joeljang / ELM
[ICML 2023] Exploring the Benefits of Training Expert Language Models over Instruction Tuning
☆97Updated last year
Related projects: ⓘ
- Retrieval as Attention☆77Updated last year
- DEMix Layers for Modular Language Modeling☆51Updated 3 years ago
- [ICLR 2022] Towards Continual Knowledge Learning of Language Models☆93Updated last year
- TBC☆26Updated last year
- [EMNLP 2022] TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models☆65Updated 4 months ago
- SILO Language Models code repository☆80Updated 6 months ago
- Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"☆71Updated last year
- ☆78Updated last year
- [EMNLP 2023 Findings] Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt☆20Updated 10 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆28Updated 3 months ago
- ☆24Updated 6 months ago
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆83Updated 2 years ago
- ☆26Updated last year
- [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following☆79Updated last week
- Findings of ACL'2023: Optimizing Test-Time Query Representations for Dense Retrieval☆29Updated 10 months ago
- ☆55Updated last year
- ☆46Updated 10 months ago
- Benchmarking Generalization to New Tasks from Natural Language Instructions☆25Updated 3 years ago
- ☆44Updated 2 weeks ago
- ☆14Updated 6 months ago
- This is the oficial repository for "Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts" (EMNLP 2022)☆96Updated last year
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆91Updated last year
- Influence Experiments☆36Updated last year
- ☆32Updated 5 months ago
- [ICLR 2023] Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners☆109Updated last week
- Code for paper 'Data-Efficient FineTuning'☆29Updated last year
- ☆15Updated last year
- [ACL 2024 NLP4ConvAI Oral] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system m…☆33Updated 3 months ago
- The official code of TACL 2021, "Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies".☆64Updated last year
- [NeurIPS 2022] Generating Training Data with Language Models: Towards Zero-Shot Language Understanding☆63Updated 2 years ago