Open Problems in Mechanistic Interpretability
Paper
•
2501.16496
•
Published
•
19
Mechanistic Interpretability Benchmark
university
AI & ML interests
Principled evaluation of mechanistic interpretability methods.
mib-bench's activity
atticusg
authored
a
paper
2 months ago
hadasor
authored
a
paper
3 months ago
hadasor
authored
a
paper
6 months ago
atticusg
authored
a
paper
7 months ago
AdamBelfki
authored
a
paper
9 months ago
amueller
authored
a
paper
9 months ago
sarahwie
authored
5
papers
9 months ago
Self-Refine: Iterative Refinement with Self-Feedback
Paper
•
2303.17651
•
Published
•
2
Reframing Human-AI Collaboration for Generating Free-Text Explanations
Paper
•
2112.08674
•
Published
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing
Paper
•
2102.12060
•
Published
Attentiveness to Answer Choices Doesn't Always Entail High QA Accuracy
Paper
•
2305.14596
•
Published
•
1
The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
Paper
•
2401.06751
•
Published
•
1
alestolfo
authored
a
paper
10 months ago
hij
authored
3
papers
10 months ago
Rigorously Assessing Natural Language Explanations of Neurons
Paper
•
2309.10312
•
Published
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
Paper
•
2401.12631
•
Published
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
Paper
•
2403.07809
•
Published
•
1
atticusg
authored
5
papers
10 months ago
DynaSent: A Dynamic Benchmark for Sentiment Analysis
Paper
•
2012.15349
•
Published
ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning
Paper
•
2305.19426
•
Published
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
Paper
•
2205.14140
•
Published
Rigorously Assessing Natural Language Explanations of Neurons
Paper
•
2309.10312
•
Published
Linear Representations of Sentiment in Large Language Models
Paper
•
2310.15154
•
Published