mt-upc / logit-explanationsLinks
☆14Updated 2 years ago
Alternatives and similar repositories for logit-explanations
Users that are interested in logit-explanations are comparing it to the libraries listed below
Sorting:
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆68Updated 2 years ago
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆59Updated last year
- ☆44Updated 11 months ago
- ☆17Updated 2 years ago
- [ACL 2023] Knowledge Unlearning for Mitigating Privacy Risks in Language Models☆82Updated 11 months ago
- Unofficial re-implementation of "Trusting Your Evidence: Hallucinate Less with Context-aware Decoding"☆31Updated 9 months ago
- ☆64Updated 2 years ago
- Code & Data for our Paper "Alleviating Hallucinations of Large Language Models through Induced Hallucinations"☆69Updated last year
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆61Updated last year
- ☆87Updated 2 years ago
- Official Code for EMNLP2023 Main Conference paper: "KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detec…☆30Updated last year
- [EMNLP 2022] TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models☆73Updated last year
- ☆75Updated last year
- This is the oficial repository for "Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts" (EMNLP 2022)☆102Updated 2 years ago
- contrastive decoding☆203Updated 2 years ago
- ☆28Updated 11 months ago
- ☆27Updated 2 years ago
- ☆34Updated 2 years ago
- EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975☆38Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆114Updated last year
- ☆81Updated 8 months ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- ☆77Updated last year
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆102Updated 2 years ago
- ☆20Updated last year
- ☆25Updated 2 months ago
- Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".☆20Updated last year
- ☆177Updated last year
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆114Updated 11 months ago
- AbstainQA, ACL 2024☆28Updated 10 months ago