The Ranking and 1-Best Selection process is a decoding method that involves three main stages. First, in the Expansion stage, a set of potential next tokens is generated. Second, in the Ranking stage, these candidates are sorted based on their probabilities from highest to lowest. Finally, in the Output stage, the single token with the highest probability (the '1-best') is selected, and all other lower-probability tokens are discarded or 'pruned'.

Ranking and 1-Best Selection Process

Ranking and K-Best Selection Process

Top-k sampling is a text generation strategy that balances creativity and coherence. The process involves several stages: first, an 'Expansion' stage generates all possible next tokens; second, a 'Ranking' stage filters this list to only the top 'k' most probable tokens; third, a 'Selection and Sampling' stage renormalizes the probabilities of these k tokens and samples one; and finally, an 'Output' stage finalizes the sampled token as the next word in the sequence.

Top-K Sampling Process

Top-p, or nucleus, sampling is a probabilistic text generation technique that involves a multi-stage process. First, in the expansion stage, all potential next tokens are generated. Second, these tokens are ranked by probability. Third, a 'nucleus' of the top-ranked tokens is selected, such that their cumulative probability exceeds a predefined threshold 'p'. The probabilities within this nucleus are then renormalized. Finally, a single token is sampled from this renormalized set to become the output. This method balances quality and diversity by filtering out the long tail of low-probability tokens.

Top-p (Nucleus) Sampling Process

The flowchart helps work out different scenarios or use cases that the design of a system or service must take into account, especially when the process can go one way or another at an important decision points.

University of Michigan - Ann Arbor

Here are six ways to make frameworks (to conduct reframing)
- Taxonomies 
- Maps 
- Timelines 
- Flowcharts 
- Spectrums 
- Two-by-two matrixes

6 ways to make frameworks

Goodman, E., Kuniavsky, M., & Moed, A. Observing the User Experience, 2nd Edition.

References: Analyzing Qualitative Data

A taxonomy is a hierarchical organization that essentially brings together all your 
existing categories and subcategories and is especially useful in translating your analysis into frameworks useful for interface and information design (like the data from card sorting).

1) Taxonomies

Placing data into spatial representations serves a variety 
of purposes, espeically useful for designing mobile- or location-based services.

2) Maps

Many research outcomes, such as a diary study, have a basis of sequences of activities over a period of time, which can be tracked and presented by timelines. Timelines are especially crucial if the interest is in cyclical activities and can often present life patterns that would be difficult to observe. 

3) Timelines

4) Flowcharts

The spectrum allows you to identify an important way in which people differ in attitudes, behaviors, or values. For example, the spectrum is laid out horizontally, and
each participant is given a specific point on the line.


5) Spectrums

A two-by-two matrix uses two spectrums as the axes for a grid, then research elements (people, objects, activities, products, etc.) distribute around the four quadrants, which helps make comparisons between different categories or start thinking about cause-and-effect relationships.  

Learn Before

Related

Learn After