model
(4)
commonsense reasoning
(3)
multiple-choice question
(3)
in-context learning
(3)
mechanistic interpretability
(2)
text generation
(2)
plausibility judgment
(2)
faithful explanation
(2)
activation patching
(2)
explanation generation
(2)
attention mechanism
(2)
natural language inference
(2)
human-ai interaction
(2)
pre-trained language model
(2)
instruction tuning
(2)
multi-label classification
(1)
narrative generation
(1)
commonsense knowledge
(1)
transfer learning
(1)
Papers
Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility
ACL 2026
Can you map it to English? The Role of Cross-Lingual Alignment in the Multilingual Performance of LLMs
EACL 2026
Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
ICLR 2025
Fine-Tune on the Format: First Improving Multiple-Choice Evaluation for Intermediate LLM Checkpoints
ACL 2025
MIB: A Mechanistic Interpretability Benchmark
ICML 2025
On Linear Representations and Pretraining Data Frequency in Language Models
ICLR 2025
Explanation in the Era of Large Language Models
NAACL 2024
Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals
EMNLP 2024
Mechanistic?
EMNLP 2024
Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning
EMNLP 2024
The Art of Saying No: Contextual Noncompliance in Language Models
NeurIPS 2024
The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
ACL 2024
Editing Common Sense in Transformers
EMNLP 2023
Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy
EMNLP 2023
Self-Refine: Iterative Refinement with Self-Feedback
NeurIPS 2023
Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes
EMNLP 2022
Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning
EMNLP 2022
Reframing Human-AI Collaboration for Generating Free-Text Explanations
NAACL 2022
Measuring Association Between Labels and Free-Text Rationales
EMNLP 2021
Learning to Faithfully Rationalize by Construction
ACL 2020
Attention is not not Explanation
EMNLP 2019
Clinical Concept Extraction for Document-Level Coding
ACL 2019
Explainable Prediction of Medical Codes from Clinical Text
NAACL 2018