BunsenFeng / PoliLean
Code for "From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models". ACL 2023. Best Paper Award.
☆26Updated 6 months ago
Related projects: ⓘ
- EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975☆37Updated 9 months ago
- ☆19Updated 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…☆44Updated 9 months ago
- ☆92Updated 4 months ago
- ☆77Updated last year
- AbstainQA, ACL 2024☆17Updated 3 weeks ago
- ☆32Updated 5 months ago
- Code for the ACL 2023 Paper "Fact-Checking Complex Claims with Program-Guided Reasoning"☆47Updated last year
- Codes for ACL 2023 Paper "Fact-Checking Complex Claims with Program-Guided Reasoning"☆27Updated last year
- The Prism Alignment Project☆32Updated 4 months ago
- ☆35Updated last year
- Code and data associated with the AmbiEnt dataset in "We're Afraid Language Models Aren't Modeling Ambiguity" (Liu et al., 2023)☆51Updated 7 months ago
- ☆46Updated 10 months ago
- ☆36Updated 5 months ago
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆83Updated 2 years ago
- Repository for ACL 2022 paper Mix and Match: Learning-free Controllable Text Generation using Energy Language Models☆39Updated 2 years ago
- ☆44Updated 8 months ago
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models"☆54Updated 8 months ago
- Evaluate the Quality of Critique☆35Updated 3 months ago
- Teaching Models to Express Their Uncertainty in Words☆36Updated 2 years ago
- EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation☆38Updated last year
- ☆42Updated 7 months ago
- Methods and evaluation for aligning language models temporally☆24Updated 6 months ago
- ☆44Updated 2 weeks ago
- Official repository for EMNLP'22 paper: Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering☆24Updated last year
- Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant se…☆51Updated last year
- Code and data for paper "Context-faithful Prompting for Large Language Models".☆37Updated last year
- [ICLR'24 Spotlight] "Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts"☆51Updated 5 months ago
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval☆41Updated last month
- Resources for Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. EMNLP 2022.☆19Updated last year