You can give the LLM this information and have it tell you which is right. Here's a demo.
=== input to ChatGPT 4o ===
I'm trying to read some text but one of the characters is unclear. I will use the notation [xy] to indicate that I think the character is either x or y. Please tell me which one you think is correct. Here is the text: "There was a lot of traffic on [I1]-80 this morning." In your response, please include a line like "correct character: x" so I can see the conclusion at a glance.
=== ChatGPT's response ===
The correct character in the text is likely "I".
Interstate highways in the United States are often denoted by "I-" followed by the highway number. "I-80" is a major interstate highway that runs across the United States, so it makes more sense in this context than "1-80," which would imply a different and less common road designation.
Ah, interesting. I guess you could probably get bounding boxes etc.,. too, so you could pass the image as well to a multimodal model (although maybe it'll just run tesseract behind the scenes lol)
You can give the LLM this information and have it tell you which is right. Here's a demo.
=== input to ChatGPT 4o ===
I'm trying to read some text but one of the characters is unclear. I will use the notation [xy] to indicate that I think the character is either x or y. Please tell me which one you think is correct. Here is the text: "There was a lot of traffic on [I1]-80 this morning." In your response, please include a line like "correct character: x" so I can see the conclusion at a glance.
=== ChatGPT's response ===
The correct character in the text is likely "I".
Interstate highways in the United States are often denoted by "I-" followed by the highway number. "I-80" is a major interstate highway that runs across the United States, so it makes more sense in this context than "1-80," which would imply a different and less common road designation.
correct character: I