6/ ChatGPT for Text-Annotation – shows that ChatGPT outperforms crowd-workers on several annotation tasks such as relevance, topics, and frames detection; besides better 0-shot accuracy, the per-annotation cost of ChatGPT is ~20 times cheaper than MTurk.
@dair_ai
-
LLM Agents Execute Computer Tasks Through Recursive Self-Improvement
By
–
7/ LLMs for Computer Tasks – shows that a pre-trained LLM agent can execute computer tasks using a simple prompting scheme where the agent recursively criticizes and improves its outputs.
-
ChatDoctor: Medical LLM Fine-tuned on LLaMA for Healthcare
By
–
4/ ChatDoctor – a medical chat model fine-tuned on LLaMA using medical domain knowledge. Collects data on around 700 diseases and generated 5K doctor-patient conversations to finetune the LLM.
-
LLaMA-Adapter: Lightweight Method Fine-Tune Instruction-Following Models
By
–
5/ LLaMA-Adapter – a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model; generates responses comparable to Alpaca with fully fine-tuned 7B parameter; it’s also extended for multi-modal input support.
-
Prompt Engineering Guide: Stay Updated with Latest Techniques
By
–
Prompt Engineering Guide ICYMI, we recently launched the prompt engineering guide that makes it easier to stay up-to-date with prompt engineering techniques and papers. https://
promptingguide.ai -
NeRFMeshing enables compact 3D surface reconstruction from NeRF
By
–
9/ NeRFMeshing – a compact and flexible architecture that enables easy 3D surface reconstruction from any NeRF-driven approach; distills NeRFs into geometrically-accurate 3D meshes.
-
FlexGen: High-Throughput LLM Engine for Limited GPU Memory
By
–
10/ FlexGen – a high-throughput generation engine for running LLMs with limited GPU memory.
-
Universal Prompt Retrieval Improves Zero-Shot AI Performance
By
–
7/ Universal Prompt Retrieval – a new approach to tune a lightweight and versatile retriever to automatically retrieve prompts to improve zero-shot performance and help mitigate hallucinations.
-
ConvMixer: Parameter-Efficient Alternative to Vision Transformers
By
–
8/ Patches Are All You Need – proposes ConvMixer, a parameter-efficient fully-convolutional model which replaces self-attention and MLP layers in ViTs with less-expressive depthwise and pointwise convolutional layers.
-
Deep RNNs Recovery for Long-Range Reasoning Tasks
By
–
6/ Resurrecting RNNs – demonstrates that careful design of deep RNNs using standard signal propagation arguments can recover the performance of deep state-space models on long-range reasoning tasks.