hartvigsen-group / composable-interventions

Related projects ⓘ

Alternatives and complementary repositories for composable-interventions

• petezh / OpenD5
  Tasks for describing differences between text distributions.
  ☆16Updated 3 months ago
• activatedgeek / calibration-tuning
  ☆36Updated 3 months ago
• ThomasScialom / T0_continual_learning
  Adding new tasks to T0 without catastrophic forgetting
  ☆30Updated 2 years ago
• ruiqi-zhong / nlparam
  Augmenting Statistical Models with Natural Language Parameters
  ☆17Updated 2 months ago
• maszhongming / ParaKnowTransfer
  Code for "Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective"
  ☆30Updated 6 months ago
• ctlllll / reward_collapse
  ☆26Updated last year
• qcznlp / uncertainty_attack
  ☆12Updated 2 months ago
• formll / resolving-scaling-law-discrepancies
  ☆15Updated 4 months ago
• AndyShih12 / LongHorizonTemperatureScaling
  PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023
  ☆19Updated last year
• scalable-model-editing / unified-model-editing
  We introduce EMMET and unify model editing with popular algorithms ROME and MEMIT.
  ☆12Updated 2 months ago
• lingchen0331 / UQ_ICL
  Uncertainty quantification for in-context learning of large language models
  ☆12Updated 7 months ago
• ylsung / vl-merging
  PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"
  ☆36Updated last year
• uscnlp-lime / safer-instruct
  This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"
  ☆17Updated 8 months ago
• google / belief-localization
  This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…
  ☆55Updated last year
• tml-epfl / icl-alignment
  Is In-Context Learning Sufficient for Instruction Following in LLMs?
  ☆25Updated 5 months ago
• EvanZhuang / vector-icl
  Official implementation of Vector-ICL: In-context Learning with Continuous Vector Representations
  ☆11Updated last month
• nathanhu0 / CaMeLS
  Codebase for Context-aware Meta-learned Loss Scaling (CaMeLS). https://arxiv.org/abs/2305.15076.
  ☆23Updated 9 months ago
• TianduoWang / DPO-ST
  [ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
  ☆30Updated 3 months ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆24Updated 7 months ago
• BaohaoLiao / mefts
  [NeurIPS 2023] Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
  ☆29Updated last year
• MaHuanAAA / g_fair_prompting
  ☆31Updated last year
• felixzli / synthetic_pretraining
  ☆40Updated 2 years ago
• allenai / easy-to-hard-generalization
  Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"
  ☆44Updated 10 months ago
• VITA-Group / Random-MoE-as-Dropout
  [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…
  ☆44Updated last year
• Dakingrai / awesome-mechanistic-interpretability-lm-papers
  ☆73Updated 4 months ago
• milesaturpin / cot-unfaithfulness
  ☆32Updated last year
• alon-albalak / FLAD
  Few-shot Learning with Auxiliary Data
  ☆26Updated 11 months ago
• RyanWangZf / PromptEHR
  EMNLP'22 | PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning
  ☆26Updated last year
• THU-KEG / Skill-Neuron
  Source code for EMNLP2022 paper "Finding Skill Neurons in Pre-trained Transformers via Prompt Tuning".
  ☆18Updated last year
• shauli-ravfogel / rlace-icml
  ☆34Updated 2 years ago