HanNight / AdaCAD
Code for paper "AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge"
☆12Updated 3 months ago
Alternatives and similar repositories for AdaCAD:
Users that are interested in AdaCAD are comparing it to the libraries listed below
- Merging Generated and Retrieved Knowledge for Open-Domain QA (EMNLP 2023)☆22Updated last year
- ☆38Updated last year
- Source code for InBedder, an instruction-following text embedder☆24Updated 3 months ago
- Resources for Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. EMNLP 2022.☆21Updated 2 years ago
- Answering Ambiguous Questions via Iterative Prompting☆13Updated 7 months ago
- Code and data for paper "Context-faithful Prompting for Large Language Models".☆39Updated last year
- Methods and evaluation for aligning language models temporally☆27Updated 10 months ago
- Resources for our ACL 2023 paper: Distilling Script Knowledge from Large Language Models for Constrained Language Planning☆35Updated last year
- ☆31Updated last year
- AbstainQA, ACL 2024☆25Updated 3 months ago
- [ACL 23] CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors☆33Updated 7 months ago
- ☆14Updated last year
- BeHonest: Benchmarking Honesty in Large Language Models☆30Updated 5 months ago
- [NAACL 2024] Making Language Models Better Tool Learners with Execution Feedback☆39Updated 10 months ago
- ☆34Updated 2 months ago
- This code accompanies the paper DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering.☆17Updated last year
- the instructions and demonstrations for building a formal logical reasoning capable GLM☆53Updated 4 months ago
- [ICLR'24 Spotlight] "Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts"☆64Updated 9 months ago
- The official code and dataset for EMNLP 2022 paper "COPEN: Probing Conceptual Knowledge in Pre-trained Language Models".☆19Updated last year
- Data and code for ACL 2022 paper "MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data"☆42Updated 2 months ago
- WikiWhy is a new benchmark for evaluating LLMs' ability to explain between cause-effect relationships. It is a QA dataset containing 9000…☆47Updated last year
- ☆85Updated last year
- Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆39Updated last month
- "FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context Learning" (ACL 2023)☆13Updated last year
- ☆28Updated 11 months ago
- Towards Systematic Measurement for Long Text Quality☆31Updated 4 months ago
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval☆65Updated 2 weeks ago
- Findings of EMNLP 2023: InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspe…☆14Updated 5 months ago
- ☆40Updated last year
- Evaluate the Quality of Critique☆35Updated 7 months ago