ahans30 / BinocularsLinks
[ICML 2024] Binoculars: Zero-Shot Detection of LLM-Generated Text
☆306Updated last year
Alternatives and similar repositories for Binoculars
Users that are interested in Binoculars are comparing it to the libraries listed below
Sorting:
- Ghostbuster: Detecting Text Ghostwritten by Large Language Models (NAACL 2024)☆162Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆233Updated 11 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆269Updated 3 months ago
- Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]☆343Updated 7 months ago
- Can AI-Generated Text be Reliably Detected?☆83Updated last year
- utilities for decoding deep representations (like sentence embeddings) back to text☆939Updated last month
- Code accompanying "How I learned to start worrying about prompt formatting".☆111Updated 3 months ago
- RAID is the largest and most challenging benchmark for AI-generated text detection. (ACL 2024)☆83Updated 2 weeks ago
- Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!☆317Updated 11 months ago
- ☆140Updated 3 years ago
- Attribute (or cite) statements generated by LLMs back to in-context information.☆282Updated 11 months ago
- Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense…☆174Updated last year
- A survey and reflection on the latest research breakthroughs in LLM-generated Text detection, including data, detectors, metrics, current…☆76Updated 10 months ago
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆186Updated 7 months ago
- Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]☆74Updated 7 months ago
- ☆623Updated this week
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆138Updated 3 months ago
- Code for the paper "Fishing for Magikarp"☆165Updated 4 months ago
- Python package for measuring memorization in LLMs.☆166Updated 2 months ago
- ☆46Updated 6 months ago
- Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vecto…☆247Updated 7 months ago
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆91Updated 9 months ago
- Evaluating LLMs with fewer examples☆161Updated last year
- ☆248Updated 5 months ago
- We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…☆321Updated last year
- A Comprehensive Assessment of Trustworthiness in GPT Models☆302Updated last year
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆230Updated last month
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆111Updated 6 months ago
- ☆183Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago