atticusg / Interchange
☆11Updated 2 years ago
Related projects: ⓘ
- Code repository for the paper "Mission: Impossible Language Models".☆27Updated 8 months ago
- A codebase for ACL 2023 paper: Mitigating Label Biases for In-context Learning☆9Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆26Updated last month
- A framework to train language models to learn invariant representations.☆12Updated 2 years ago
- Official code for paper Understanding the Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation☆13Updated 6 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆28Updated 6 months ago
- ☆10Updated 2 years ago
- The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning (NeurIPS 2022)☆13Updated last year
- CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior☆11Updated last year
- The official repository for Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapte…☆14Updated 8 months ago
- Code for preprint: Summarizing Differences between Text Distributions with Natural Language☆39Updated last year
- NLPBench: Evaluating NLP-Related Problem-solving Ability in Large Language Models☆9Updated 10 months ago
- The data and the PyTorch implementation for the models and experiments in the paper "Language Model Decoding as Likelihood–Utility Alignm…☆13Updated last year
- Code for NAACL 2022 paper "Reframing Human-AI Collaboration for Generating Free-Text Explanations"☆31Updated last year
- ☆25Updated 9 months ago
- ☆22Updated 6 months ago
- Repository of paper "LLMs with Chain-of-Thought Are Non-Causal Reasoners"☆14Updated 5 months ago
- ☆30Updated 7 months ago
- Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".☆17Updated last year
- Add note-taking to semantic scholar☆11Updated last year
- Group-conditional DRO to alleviate spurious correlations☆15Updated 3 years ago
- Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding☆18Updated last year
- ☆29Updated 10 months ago
- ☆26Updated 5 months ago
- ☆10Updated 7 months ago
- ☆19Updated 11 months ago
- Is Vec2Text Really a Threat toDense Retrieval Systems?☆15Updated 2 months ago
- [EMNLP 2021] Dataset and PyTorch Code for ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning☆10Updated last year
- The code of paper "Toward Optimal LLM Alignments Using Two-Player Games".☆11Updated 2 months ago
- [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evalua…☆26Updated last year