Update section 4#1
Merged
blengerich merged 8 commits intoAdaptInfer:mainfrom May 4, 2026
Merged
Conversation
LZYEIL
commented
Mar 5, 2026
LZYEIL
commented
- Update the section 4 with motivation and introduction
- Merge to check if the rendered PDF/HTML displays contents and references as expected
Author
|
I've read several venues' (NMI Review/ACM Computing Survey) requirements: 4k words/35 pages of length with ~100 references. Current Draft
What is Next
Questions
|
hjung-stat
reviewed
Apr 19, 2026
Comment on lines
+152
to
+153
|
|
||
| A core assumption of RAG is that the retrieved documents are inherently helpful. However, biomedical literature and clinical records are fraught with conflicting studies. When general-purpose LLMs are fed contradictory context—often termed "retrieval noise"—their reasoning ability can be seriously compromised. Retrieval noise actively disrupts the LLM's causal reasoning and leads to confusion. Recent work has proposed a 'self-reflection' mechanism, where the model evaluates the relevance of retrieved documents before generation [@doi:10.1093/bioinformatics/btae238]. However, such approaches remain preliminary. |
Contributor
There was a problem hiding this comment.
It might be helpful to extend this beyond 'retrieval noise' to highlight a more structural issue: RAG systems typically do not distinguish between different levels of medical evidence (e.g., RCTs vs. case reports). This lack of an 'evidence hierarchy' could be a fundamental reason why conflicting information disrupts the model's reasoning, as it cannot prioritize more rigorous studies over anecdotal ones.
Author
There was a problem hiding this comment.
I've revised the structure of the section, making it more compact from a perspective-style-driven perspective, and I've briefly added this idea.
github-actions Bot
pushed a commit
that referenced
this pull request
May 4, 2026
[ci skip] This build is based on dac3b9e. This commit was created by the following CI build and job: https://github.com/AdaptInfer/fm-survey/commit/dac3b9e6f625cc79d94cbe4b9af0d1f498546e1f/checks https://github.com/AdaptInfer/fm-survey/actions/runs/25328725956
github-actions Bot
pushed a commit
that referenced
this pull request
May 4, 2026
[ci skip] This build is based on dac3b9e. This commit was created by the following CI build and job: https://github.com/AdaptInfer/fm-survey/commit/dac3b9e6f625cc79d94cbe4b9af0d1f498546e1f/checks https://github.com/AdaptInfer/fm-survey/actions/runs/25328725956
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.