SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.20033 · NeurIPS · 2023

Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization

Zonghai Yao, Hong Yu, Prakamya Mishra, Shuwei Chen, Beining Wang, Rohan Mittal

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 4 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2310.20033.json · badge: /api/ran/2310.20033.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
seasonyao/LearnFromHumanEdit canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
seasonyao/learnfromhumanedit alias (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Gap Ran
ran on a synthesized input · constructed an object; no result was computed
seasonyao/learnfromhumanedit/sequence_alignment/core.py
pointer only (licence: NONE) · get_code("086a54465906eda1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/learnfromhumanedit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

OptimalAlignment Ran
ran on a synthesized input · constructed an object; no result was computed
seasonyao/learnfromhumanedit/sequence_alignment/core.py
pointer only (licence: NONE) · get_code("0195e9f1723de5b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/learnfromhumanedit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ScoreMatrix Ran
ran on a synthesized input · constructed an object; no result was computed
seasonyao/learnfromhumanedit/sequence_alignment/core.py
pointer only (licence: NONE) · get_code("a2898c7c195ce1aa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/learnfromhumanedit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_prompt Ran
ran; our contract draft was wrong, not the code
seasonyao/LearnFromHumanEdit/trainer.py
pointer only (licence: NONE) · get_code("bcfd3a2ac6316b60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/LearnFromHumanEdit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_position_status Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
seasonyao/LearnFromHumanEdit/sequence_alignment/needle.py
pointer only (licence: NONE) · get_code("e2c3f46dc6315f45")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/LearnFromHumanEdit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_triples Ran
ran; our contract draft was wrong, not the code
seasonyao/LearnFromHumanEdit/metrics.py
pointer only (licence: NONE) · get_code("ae0cdcbf80c23151")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/LearnFromHumanEdit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

process_triples Ran
ran; our contract draft was wrong, not the code
seasonyao/LearnFromHumanEdit/metrics.py
pointer only (licence: NONE) · get_code("814172c8e37b1334")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/LearnFromHumanEdit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_dataset Not yet run
unverified (harvested, no recorded run)
seasonyao/LearnFromHumanEdit/trainer.py
pointer only (licence: NONE) · get_code("26bb4f14cecaa8bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/LearnFromHumanEdit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

remove_stopword_and_punc_in_list Not yet run
unverified (harvested, no recorded run)
seasonyao/LearnFromHumanEdit/metrics.py
pointer only (licence: NONE) · get_code("a82a905574e3548e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, seasonyao/LearnFromHumanEdit when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 8 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 6 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
remove_stopword_and_punc_in_list 2 other papers
1 dated earlier, 1 the same month
2305.03495 (2023-05)
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
2310.05857 (2023-10)
Improving Summarization with Human Edits
Gap
brick of this paper's assembly: helper
1 other paper
1 the same month · 1 only as an assembly brick
2310.05857 (2023-10)
Improving Summarization with Human Edits
OptimalAlignment
brick of this paper's assembly: entry
1 other paper
1 the same month · 1 only as an assembly brick
2310.05857 (2023-10)
Improving Summarization with Human Edits
ScoreMatrix
brick of this paper's assembly: helper
1 other paper
1 the same month · 1 only as an assembly brick
2310.05857 (2023-10)
Improving Summarization with Human Edits
extract_prompt 1 other paper
1 the same month
2310.05857 (2023-10)
Improving Summarization with Human Edits
get_position_status 1 other paper
1 the same month
2310.05857 (2023-10)
Improving Summarization with Human Edits
make_triples 1 other paper
1 dated earlier
2305.03495 (2023-05)
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
process_triples 1 other paper
1 dated earlier
2305.03495 (2023-05)
Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Models (LLMs) like the GPT and LLaMA families have demonstrated exceptional capabilities in capturing and condensing critical contextual information and achieving state-of-the-art performance in the summarization task. However, community concerns about these models' hallucination issues continue to rise. LLMs sometimes generate factually hallucinated summaries, which can be extremely harmful in the clinical domain NLP tasks (e.g., clinical note summarization), where factually incorrect statements can lead to critically erroneous diagnoses. Fine-tuning LLMs using human feedback has shown the promise of aligning LLMs to be factually consistent during generation, but such training procedure requires high-quality human-annotated data, which can be extremely expensive to get in the clinical domain. In this work, we propose a new pipeline using ChatGPT 2 instead of human experts to generate high-quality feedback data for improving factual consistency in the clinical note summarization task. We focus specifically on edit feedback because recent work discusses the shortcomings of human alignment via preference feedback in complex situations (such as clinical NLP tasks that require extensive expert knowledge), as well as some advantages of collecting edit feedback from domain experts. In addition, although GPT has reached the expert level in many clinical NLP tasks (e.g., USMLE QA), there is not much previous work discussing whether GPT can generate expert-level edit feedback for LMs in the clinical note summarization task. We hope to fill this gap. Finally, our evaluations demonstrate the potential use of GPT edits in human alignment, especially from a factuality perspective. 3 * indicates equal contribution 2 We used ChatGPT using Azure OpenAI Service: https://azure.microsoft.com/en-us/products/aiservices/openai-service/ 3 Our code and dataset will be released at https://github.com/seasonyao/LearnFromHumanEdit To appear in NeurIPS 2023 Workshop SyntheticData4ML Preprint. Under review.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.20033")
get_code_for_paper("2310.20033")
have("2310.20033")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2310.20033.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2310.20033.svg)](https://syntology.ai/paper/2310.20033)

Connect an agent — have() is free.