kaistAI / factual-knowledge-acquisitionLinks
☆22Updated 2 weeks ago
Alternatives and similar repositories for factual-knowledge-acquisition
Users that are interested in factual-knowledge-acquisition are comparing it to the libraries listed below
Sorting:
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆32Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆44Updated last year
- [ACL 2023] Gradient Ascent Post-training Enhances Language Model Generalization☆29Updated 11 months ago
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆49Updated 2 weeks ago
- SILO Language Models code repository☆81Updated last year
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙 𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆51Updated last year
- ☆29Updated last year
- [ICML 2023] Exploring the Benefits of Training Expert Language Models over Instruction Tuning☆99Updated 2 years ago
- Code for "Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model", EMNLP Findings 20…☆28Updated last year
- Adding new tasks to T0 without catastrophic forgetting☆33Updated 2 years ago
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆22Updated last year
- [AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following☆78Updated 11 months ago
- [ACL 2025 Main] Official Repository for "Evaluating Language Models as Synthetic Data Generators"☆38Updated 8 months ago
- Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators (Liu et al.; COLM 2024)☆48Updated 7 months ago
- [ICLR 2023] Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners☆116Updated last month
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions☆45Updated last year
- Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation☆15Updated 4 months ago
- This repository contains data, code and models for contextual noncompliance.☆24Updated last year
- Codebase for Instruction Following without Instruction Tuning☆35Updated 11 months ago
- [ICLR 2025 Oral] Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition☆12Updated 9 months ago
- ☆74Updated last year
- ☆27Updated last year
- Repository for "Propagating Knowledge Updates to LMs Through Distillation" (NeurIPS 2023).☆26Updated last year
- Learning adapter weights from task descriptions☆19Updated last year
- An unofficial implementation of SOLAR-10.7B model and the newly proposed interlocked-DUS(iDUS) implementation and experiment details.☆12Updated last year
- 👻 Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"☆55Updated last year
- ☆14Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- ☆45Updated 4 months ago
- Few-shot Learning with Auxiliary Data☆31Updated last year