research papers

February 9, 2024 · 1 min read · tech, machine-learning

• aiaac, AI incidents database.

• Scalable Extraction of Traning Data from (Production) Language Models

  • Making LLMs repeat the same word over and over again makes them emit the training data 3.5X better

• The pain of Building copilots

  • Microsoft researchers document the pain of building an LLM based copilot for users and how developers find multiple things counter-intuitive

• Microsoft LASER

  • Microsoft uses LASER to intervene with a model and improve it’s reasoning ability. sort of like a Laser eye research

• Can Knowledge Graphs reduce Hallucinations?

  • Creating a knowledge graph to ground the reasoning of the LLM helps in fixing the hallucination problem

• Reasoning on Graphs

  • Using a Graph to generate reasoning paths and utilize it to answer questions.

• Should LLMs replace mTurk

  • Models are with a lot of biases built in them

• Artificial Artifical intelligence: Crowd workers…

• Chronicling America