zai-org/GLM-4.6
Text Generation
ā¢
357B
ā¢
Updated
ā¢
141k
ā¢
ā¢
1.19k
Offer L.
OfferL
AI & ML interests
None yet
Recent Activity
liked
a model
about 1 month ago
zai-org/GLM-4.6
liked
a model
about 2 months ago
meta-llama/Llama-4-Scout-17B-16E-Instruct
liked
a Space
3 months ago
AgentFlow/agentflow
Organizations
liked
a
model
about 1 month ago
liked
a
model
about 2 months ago
liked
a
Space
3 months ago
liked
a
Space
4 months ago
liked
a
Space
5 months ago
reacted to
chansung's
post with š
11 months ago
Post
2062
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:
š¤ An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
š¤ 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
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:
š¤ An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
š¤ 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
liked
a
model
about 1 year ago
liked
a
Space
about 1 year ago
liked
a
model
about 1 year ago
liked
a
model
over 1 year ago
liked
5
Spaces
over 1 year ago
Llama3.1 S V0.2 Checkpoint 2024 08 20
š»
115
Convert text to audio and vice versa
Kolors Virtual Try-On
š
9.94k
Try on clothes on a person image
Falcon Mamba Playground
š
65
Generate chat responses using FalconMamba-7b model
Paligemma HF
š¤
83
Generate text and segment images using PaliGemma
FLUX.1 [dev]
š„
9.35k
Generate images from text descriptions
liked
a
model
over 1 year ago
liked
3
Spaces
over 1 year ago
liked
a
model
over 1 year ago
