ncsoft / offsetbias
Official implementation of "OffsetBias: Leveraging Debiased Data for Tuning Evaluators"
☆14Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for offsetbias
- An unofficial implementation of SOLAR-10.7B model and the newly proposed interlocked-DUS(iDUS) implementation and experiment details.☆13Updated 7 months ago
- [NAACL 2024] Official repository for "KTRL+F: Knowledge-Augmented In-Document Search"☆20Updated last month
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆36Updated last month
- KoCommonGEN v2: A Benchmark for Navigating Korean Commonsense Reasoning Challenges in Large Language Models☆25Updated 2 months ago
- [ACL 2024] LangBridge: Multilingual Reasoning Without Multilingual Supervision☆78Updated last week
- Sakura-SOLAR-DPO: Merge, SFT, and DPO☆115Updated 10 months ago
- ☆9Updated last month
- ☆18Updated 3 months ago
- All-in-one repository for Fine-tuning & Pretraining (Large) Language Models☆15Updated last year
- Difference-based Contrastive Learning for Korean Sentence Embeddings☆24Updated last year
- Official code and dataset repository of KoBBQ (TACL 2024)☆14Updated 5 months ago
- Calculating Expected Time for training LLM.☆38Updated last year
- 1-Click is all you need.☆59Updated 6 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆28Updated 5 months ago
- evolve llm training instruction, from english instruction to any language.☆113Updated last year
- CLIcK: A Benchmark Dataset of Cultural and Linguistic Intelligence in Korean☆41Updated 2 months ago
- Developing a Korean LLM model : Hate Speech Filtering, Improving conversational skills, Finetuning with the RLHF method☆15Updated 4 months ago
- [EACL 2023] CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification☆37Updated last year
- Evaluate gpt-4o on CLIcK (Korean NLP Dataset)☆20Updated 5 months ago
- Chain-of-thought 방식을 활용하여 llama2를 fine-tuning☆10Updated 11 months ago
- [ACL 2023] Gradient Ascent Post-training Enhances Language Model Generalization☆27Updated 2 months ago
- 언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.☆19Updated last year
- Reward Model을 이용하여 언어모델의 답변을 평가하기☆27Updated 8 months ago
- huggingface에 있는 한국어 데이터 세트☆21Updated last month
- ☆23Updated 11 months ago
- Hate speech detection corpus in Korean, shared with EMNLP 2023 paper☆13Updated 6 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆41Updated 9 months ago
- MEXMA: Token-level objectives improve sentence representations☆32Updated this week
- ☆37Updated last year