Cobus GreylingFlowMind Is An Automatic Workflow GeneratorThe FlowMind research was conducted by JPMorganChase to use LLMs to overcome the rigidity of RPA. FlowMind leverages a prompt template to…17h ago17h ago
Cobus GreylingCan Conversation Designers Excel As Data Designers?The Emergence Of Data Design to create highly granular, conversational & refined data for language model fine-tuning.1d ago1d ago
Cobus GreylingPhi-3 Is A Small Language Model Which Can Run On Your PhonePhi-3 is a family of small language models with short & long context lengths.Jun 19Jun 19
Cobus GreylingLangGraph From LangChain Explained In Simple TermsLangGraph is a method for creating state machines for conversational flow by defining them as graphs & it’s easier to understand than you…Jun 172Jun 172
Cobus GreylingDR-RAG: Applying Dynamic Document Relevance To Question-Answering RAGDR-RAG is a two-stage retrieval process which is focussed on calling the LLM only once by performing a multi-hop process on QA datasets…Jun 14Jun 14
Cobus GreylingCreating A Benchmark Taxonomy For Prompt EngineeringBenchmarking prompts presents challenges due to differences in their usage, level of detail, style, and purpose. A recent study tackled…Jun 13Jun 13
Cobus GreylingLanguage Agent Tree Search — LATSThe LATS framework is a first of its kind general framework that synergises the capabilities of LMs in reasoning, acting, and planning. It…Jun 122Jun 122
Cobus GreylingTree Of Thoughts Prompting (ToT)Prompting techniques are continuously evolving & this evolution demands supporting structures to put more complex prompts to work. This…Jun 111Jun 111
Cobus GreylingUsing Fine-Tuning To Imbed Hidden Messages In Language ModelsThis text is revealed only when triggered by a specific query to the Language Model.Jun 102Jun 102
Cobus GreylingImplementing Chain-of-Thought Principles in Fine-Tuning Data for RAG SystemsKnowledge-oriented question answering is now a crucial aspect of enterprise knowledge management, aiming to provide accurate responses to…Jun 7Jun 7