[24' ACL] Spectral Filters, Dark Signals, and Attention Sinks 2024.09.04 | Language Attention Interpretability
[24' ICLR] StreamingLLM: Efficient Streaming Language Models with Attention Sinks 2024.08.29 | Language Attention Efficiency
[24' ICLR] PASTA: Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs 2024.08.29 | Language Attention
[Mechanistic Interpretability] Token-wise Attribution Analysis (History of Kobayashi) 2024.08.24 | Language Interpretability Summary
[Summary] Recent Contrastive Decoding Variants (2) 2024.08.16 | Language Contrastive Decoding Summary
[Summary] Recent Contrastive Decoding Variants (1) 2024.08.15 | Language Contrastive Decoding Summary
[24' ICLR] DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models 2024.08.14 | Language Contrastive Decoding Interpretability
[23' ACL] Contrastive Decoding: Open-ended Text Generation as Optimization 2024.08.14 | Language Contrastive Decoding
[23' EMNLP] Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning 2024.08.13 | Language Interpretability
[24'] Not All Layers of LLMs Are Necessary During Inference 2024.08.13 | Language Decoding Interpretability
[24' ICML-WS] Transformers need glasses! Information over-squashing in language tasks 2024.07.26 | Language Hallucination Interpretability
[24' TACL] Lost in the Middle: How Language Models Use Long Contexts 2024.07.26 | Language Hallucination
[24' ICLR] Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models 2024.07.26 | Language Hallucination Interpretability
[Summary] Analysis of Parameter-Efficient Fine-Tuning Techniques for Large Language Models 2024.06.24 | Language Analysis PEFT Summary
[22' ICLR] Towards a Unified View of Parameter-Efficient Transfer Learning 2024.06.24 | Language Adapter PEFT
[Summary] Brief Summary of Parameter-Efficient Fine-Tuning for Language Models 2024.06.23 | Language Adapter Tuning LoRA PEFT Prefix Tuning Prompt Tuning Summary
[24' ICLR] LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention 2024.06.23 | Language PEFT Prefix Tuning
[23' ICLR] Auto-CoT: Automatic Chain of Thought Prompting in Large Language Models 2024.06.20 | Language Chain-of-Thought
[22' NIPS] Zero-shot-CoT: Large Language Models are Zero-Shot Reasoners 2024.06.19 | Language Chain-of-Thought
[22' NIPS] Chain-of-Thought Prompting Elicits Reasoning in Large Language Models 2024.06.19 | Language Chain-of-Thought
[23'] RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback 2024.06.11 | Language RLAIF RLHF
[24' ICML] Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study 2024.06.11 | Language Analysis DPO PPO RLHF
[23' NIPS] Direct Preference Optimization: Your Language Model is Secretly a Reward Model 2024.06.11 | Language DPO RLHF
[24'] Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding 2024.06.03 | Language Meta-Prompting