Pinned Loading

1. FormatBiasEval FormatBiasEval Public

   Official codes for NAACL 2025 paper "LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs"

   Python 11 4

2. Adv-In-Context-Learning Adv-In-Context-Learning Public

   Forked from zhaoyiran924/Adv-In-Context-Learning

   [ACL 2024] Prompt Optimization via Adversarial In-Context Learning

   Python

3. Multi-expert-Prompting Multi-expert-Prompting Public

   Official codes for EMNLP 2024 paper "Multi-expert Prompting Improves Reliability, Safety and Usefulness of Large Language Models"

   Python 37 9

4. LongGuide LongGuide Public

   Official codes for ACL 2025 paper "Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines"

   Python 4 1

5. NLPromptEval NLPromptEval Public

   Official codes for ACL 2025 paper "What Makes a Good Natural Language Prompt?"

   Python 5

6. COO COO Public

   Official codes for COLING 2025 paper "Aligning Large Language Models with Human Opinions through Persona Selection and Value-Belief-Norm Reasoning"

   Python 4