Chain of Thought
ai_technique
Overview
Developed byGoogle Research
Licensenot applicable
Use caseimproving reasoning capabilities in large language models
Knowledge graph stats
Claims23
Avg confidence93%
Avg freshness100%
Last updatedUpdated 3 days ago
Trust distribution
100% unverified
Governance
Not assessed
Chain of Thought
concept
Prompting technique that encourages language models to show reasoning steps, fundamental to agent decision-making.
Compare with...primary use case
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| improving reasoning capabilities in large language models | ○Unverified | High | Fresh | 1 |
| improving reasoning in large language models | ○Unverified | High | Fresh | 1 |
works with
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| large language models | ○Unverified | High | Fresh | 1 |
technique type
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| prompting strategy | ○Unverified | High | Fresh | 1 |
methodology
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| step-by-step reasoning demonstration | ○Unverified | High | Fresh | 1 |
improves performance on
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| arithmetic reasoning tasks | ○Unverified | High | Fresh | 1 |
| Mathematical reasoning tasks | ○Unverified | High | Fresh | 1 |
| commonsense reasoning tasks | ○Unverified | High | Fresh | 1 |
| logical reasoning tasks | ○Unverified | High | Fresh | 1 |
requires
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| large language models | ○Unverified | High | Fresh | 1 |
| few-shot prompting | ○Unverified | Moderate | Fresh | 1 |
developed by
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| Google Research | ○Unverified | High | Fresh | 1 |
introduced year
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| 2022 | ○Unverified | High | Fresh | 1 |
license type
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| not applicable | ○Unverified | High | Fresh | 1 |
| Research publication | ○Unverified | Moderate | Fresh | 1 |
| research paper technique | ○Unverified | Moderate | Fresh | 1 |
supports model
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| GPT-3 | ○Unverified | High | Fresh | 1 |
| PaLM | ○Unverified | High | Fresh | 1 |
alternative to
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| standard prompting | ○Unverified | High | Fresh | 1 |
based on
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| Step-by-step reasoning decomposition | ○Unverified | High | Fresh | 1 |
related technique
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| Few-shot prompting | ○Unverified | Moderate | Fresh | 1 |
| Tree of Thoughts | ○Unverified | Moderate | Fresh | 1 |
related to
| Value | Trust | Confidence | Freshness | Sources |
|---|---|---|---|---|
| few-shot prompting | ○Unverified | Moderate | Fresh | 1 |