milesaturpin / cot-unfaithfulness

Related projects ⓘ

Alternatives and complementary repositories for cot-unfaithfulness

• tml-epfl / icl-alignment
  Is In-Context Learning Sufficient for Instruction Following in LLMs?
  ☆25Updated 5 months ago
• paul-rottger / exaggerated-safety
  Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆64Updated 10 months ago
• ejones313 / auditing-llms
  ☆49Updated last year
• ruiqi-zhong / nlparam
  Augmenting Statistical Models with Natural Language Parameters
  ☆17Updated 2 months ago
• pratyushmaini / llm_dataset_inference
  Official Repository for Dataset Inference for LLMs
  ☆23Updated 3 months ago
• petezh / OpenD5
  Tasks for describing differences between text distributions.
  ☆16Updated 3 months ago
• thestephencasper / explore_establish_exploit_llms
  ☆31Updated last year
• shadowkiller33 / Contrast-Instruction
  ☆19Updated last year
• tatsu-lab / linguistic_calibration
  Align your LM to express calibrated verbal statements of confidence in its long-form generations.
  ☆19Updated 5 months ago
• EleutherAI / w2s
  ☆18Updated last month
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆63Updated last year
• Nanami18 / Snowballed_Hallucination
  ☆44Updated 2 months ago
• activatedgeek / calibration-tuning
  ☆36Updated 3 months ago
• shauli-ravfogel / rlace-icml
  ☆34Updated 2 years ago
• jmerullo / lm_vector_arithmetic
  ☆28Updated last year
• google / belief-localization
  This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…
  ☆55Updated last year
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆57Updated 2 weeks ago
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆89Updated 5 months ago
• XiangLi1999 / AutoBencher
  ☆25Updated 4 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆31Updated last month
• McGill-NLP / AdversarialTriggers
  Code for "Universal Adversarial Triggers Are Not Universal."
  ☆16Updated 6 months ago
• r-three / mats
  ☆25Updated 4 months ago
• dannyallover / overthinking_the_truth
  ☆26Updated 6 months ago
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆62Updated 5 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆58Updated 8 months ago
• aviclu / ffn-values
  ☆58Updated last year
• allenai / noncompliance
  This repository contains data, code and models for contextual noncompliance.
  ☆18Updated 4 months ago
• locuslab / acr-memorization
  ☆26Updated 3 weeks ago
• deeplearning-wisc / args
  ☆33Updated 9 months ago
• mlepori1 / NeuroSurgeon
  NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
  ☆36Updated 3 months ago