awesome-parametric-knowledge-in-llms
github.com/trae1oung/awesome-parametric-knowledge-in-llms ↗Must-read papers and blogs about parametric knowledge mechanism in LLMs.
39
GitHub Stars
99
Curated Resources
16
Categories
21 hours ago
Last Refreshed
Knowledge in Transformer-based Model——Analysis🧠Knowledge in Transformer-based Model——Causal Tracing🦾Knowledge in Transformer-based Model——Gradient Attribution👀Knowledge in Transformer-based Model——Activation🫀2023Knowledge Editing 🧑⚕️Knowledge Transfer🧚♀️2024Knowledge DistillationPramatric QuantizationKnowledge InjectionParameter-Effecient Fine-tuning(PEFT)Continual LearningRAGLong Context ExtendLong2Short Compression
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me 2024 resources from awesome-parametric-knowledge-in-llms"
Installation instructions →What's inside
Knowledge Editing 🧑⚕️
- A Comprehensive Study of Knowledge Editing for Large Language Models2024
- Editable neural networks.2020
- Editing Factual Knowledge in Language Models2021
- Editing Large Language Models: Problems, Methods, and Opportunities2023
- Ethos: Rectifying language models in orthogonal parameter space2024
- FAME: Towards Factual Multi-Task Model Editing2024
2023
Knowledge in Transformer-based Model——Activation🫀
- Activation-informed merging of large language models2025
- Exploring the benefit of activation sparsity in pre-training2024
- From yes-men to truth-tellers Addressing sycophancy in large language models with pinpoint tuning2024
- Improving instruction-following in language models through activation steering2025
- Language-specific neurons: The key to multilingual capabilities in large language models.2024
- Separating tongue from thought: Activation patching reveals language-agnostic concept representations in transformers2024
Knowledge in Transformer-based Model——Analysis🧠
- Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts2024
- Decoding specialised feature neurons in LLMs with the final projection layer2025
- Disentangling Memory and Reasoning Ability in Large Language Models2024
- Dissecting recall of factual associations in auto-regressive language models2024
- Evaluating the External and Parametric Knowledge Fusion of Large Language Models2024
- INSIDE: LLMs' internal states retain the power of hallucination detection2024
Knowledge Injection
- Awakening augmented generation: Learning to awaken internal knowledge of large language models for question answering2024
- Decouple knowledge from parameters for plug-and-play language modeling2023
- Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass2024
- IN-PARAMETER KNOWLEDGE INJECTION: INTEGRATING TEMPORARY CONTEXTUAL INFORMATION INTO MODEL PARAMETERS2023
- Kformer: Knowledge injection in transformer feed-forward layers2022
- Memory injections: Correcting multi-hop reasoning failures during inference in transformer-based language models2023
Knowledge Transfer🧚♀️
- Beyond task vectors: Selective task arithmetic based on importance metrics2024
- Chat vector: A simple approach to equip LLMs with instruction following and model alignment in new languages2024
- Composing parameter-efficient modules with arithmetic operations2023
- Cross-model Control: Improving Multiple Large Language Models in One-time Training2024
- Dataless knowledge fusion by merging weights of language models2023
- Determine-then-ensemble: Necessity of top-k union for large language model ensembling2024
Parameter-Effecient Fine-tuning(PEFT)
- CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning2024
- DoRA: Weight-Decomposed Low-Rank Adaptation2024
- KaSA: Knowledge-aware singular-value adaptation of large language models2024
- Low-rank adaptation with task-relevant feature enhancement for fine-tuning language models2024
Long2Short Compression
- CoT-valve: Length-compressible chain-of-thought tuning2025
- LLMLingua-2: Data distillation for efficient and faithful task-agnostic prompt compression2024
- LLMLingua: Compressing prompts for accelerated inference of large language models2023
- TokenSkip: Controllable chain-of-thought compression in LLMs2025
Showing a sample of 99 resources. View the full list on GitHub →