HKUST-KnowComp / Knowledge-Constrained-Decoding
Official Code for EMNLP2023 Main Conference paper: "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection"
☆30Updated last year
Alternatives and similar repositories for Knowledge-Constrained-Decoding:
Users that are interested in Knowledge-Constrained-Decoding are comparing it to the libraries listed below
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆58Updated last year
- ☆17Updated last year
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆59Updated 9 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆109Updated 7 months ago
- ☆72Updated 4 months ago
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆99Updated 2 years ago
- ☆85Updated 2 years ago
- Unofficial re-implementation of "Trusting Your Evidence: Hallucinate Less with Context-aware Decoding"☆28Updated 5 months ago
- ACL'23: Unified Demonstration Retriever for In-Context Learning☆37Updated last year
- [NeurIPS'22 Spotlight] Data and code for our paper CoNT: Contrastive Neural Text Generation☆152Updated last year
- ☆31Updated last year
- ☆41Updated last year
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆68Updated 2 years ago
- ☆75Updated last year
- ☆61Updated 2 years ago
- [ICLR'24 Spotlight] "Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts"☆67Updated last year
- The code implementation of the EMNLP2022 paper: DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Gene…☆26Updated last year
- AbstainQA, ACL 2024☆25Updated 6 months ago
- Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".☆21Updated last year
- First explanation metric (diagnostic report) for text generation evaluation☆61Updated last month
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆63Updated last year
- Code base of In-Context Learning for Dialogue State tracking☆45Updated last year
- EMNLP'2023: Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration☆35Updated last year
- Code and data for the FACTOR paper☆45Updated last year
- This code accompanies the paper DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering.☆17Updated 2 years ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆108Updated last year
- ☆48Updated last year
- ☆13Updated 2 years ago
- ☆73Updated 11 months ago
- ☆42Updated 5 months ago