Added SDM and sample of related precursor papers #45
+15
−0
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Outdated suggestions cannot be applied.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.
These may be of interest to the audience. I added the instance-based, metric (representation) learning, interpretability, and uncertainty quantification papers, which for the reasons noted in the comments, are directly applicable to the hallucination detection task (in its various forms). The recommended approach moving forward is the SDM-based approaches in the most recent paper, "Similarity-Distance-Magnitude Universal Verification", but I think folks may be interested in the related background of the preceding two papers, which are relatively old compared to other papers in this repo. (I have other related papers, as well, but these cover the crux of the approaches.)
I didn't see an obvious ordering in the list, so I just added these directly under the header assuming you will re-arrange. (Also, obviously, feel free to not include any or all of these suggestions.)