Context Relevancy v2 #59
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jjmachan
reviewed
Jul 13, 2023
Comment on lines
+101
to
+104
| questions, contexts = dataset["question"], dataset["contexts"] | ||
| for q, c in zip(questions, contexts): | ||
| prompt = CONTEXT_RELEVANCE.format(q, "\n".join(c)) | ||
| prompts.append(prompt) |
There was a problem hiding this comment.
wouldn't this need batching. If there are more than 20 (questions, contexts) pairs openAI will return an error?
|
|
||
| return score_ds | ||
| return dataset.add_column(f"{self.name}", scores) # type: ignore |
There was a problem hiding this comment.
why are we type ignoring here? just curious
There was a problem hiding this comment.
A warning for not passing the dataset fingerprint argument, The same is done in the Faithfulness class.
| model_name: str = "t5-base" | ||
| batch_size: int = 15 | ||
| agreement_metric: str = "bert_score" | ||
| strictness: int = 2 |
There was a problem hiding this comment.
what does the strictness param do? would be great to have doc string at this point I guess
|
@jjmachan Added the required changes. |
jjmachan
approved these changes
Jul 14, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What
Added support for new context relevancy metrics
Why
The earlier used context_relevancy metric was found to have a poor correlation with actual results.
How
New paradigm leverages candidate sentence extraction with self-consistency checks to ensure far better results even with larger context lengths.
Screenshots