rmovva / LLM-publication-patterns-publicLinks
Describing changes in LLM research trends in 2023. https://arxiv.org/abs/2307.10700
β18Updated last year
Alternatives and similar repositories for LLM-publication-patterns-public
Users that are interested in LLM-publication-patterns-public are comparing it to the libraries listed below
Sorting:
- πΎ Universal, customizable and deployable fine-grained evaluation for text generation.β23Updated last year
- Aligned, Review-Informed Edits of Scientific Papersβ53Updated last year
- Codebase the paper "The Remarkable Robustness of LLMs: Stages of Inference?"β18Updated 2 weeks ago
- Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.β40Updated 3 months ago
- A package dedicated for running benchmark agreement testingβ16Updated last month
- β53Updated 6 months ago
- [EMNLP 2024] A Retrieval Benchmark for Scientific Literature Searchβ89Updated 6 months ago
- [ICLR'25] "Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers"β23Updated 2 months ago
- Few-shot Learning with Auxiliary Dataβ28Updated last year
- Retrieval-Augmented Generation battle!β52Updated 6 months ago
- Code/data for MARG (multi-agent review generation)β44Updated 7 months ago
- β35Updated 2 years ago
- β22Updated 6 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Modelβ43Updated last year
- The codebase for our ACL2023 paper: Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learniβ¦β30Updated last year
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.β41Updated last year
- β13Updated last month
- Starbucks: Improved Training for 2D Matryoshka Embeddingsβ21Updated 4 months ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Caβ¦β61Updated 2 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 laβ¦β48Updated last year
- List of papers on Self-Correction of LLMs.β73Updated 5 months ago
- β44Updated 7 months ago
- The Codebase for Causal Distillation for Language Models (NAACL '22)β25Updated 3 years ago
- β25Updated last year
- β51Updated last year
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructionsβ44Updated 11 months ago
- This repository includes a benchmark and code for the paper "Evaluating LLMs at Detecting Errors in LLM Responses".β29Updated 10 months ago
- β38Updated last year
- Official Repository for "Hypencoder: Hypernetworks for Information Retrieval"β25Updated 3 months ago
- Support Continual pre-training & Instruction Tuning forked from llama-recipesβ32Updated last year