Daking Rai
Orcid: 0009-0003-3769-4974
According to our database1,
Daking Rai authored at least 9 papers
between 2023 and 2025.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2025
Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones.
CoRR, July, 2025
CoRR, February, 2025
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025
All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
2024
Understanding the Effect of Algorithm Transparency of Model Explanations in Text-to-SQL Semantic Parsing.
CoRR, 2024
A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models.
CoRR, 2024
An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
2023
Improving Generalization in Language Model-based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-based Techniques.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2023
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023