emory-irlab / DUQGen
Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation
☆12Updated 7 months ago
Alternatives and similar repositories for DUQGen:
Users that are interested in DUQGen are comparing it to the libraries listed below
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval☆41Updated 4 months ago
- ☆17Updated 4 months ago
- Starbucks: Improved Training for 2D Matryoshka Embeddings☆18Updated 3 weeks ago
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions☆43Updated 8 months ago
- ☆39Updated 6 months ago
- This is the official project of paper: Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conver…☆17Updated 3 months ago
- Synthesizing realistic and diverse text-datasets from augmented LLMs☆12Updated last week
- ☆17Updated 6 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆31Updated 8 months ago
- ☆15Updated 4 months ago
- [arXiv preprint] Official Repository for "Evaluating Language Models as Synthetic Data Generators"☆34Updated 2 months ago
- ☆57Updated 5 months ago
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆43Updated 2 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆54Updated 6 months ago
- ☆19Updated 3 months ago
- XTR: Rethinking the Role of Token Retrieval in Multi-Vector Retrieval☆45Updated 8 months ago
- Tasks for describing differences between text distributions.☆16Updated 6 months ago
- Embedding Recycling for Language models☆38Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated 11 months ago
- Official implementation for "Law of the Weakest Link: Cross capabilities of Large Language Models"☆42Updated 5 months ago
- ☆12Updated 5 months ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆46Updated last year
- ☆20Updated 9 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆42Updated last year
- Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"☆83Updated 6 months ago
- Codes and datasets for the paper Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Ref…☆43Updated this week
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval☆80Updated 2 weeks ago
- ☆42Updated 8 months ago
- ☆12Updated last year