KimRina's picture

15 22

KimRina

KimRina

·

KimRina-ai

AI & ML interests

Multimodal (CV & LLM)

Recent Activity

liked a dataset 4 days ago

yale-nlp/MMVU

liked a dataset 4 days ago

huggingface/policy-docs

reacted to chansung's post with 👍 4 days ago

Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind) The process starts by posing a question. 1) The LLM generates initial responses. 2) These generated responses are evaluated according to specific criteria (program-based checker). 3) The LLM critiques the evaluated results. 4) The LLM refines the responses based on the evaluation, critique, and original responses. The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged). Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios. However, there are two major drawbacks: 🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.) 🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.) https://arxiv.org/abs/2501.09891

View all activity

Organizations

Collections 1

models 3

KimRina/Ko-BioMistral-7B-ties

Text Generation • Updated May 30, 2024 • 12

KimRina/Ko-BioMistral-7B-dare

Text Generation • Updated May 30, 2024 • 11

KimRina/Ko-BioMistral-7B-slerp

Text Generation • Updated May 30, 2024 • 13

datasets

None public yet