SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.01304 · 2024

Improving the Validity of Automatically Generated Feedback via Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

9 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 4 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/2403.01304.json · badge: /api/ran/2403.01304.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
umass-ml4ed/feedback-gen-dpo canonical (classifier label)
classifier basis: census
9 ran · 4 no recorded run
FunctionStatusWhere it lives
clean_whitespace Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/feedback_dataset.py
pointer only (licence: NONE) · get_code("7e37d709fb1141d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

expand_rows Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/feedback_dataset.py
pointer only (licence: NONE) · get_code("142b6a27e89b148d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

feedback_prompt_input Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/create_reward_dataset.py
pointer only (licence: NONE) · get_code("32fe9ec6a920dbd2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

feedback_prompt_input_sol Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/create_reward_dataset.py
pointer only (licence: NONE) · get_code("ae7826c477041916")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

feedback_prompt_output Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/create_reward_dataset.py
pointer only (licence: NONE) · get_code("962fe5e7b6a783dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

format_input Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/reward_model_dataset.py
pointer only (licence: NONE) · get_code("fca5d04c2f6ba6c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

format_input_enc Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/reward_model_dataset.py
pointer only (licence: NONE) · get_code("31e2f3ed91401af8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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_saved_cache Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/llm.py
pointer only (licence: NONE) · get_code("8bffebe98b61c348")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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_data Ran
ran; our contract draft was wrong, not the code
umass-ml4ed/feedback-gen-dpo/train_reticl.py
pointer only (licence: NONE) · get_code("107bcb2dd90aff86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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_stats Not yet run
unverified (harvested, no recorded run)
umass-ml4ed/feedback-gen-dpo/analyze_reward_dataset.py
pointer only (licence: NONE) · get_code("1c2a77c38afe9780")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

get_tokenizer Not yet run
unverified (harvested, no recorded run)
umass-ml4ed/feedback-gen-dpo/reward_model.py
pointer only (licence: NONE) · get_code("94152c91edb8e94e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

load_dataset Not yet run
unverified (harvested, no recorded run)
umass-ml4ed/feedback-gen-dpo/reward_model_dataset.py
pointer only (licence: NONE) · get_code("59c7d2e02b3c4856")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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.

load_dataset Not yet run
unverified (harvested, no recorded run)
umass-ml4ed/feedback-gen-dpo/count_tokens.py
pointer only (licence: NONE) · get_code("ca23aa0b59dd9b4d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, umass-ml4ed/feedback-gen-dpo 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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.

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

Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and evaluation are challenging: feedback content has to be valid especially in subjects like math, which requires models to understand the problem, the solution, and where the student's error lies. Feedback also has to be pedagogically valid to reflect effective tutoring strategies, such as explaining possible misconceptions and encouraging the student, among other desirable features. In this work, we address both problems of automatically generating and evaluating feedback while considering both correctness and alignment. First, we propose a rubric for evaluating math feedback and show that GPT-4 is able to effectively use it to annotate human-written and LLM-generated feedback. Second, we propose a framework for feedback generation that optimizes both correctness and alignment using reinforcement learning (RL). Specifically, we use GPT-4's annotations to create preferences over feedback pairs in an augmented dataset for training via direct preference optimization (DPO). We show that our methods significantly increase the correctness and alignment of generated feedback with Llama 2, an open-source LLM, qualitatively analyze our generation and evaluation systems using case studies, and outline several areas for future work.

For agents

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

get_harvested_code_for_paper("2403.01304")
get_code_for_paper("2403.01304")
have("2403.01304")

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

curl https://syntology.ai/api/ran/2403.01304.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.01304.svg)](https://syntology.ai/paper/2403.01304)

Connect an agent — have() is free.