QingruZhang / PASTALinks
PASTA: Post-hoc Attention Steering for LLMs
☆117Updated 6 months ago
Alternatives and similar repositories for PASTA
Users that are interested in PASTA are comparing it to the libraries listed below
Sorting:
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆106Updated 3 months ago
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆81Updated 9 months ago
- Self-Alignment with Principle-Following Reward Models☆161Updated 3 weeks ago
- Inspecting and Editing Knowledge Representations in Language Models☆116Updated last year
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆73Updated 2 weeks ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆110Updated last year
- Implementation of the paper: "Answering Questions by Meta-Reasoning over Multiple Chains of Thought"☆95Updated last year
- [ICML 2023] Code for our paper “Compositional Exemplars for In-context Learning”.☆100Updated 2 years ago
- contrastive decoding☆200Updated 2 years ago
- ☆97Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆58Updated 6 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆167Updated last month
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆78Updated 4 months ago
- A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.☆85Updated last year
- ☆94Updated last year
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆68Updated 2 years ago
- [ICLR 2024] Evaluating Large Language Models at Evaluating Instruction Following☆127Updated 10 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆111Updated 8 months ago
- The Paper List on Data Contamination for Large Language Models Evaluation.☆94Updated 2 months ago
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval☆125Updated 2 weeks ago
- Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".☆159Updated last year
- [ICLR'24 Spotlight] "Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts"☆68Updated last year
- [NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't…☆111Updated 10 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆76Updated last year
- ☆131Updated 6 months ago
- ☆85Updated 2 years ago
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆51Updated last year
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆111Updated 8 months ago
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging☆106Updated last year
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"☆155Updated 2 weeks ago