7/ Language Modeling is Compression – evaluates the compression capabilities of LLMs; investigates how and why compression and prediction are equivalent; shows that LLMs are powerful general-purpose compressors due to their in-context learning abilities.
@dair_ai
-
LMSYS-Chat-1M: 1M Conversations Dataset with 25 LLMs
By
–
6/ LMSYS-Chat-1M – a large-scale dataset containing 1 million real-world conversations with 25 state-of-the-art LLM; it is collected from 210K unique IP addresses on the Vincuna demo and Chatbot Arena website.
-
LLMs for Structured Data Generation: Fine-tuning Approach
By
–
5/ LLMs for Generating Structured Data – studies the use of LLMs for generating complex structured data; proposes a structure-aware fine-tuning method, applied to Llama-7B, which significantly outperform other model like GPT-3.5/4 and Vicuna-13B.
-
Contrastive Decoding Improves LLM Reasoning Performance
By
–
3/ Contrastive Decoding Improves Reasoning in Large Language Models – shows that contrastive decoding leads Llama-65B to outperform Llama 2 and other models on commonsense reasoning and reasoning benchmarks.
-
AlphaMissense: AI Model Classifies Genetic Disease Variants
By
–
1/ AlphaMissense – an AI model classifying missense variants to help pinpoint the cause of diseases; used to develop a catalogue of genetic mutations; it can categorize 89% of all 71 mil missense variants as either likely pathogenic or likely benign.https://t.co/TIYUbN4hYu
— DAIR.AI (@dair_ai) 24 septembre 20231/ AlphaMissense – an AI model classifying missense variants to help pinpoint the cause of diseases; used to develop a catalogue of genetic mutations; it can categorize 89% of all 71 mil missense variants as either likely pathogenic or likely benign.
-
Top Machine Learning Papers of the Week: LongLoRA, AlphaMissense
By
–
Top ML Papers of the Week (Sep 18 – Sep 24): – LongLoRA
– AlphaMissense
– Chain-of-Verification
– LLMs for IT Operations
– Language Modeling is Compression
– LLMs for Generating Structured Data
… -
Chain-of-Verification Reduces LLM Hallucinations Through Deliberation
By
–
2/ Chain-of-Verification reduces Hallucination in LLMs – a method to enable LLMs to "deliberate" on responses to correct mistakes.
-
MAmmoTH: Open-Source LLMs for Mathematical Problem-Solving
By
–
10/ MAmmoTH – a series of open-source LLMs tailored for general math problem-solving; the models are trained on a curated instruction tuning dataset and outperform existing open-source models on several mathematical reasoning datasets.
-
Radiology-Llama2: Specialized LLM for Medical Imaging
By
–
8/ Radiology-Llama2: Best-in-Class LLM for Radiology – presents an LLM based on Llama 2 tailored for radiology; it's tuned on a large dataset of radiology reports to generate coherent and clinically useful impressions from radiology findings.
-
ChatDev: AI-Powered Software Development in Under Seven Minutes
By
–
9/ ChatDev – a virtual chat-powered software development company mirroring the waterfall model; shows efficacy in software generation, even completing the entire software development process in less than seven minutes for less than one dollar.