Generative AI Weekly Research Highlights | Sep'23 Part 3

Disclaimer: The content in this video is AI-generated and adheres to YouTube's guidelines. Each video undergoes manual review and curation before publishing to ensure accuracy and quality.

When Large Language Models Meet Citation: A Survey (https://arxiv.org/pdf/2309.09727.pdf)

PolicyGPT: Automated Analysis of Privacy Policies with Large Language Models (https://arxiv.org/pdf/2309.10238.pdf)

JobRecoGPT: Explainable job recommendations using LLMs (https://arxiv.org/pdf/2309.11805.pdf)

STRUC-BENCH: Are Large Language Models Really Good at Generating Complex Structured Data? (https://arxiv.org/pdf/2309.08963.pdf)

Language Modeling Is Compression (https://arxiv.org/pdf/2309.10668.pdf)

LONGLORA: EFFICIENT FINE-TUNING OF LONGCONTEXT LARGE LANGUAGE MODELS (https://arxiv.org/pdf/2309.12307.pdf)

CHAIN-OF-VERIFICATION REDUCES HALLUCINATION IN LARGE LANGUAGE MODELS (https://arxiv.org/pdf/2309.11495.pdf)

Retrieving Supporting Evidence for Generative Question Answering (https://arxiv.org/pdf/2309.11392.pdf)

00:00 Intro

00:17 LLMs with Citation Analysis

00:40 Policy GPT for Privacy Policies

00:59 Job Recommendation with LLMs

01:21 StrucBench for Structured Data

01:42 Prediction through Compression

02:00 LongLora: Extending Context Sizes

02:18 Chain of Verification for LLMs

02:35 Retrieving Supporting Evidence for QA

03:02 End

#generativeai,#promptengineering,#largelanguagemodels,#openai,#chatgpt,#gpt4,#ai,#abcp,