Seuraa
Atticus Geiger
Atticus Geiger
Pr(Ai)²R Group
Vahvistettu sähköpostiosoite verkkotunnuksessa stanford.edu - Kotisivu
Nimike
Viittaukset
Viittaukset
Vuosi
Dynabench: Rethinking benchmarking in NLP
D Kiela, M Bartolo, Y Nie, D Kaushik, A Geiger, Z Wu, B Vidgen, G Prasad, ...
In Proceedings of the 2021 Conference of the North American Chapter of the …, 2021
4022021
Causal abstractions of neural networks
A Geiger, H Lu, T Icard, C Potts
Advances in Neural Information Processing Systems 34, 9574-9586, 2021
1802021
Neural natural language inference models partially embed theories of lexical entailment and negation
A Geiger, K Richardson, C Potts
In Proceedings of the Third BlackboxNLP Workshop on Analyzing and …, 2020
932020
DynaSent: A dynamic benchmark for sentiment analysis
C Potts, Z Wu, A Geiger, D Kiela
arXiv preprint arXiv:2012.15349, 2020
812020
Interpretability at scale: Identifying causal mechanisms in alpaca
Z Wu, A Geiger, T Icard, C Potts, N Goodman
Advances in Neural Information Processing Systems 36, 2024
792024
Inducing causal structure for interpretable neural networks
A Geiger, Z Wu, H Lu, J Rozner, E Kreiss, T Icard, N Goodman, C Potts
International Conference on Machine Learning, 7324-7338, 2022
752022
Finding alignments between interpretable causal variables and distributed neural representations
A Geiger, Z Wu, C Potts, T Icard, N Goodman
Causal Learning and Reasoning, 160-187, 2024
722024
Hybrid Pluggable Processing Pipeline (HyP3): A cloud-based infrastructure for generic processing of SAR data
K Hogenson, SA Arko, B Buechler, R Hogenson, J Herrmann, A Geiger
Agu fall meeting abstracts 2016, IN21B-1740, 2016
632016
Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
A Geiger, D Ibeling, A Zur, M Chaudhary, S Chauhan, J Huang, A Arora, ...
arXiv preprint arXiv:2301.04709, 2023
54*2023
Posing fair generalization tasks for natural language inference
A Geiger, I Cases, L Karttunen, C Potts
In Proceedings of the 2019 Conference on Empirical Methods in Natural …, 2019
492019
Cebab: Estimating the causal effects of real-world concepts on nlp model behavior
ED Abraham, K D'Oosterlinck, A Feder, Y Gat, A Geiger, C Potts, ...
Advances in Neural Information Processing Systems 35, 17582-17596, 2022
442022
Language Models Linearly Represent Sentiment
O Hollinsworth, C Tigges, A Geiger, N Nanda
Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting …, 2024
38*2024
Reft: Representation finetuning for language models
Z Wu, A Arora, Z Wang, A Geiger, D Jurafsky, CD Manning, C Potts
arXiv preprint arXiv:2404.03592, 2024
332024
Causal proxy models for concept-based model explanations
Z Wu, K D’Oosterlinck, A Geiger, A Zur, C Potts
International conference on machine learning, 37313-37334, 2023
332023
Recursive routing networks: Learning to compose modules for language understanding
I Cases, C Rosenbaum, M Riemer, A Geiger, T Klinger, A Tamkin, O Li, ...
Proceedings of the 2019 Conference of the North American Chapter of the …, 2019
302019
Stress-testing neural models of natural language inference with multiply-quantified sentences
A Geiger, I Cases, L Karttunen, C Potts
arXiv preprint arXiv:1810.13033, 2018
302018
Rigorously assessing natural language explanations of neurons
J Huang, A Geiger, K D'Oosterlinck, Z Wu, C Potts
arXiv preprint arXiv:2309.10312, 2023
272023
Relational reasoning and generalization using nonsymbolic neural networks.
A Geiger, A Carstensen, MC Frank, C Potts
Psychological Review 130 (2), 308, 2023
222023
Causal distillation for language models
Z Wu, A Geiger, J Rozner, E Kreiss, H Lu, T Icard, C Potts, ND Goodman
arXiv preprint arXiv:2112.02505, 2021
222021
Is this the subspace you are looking for? an interpretability illusion for subspace activation patching
A Makelov, G Lange, N Nanda
arXiv preprint arXiv:2311.17030, 2023
122023
Järjestelmä ei voi suorittaa toimenpidettä nyt. Yritä myöhemmin uudelleen.
Artikkelit 1–20