WhereIsAI / BiLLM
Tool for converting LLMs from uni-directional to bi-directional by removing causal mask for tasks like classification and sentence embeddings. Compatible with 🤗 transformers.
☆47Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for BiLLM
- Rethinking Negative Instances for Generative Named Entity Recognition☆44Updated 8 months ago
- Leveraging passage embeddings for efficient listwise reranking with large language models.☆33Updated last month
- ☆27Updated 10 months ago
- SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples☆74Updated 2 years ago
- Implementation of paper: HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking☆66Updated last year
- EMNLP'2023 (Findings): Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!☆38Updated 7 months ago
- Code and dataset for the emnlp paper titled Instruct and Extract: Instruction Tuning for On-Demand Information Extraction☆50Updated 10 months ago
- ☆21Updated last year
- Implementation of "Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation"☆77Updated last year
- [NAACL 2024] Making Language Models Better Tool Learners with Execution Feedback☆38Updated 8 months ago
- code for paper 《RankingGPT: Empowering Large Language Models in Text Ranking with Progressive Enhancement》☆29Updated 10 months ago
- ☆89Updated last month
- [EMNLP 2023] C-STS: Conditional Semantic Textual Similarity☆66Updated 6 months ago
- Source code for ACL 2023 paper Decoder Tuning: Efficient Language Understanding as Decoding☆48Updated last year
- The baseline method for CCIR 22 https://www.datafountain.cn/competitions/573☆13Updated 2 years ago
- Dual Cross Encoder for Dense Retrieval☆16Updated last year
- Code for Search-in-the-Chain: Towards Accurate, Credible and Traceable Large Language Models for Knowledge-intensive Tasks☆47Updated 7 months ago
- Implementation of the paper: "Making Retrieval-Augmented Language Models Robust to Irrelevant Context"☆62Updated 3 months ago
- ConTextual Mask Auto-Encoder for Dense Passage Retrieval☆35Updated 2 weeks ago
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆36Updated 8 months ago
- ☆7Updated last year
- ☆78Updated 2 years ago
- Code for "FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (ACL 2024)"☆89Updated 3 weeks ago
- Dataset for Findings of ACL 23 "VCSum: A Versatile Chinese Meeting Summarization Dataset"☆29Updated last year
- Code and data for "Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation" (EMNLP 2023)☆62Updated 11 months ago
- We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆51Updated 3 weeks ago
- Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation☆67Updated last week
- ☆26Updated last year
- [ACL'23 Findings] "Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors"☆38Updated 11 months ago
- An Experiment on Dynamic NTK Scaling RoPE☆61Updated 11 months ago