9). Can LLMs Design Good Questions? – systematically evaluates the quality of questions generated with LLMs; here are the main findings: 1) there is a strong preference for asking about specific facts and figures in both LLaMA and GPT models…
LLMS
-
Meta Chain-of-Thought Extends AI System 2 Reasoning Capabilities
By
–
5). Towards System 2 Reasoning – proposes Meta Chain-of-Thought (Meta-CoT), which extends traditional Chain-of-Thought (CoT) by modeling the underlying reasoning required to arrive at a particular CoT.
-
rStar-Math: Code-Augmented CoT for Enhanced Math Reasoning
By
–
6). rStar-Math – a new approach proposes three core components to enhance math reasoning: 1) a code-augmented CoT data synthesis method involving MCTS to generate step-by-step verified reasoning trajectories which are used to train the policy SLM…
-
Agent Laboratory: LLM Agents Advancing Research Process
By
–
2). Agent Laboratory – an approach that leverages LLM agents capable of completing the entire research process; the main findings are: 1) agents driven by o1-preview resulted in the best research outcomes…
-
Long Context LLMs Outperform RAG in Question-Answering
By
–
3). Long Context vs. RAG for LLMs – performs a comprehensive evaluation of long context (LC) LLMs compared to RAG systems; the three main findings are: 1) LC generally outperforms RAG in question-answering benchmarks…
-
Search-o1 Framework Combines Reasoning Models with Agentic Search
By
–
4). Search-o1 – a framework that combines large reasoning models (LRMs) with agentic search and document refinement capabilities to tackle knowledge insufficiency…
-
o1 Model Requires Different Approach Than Standard Chat Models
By
–
o1 is a different kind of model. great performance requires using it in a new way relative to standard chat models.
-
GPT-3 training: SFT vs RLHF and EOT penalty issue
By
–
It "isn't pretty" but still works with effort. GPT-3 was just SFT for a long time — even text-davinci-002 wasn't actually RLHF, just SFT/FeedME, and looping text like this was rare at that point Issue here IMO is lack of EOT training; w/o that you need freq penalty etc
-
APIs: Connecting ML Models and Data in Production
By
–
When we talk about building powerful machine learning solutions, like large language models or retrieval-augmented generation, one key element that often flies under the radar is how to connect all the data and models and deploy them in a real product. This is where APIs come in.
-
Developing LLM Partnership for Zero Shot Code Generation
By
–
https://t.co/oyORhKI2ns pic.twitter.com/mL5cNcQ1VG
— Varun Mayya (@waitin4agi_) 12 janvier 2025People use LLMs as if they are on one night stand I use LLMs as if it is my partner This is why me and Claude have grown together to develop a better understanding on how to 0 shot the requirements and the corresponding code