conftrace_

attention head

146 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) large language model (13587) language model (4599) mechanistic interpretability (133) model compression (3302) transformer model (1996) in-context learning (1405) representation learning (6206) transformer architecture (1560) model pruning (237)

Papers

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis EMNLP 2024
When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models EMNLP 2024
Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models EMNLP 2024
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks NIPS 2024
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control NIPS 2024
HydraViT: Stacking Heads for a Scalable ViT NIPS 2024
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network NIPS 2024
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP NIPS 2024
The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models ACL 2024
Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024
Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations EMNLP 2024
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task EMNLP 2024
LoFiT: Localized Fine-tuning on LLM Representations NIPS 2024
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning NIPS 2024
Fairness-Aware Structured Pruning in Transformers AAAI 2024
Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach ACL 2024
LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models ACL 2024
How and where does CLIP process negation? ACL 2024
Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models ACL 2024
Identifying Semantic Induction Heads to Understand In-Context Learning ACL 2024
An Adversarial Example for Direct Logit Attribution: Memory Management in GELU-4L EMNLP 2024
Copy Suppression: Comprehensively Understanding a Motif in Language Model Attention Heads EMNLP 2024
VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers EMNLP 2023
Towards Lossless Head Pruning through Automatic Peer Distillation for Language Models IJCAI 2023
GOHSP: A Unified Framework of Graph and Optimization-Based Heterogeneous Structured Pruning for Vision Transformer AAAI 2023