9). Small Language Models Survey – a comprehensive survey on small language models (SLMs) across architectures, training datasets, and training algorithms; analyzes 59 state-of-the-art open-source SLMs and capabilities such as reasoning, in-context learning, maths, and coding.
RESEARCH
-
RAG Task Categorization Survey: External Data Classification
By
–
7). RAG and Beyond – presents a survey that introduces a RAG task categorization method that helps to classify user queries into four levels according to the type of external data required and the focus of the task.
-
o1 Preview Model Outperforms GPT-4 in Medical Scenarios
By
–
8). A Preliminary Study of o1 in Medicine – provides a preliminary exploration of the o1-preview model in medical scenarios; shows that o1 surpasses the previous GPT-4 in accuracy by an average of 6.2% and 6.6% across 19 datasets and two newly created complex QA scenarios.
-
Scaled-Up LLMs Show Decreased Reliability in Instruction Following
By
–
5). Scaled-up Instructable Model Become Less Reliable – suggests that larger and more instructable LLMs may become less reliable; investigates LLMs across three elements: difficulty concordance, task avoidance, and prompting stability…
-
Logic-of-Thought: Propositional Logic Prompting Technique
By
–
6). Logic-of-Thought – proposes a new prompting technique called Logic-of-Thought (LoT) which employs propositional logic to generate and inject expanded logical information from the input context.
-
Large Language Models Struggle with Domain-Independent Planning Tasks
By
–
4). LLMs Still Can’t Plan – evaluates whether large reasoning models such as o1 can plan; finds that a domain-independent planner can solve all instances of Mystery Blocksworld but LLMs struggle, even on small instances…
-
AlphaChip: Reinforcement Learning Designs Google TPU Physical Layout
By
–
3). AlphaChip – a reinforcement learning-based method trained to design the physical layout of chips; AlphaChip is reportedly used in three additional generations of Google’s TPU…https://t.co/kM6HcgSTj4
— DAIR.AI (@dair_ai) 29 septembre 20243). AlphaChip – a reinforcement learning-based method trained to design the physical layout of chips; AlphaChip is reportedly used in three additional generations of Google’s TPU…
-
SolarLLM Podcast: Google AI’s Latest Language Model
By
–
PodCast about #SolarLLM by @GoogleAI #NotebookLM.
— Sung Kim (@hunkims) 29 septembre 2024
Also check out https://t.co/soZOfwlhzb. pic.twitter.com/ggO1uO7JKgPodCast about #SolarLLM by @GoogleAI #NotebookLM. Also check out https://
huggingface.co/upstage/solar-
pro-preview-instruct
…. -
Claude vs Gemini: Choosing the Right Language Model
By
–
Claude vs Gemini: A Guide to Choose the Right Model: Introduction Within the quickly changing field of artificial intelligence, two language models, Claude and Gemini,… https://
analyticsvidhya.com/blog/2024/09/c
laude-vs-gemini/?utm_source=dlvr.it&utm_medium=twitter
… #DataAnalytics #DataScience #DataDriven #CIO #BigData #AI #CTO #ArtificialIntelligence -
Model Merging Techniques and Hidden Representation Dynamics
By
–
I'd say it barely works tbh… 🙂 It really depends on the type of merge and whether you retrain it or not. In this case, it's not really "working". The additional layers seem to push the hidden representations into new areas, which may or may not be interesting, depending on