elvis
@eos.bsky.social
Building with AI agents • Prev: Meta AI, Elastic, Galactica LLM, PhD • Prompting Guide (~6M+ learners) • I also teach how to build with AI: https://dair-ai.thinkific.com/
Paper: arxiv.org/abs/2501.13824
Hallucinations Can Improve Large Language Models in Drug Discovery
Concerns about hallucinations in Large Language Models (LLMs) have been raised by researchers, yet their potential in areas where creativity is vital, such as drug discovery, merits exploration....
arxiv.org
January 24, 2025 at 1:56 PM
Paper: arxiv.org/abs/2501.13824
In addition, hallucinations generated by GPT-4o provide the most consistent improvements across models.
January 24, 2025 at 1:56 PM
In addition, hallucinations generated by GPT-4o provide the most consistent improvements across models.
A new paper claims that LLMs can achieve better performance in drug discovery tasks with text hallucinations compared to input prompts without hallucination.
Llama-3.1-8B achieves an 18.35% gain in ROC-AUC compared to the baseline without hallucination.
Llama-3.1-8B achieves an 18.35% gain in ROC-AUC compared to the baseline without hallucination.
January 24, 2025 at 1:56 PM
A new paper claims that LLMs can achieve better performance in drug discovery tasks with text hallucinations compared to input prompts without hallucination.
Llama-3.1-8B achieves an 18.35% gain in ROC-AUC compared to the baseline without hallucination.
Llama-3.1-8B achieves an 18.35% gain in ROC-AUC compared to the baseline without hallucination.
paper: arxiv.org/abs/2412.20512
Dive into Time-Series Anomaly Detection: A Decade Review
Recent advances in data collection technology, accompanied by the ever-rising volume and velocity of streaming data, underscore the vital need for time series analytics. In this regard,...
arxiv.org
January 6, 2025 at 2:18 PM
paper: arxiv.org/abs/2412.20512
- metrics to assess the efficiency of o1-like models
- several strategies to tackle overthinking and reduce token generation
Very informative paper.
- several strategies to tackle overthinking and reduce token generation
Very informative paper.
January 2, 2025 at 4:03 PM
- metrics to assess the efficiency of o1-like models
- several strategies to tackle overthinking and reduce token generation
Very informative paper.
- several strategies to tackle overthinking and reduce token generation
Very informative paper.
• 🌍 Flexible Environment Configuration: Define custom environments with YAML configuration files
• 🛠️ Extensible Architecture: Easy to extend and customize for your specific needs
• 🛠️ Extensible Architecture: Easy to extend and customize for your specific needs
December 31, 2024 at 3:22 PM
• 🌍 Flexible Environment Configuration: Define custom environments with YAML configuration files
• 🛠️ Extensible Architecture: Easy to extend and customize for your specific needs
• 🛠️ Extensible Architecture: Easy to extend and customize for your specific needs
• 🔄 Robust Interaction Management: Coordinate complex interactions between agents
• 💾 Checkpoint System: Save and restore agent states and interactions
• 📊 Data Generation: Generate synthetic data through agent interactions
• ⚡ Performance Optimized: Built for efficiency and scalability
• 💾 Checkpoint System: Save and restore agent states and interactions
• 📊 Data Generation: Generate synthetic data through agent interactions
• ⚡ Performance Optimized: Built for efficiency and scalability
December 31, 2024 at 3:22 PM
• 🔄 Robust Interaction Management: Coordinate complex interactions between agents
• 💾 Checkpoint System: Save and restore agent states and interactions
• 📊 Data Generation: Generate synthetic data through agent interactions
• ⚡ Performance Optimized: Built for efficiency and scalability
• 💾 Checkpoint System: Save and restore agent states and interactions
• 📊 Data Generation: Generate synthetic data through agent interactions
• ⚡ Performance Optimized: Built for efficiency and scalability
more here --> mixedbit.org/blog/2024/1...
December 17, 2024 at 2:24 PM
more here --> mixedbit.org/blog/2024/1...
more here: andrewkchan.dev/posts/yalm....
December 16, 2024 at 3:10 PM
more here: andrewkchan.dev/posts/yalm....
December 13, 2024 at 3:20 PM
The authors claim that "With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space."
arxiv.org/abs/2412.07724
arxiv.org/abs/2412.07724
Granite Guardian
We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large...
arxiv.org
December 11, 2024 at 2:28 PM
The authors claim that "With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space."
arxiv.org/abs/2412.07724
arxiv.org/abs/2412.07724