launchnlp / BOLT
Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".
☆21Updated last year
Alternatives and similar repositories for BOLT:
Users that are interested in BOLT are comparing it to the libraries listed below
- ☆25Updated 2 years ago
- ☆22Updated 5 months ago
- ☆74Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆50Updated 3 months ago
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆66Updated 2 years ago
- Restore safety in fine-tuned language models through task arithmetic☆27Updated 11 months ago
- [EMNLP-2022 Findings] Code for paper “ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback”.☆26Updated 2 years ago
- ☆15Updated 9 months ago
- ☆16Updated last year
- Code for Residual Energy-Based Models for Text Generation in PyTorch.☆23Updated 3 years ago
- ☆30Updated 10 months ago
- Augmenting Statistical Models with Natural Language Parameters☆23Updated 6 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
- The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning (NeurIPS 2022)☆14Updated 2 years ago
- ☆37Updated last year
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆54Updated 8 months ago
- AbstainQA, ACL 2024☆25Updated 5 months ago
- Resources for Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. EMNLP 2022.☆21Updated 2 years ago
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆58Updated last year
- ☆47Updated last year
- Repo for paper: Controllable Text Generation with Language Constraints☆19Updated last year
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆97Updated 2 years ago
- [EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.☆48Updated 3 years ago
- ☆28Updated last year
- Repository for ACL 2022 paper Mix and Match: Learning-free Controllable Text Generation using Energy Language Models☆42Updated 3 years ago
- ☆86Updated last year
- Methods and evaluation for aligning language models temporally☆27Updated last year
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆21Updated last week
- ☆30Updated 10 months ago
- ☆47Updated last year