Daking Rai

5 papers · 2023–2025 · 3 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16)

Venues

ACL (2) EMNLP (2) AAAI (1)

Top co-authors

Ziyu Yao (5) Yilun Zhou (3) bailin wang (2) Haiyan Zhao (1) Xuansheng Wu (1) Dong Shu (1) Ninghao Liu (1) Mengnan Du (1) Siddarth Mamidanna (1)

Research topics

Artificial Intelligence (5) Core AI (5) Deep Learning (4) Machine Learning (3) Architectures (3) Natural Language Processing (2) Models (2) Application Areas (1) Applications (1) Core Methods (1) Generation (1) Learning Types (1) Optimization & Theory (1) Techniques (1) Understanding (1)

Keywords

large language model (4) language model (2) mechanistic interpretability (2) semantic parsing (2) feature extraction (1) structured prediction (1) neural network analysis (1) feature disentanglement (1) compositional generalization (1) model interpretability (1) sparse autoencoder (1) chain-of-thought prompting (1) multi-layer perceptron (1) neuron activation (1) arithmetic reasoning (1) feed-forward layer (1) information transfer (1) neural network (1) mental math (1) layer depth (1)

Papers

All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens EMNLP 2025 A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models EMNLP 2025 An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs ACL 2024 Explaining Large Language Model-Based Neural Semantic Parsers (Student Abstract) AAAI 2023 Improving Generalization in Language Model-based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-based Techniques ACL 2023