vicgalle / distilled-self-critique
distilled Self-Critique refines the outputs of a LLM with only synthetic data
☆11Updated 11 months ago
Alternatives and similar repositories for distilled-self-critique:
Users that are interested in distilled-self-critique are comparing it to the libraries listed below
- Code for the arXiv paper: "LLMs as Factual Reasoners: Insights from Existing Benchmarks and Beyond"☆59Updated 2 months ago
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval☆43Updated 5 months ago
- The data and the PyTorch implementation for the models and experiments in the paper "Exploiting Asymmetry for Synthetic Training Data Gen…☆60Updated last year
- A extension of Transformers library to include T5ForSequenceClassification class.☆38Updated last year
- Code and data for paper "Context-faithful Prompting for Large Language Models".☆39Updated 2 years ago
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions☆42Updated 8 months ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆21Updated 3 weeks ago
- ☆23Updated 2 months ago
- A Human-LLM Collaborative Dataset for Generative Information-seeking with Attribution☆30Updated last year
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆20Updated 7 months ago
- [ACL 2023] Few-shot Reranking for Multi-hop QA via Language Model Prompting☆27Updated last year
- ☆39Updated 2 years ago
- Few-shot Learning with Auxiliary Data☆27Updated last year
- ☆43Updated 9 months ago
- ☆28Updated last year
- This is a meta-model distilled from LLMs for information extraction. This is an intermediate checkpoint that can be well-transferred to a…☆27Updated last month
- Implementation of "SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models"☆27Updated last month
- Repository for "Propagating Knowledge Updates to LMs Through Distillation" (NeurIPS 2023).☆25Updated 7 months ago
- ☆25Updated 2 years ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆18Updated last month
- ☆41Updated 2 months ago
- Code for paper 'Data-Efficient FineTuning'☆29Updated last year
- code associated with WANLI dataset in Liu et al., 2022☆30Updated last year
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆31Updated 9 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆47Updated last year
- Evaluate the Quality of Critique☆34Updated 9 months ago
- Code, datasets, models for the paper "Automatic Evaluation of Attribution by Large Language Models"☆56Updated last year
- ☆68Updated last year
- Official codebase for permutation self-consistency.☆18Updated last year
- Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"☆83Updated 7 months ago