SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.12873 · NAACL · 2024

Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model

Rui Wang, Shuming Shi, Zhaopeng Tu, Wenxiang Jiao, Zhiwei He, Xing Wang, Zhuosheng Zhang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 4 failures of our instrument; 1 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/2401.12873.json · badge: /api/ran/2401.12873.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
zwhe99/FeedbackMT canonical (classifier label)
classifier basis: census
4 ran · 1 no recorded run
FunctionStatusWhere it lives
create_prompt Ran
ran; our contract draft was wrong, not the code
zwhe99/FeedbackMT/src/inference_sft.py
pointer only (licence: NONE); the stored copy get_code serves, from pangjh3/anllm, is pointer only (licence: NONE) · get_code("4a62d89cb68ccb26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwhe99/FeedbackMT 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.

pattern_match Ran
ran; our contract draft was wrong, not the code
zwhe99/FeedbackMT/src/LMFlow/utils/lm_evaluator.py
pointer only (licence: NONE); the stored copy get_code serves, from deeplearning-wisc/weak_llm_teacher, is pointer only (licence: NONE) · get_code("c12b55ef635e9947")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwhe99/FeedbackMT 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.

read_input Ran
ran; our contract draft was wrong, not the code
zwhe99/FeedbackMT/src/inference_sft.py
pointer only (licence: NONE) · get_code("249d0dda07bcb0de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwhe99/FeedbackMT 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.

read_instruct Ran
ran; our contract draft was wrong, not the code
zwhe99/FeedbackMT/src/inference_sft.py
pointer only (licence: NONE) · get_code("f47fb9e7de49f89e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwhe99/FeedbackMT 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_full_repo_name Not yet run
unverified (harvested, no recorded run)
zwhe99/FeedbackMT/src/LMFlow/experimental/RAFT-diffusion/train_text_to_image_lora.py
pointer only (licence: NONE) · get_code("c65c0b4a64bac1ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zwhe99/FeedbackMT 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 4 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
get_full_repo_name 17 other papers
15 dated earlier, 1 later, 1 same year, order not determinable
2210.09477 (2022-10)
UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image
2211.15388 (2022-11)
Shifted Diffusion for Text-to-image Generation
2302.07944 (2023-02)
Effective Data Augmentation With Diffusion Models
and 14 more not named here
pattern_match 6 other papers
2 dated earlier, 4 later
2306.03078 (2023-06)
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
2309.06256 (2023-09)
Mitigating the Alignment Tax of RLHF
2402.11295 (2024-02)
OneBit: Towards Extremely Low-bit Large Language Models
and 3 more not named here
read_instruct 5 other papers
2 dated earlier, 1 the same month, 2 later
2308.12097 (2023-08)
Instruction Position Matters in Sequence Generation with Large Language Models
2308.12674 (2023-08)
Improving Translation Faithfulness of Large Language Models via Augmenting Instructions
2401.08350 (2024-01)
Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models
and 2 more not named here
create_prompt 2 other papers
1 the same month, 1 later
2401.08350 (2024-01)
Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models
2402.07616 (2024-02)
Anchor-based Large Language Models

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

Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation (QE), which predicts the quality of a given translation without reference, has achieved impressive alignment with human evaluations in the last two years. In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training. We first identify the overoptimization problem during QE-based feedback training, manifested as an increase in reward while translation quality declines. We examine the problem and argue that the vulnerability of the QE model might lead to high rewards for incorrect translations, resulting in overoptimization and error propagation. To address the problem, we adopt a simple yet effective method that uses heuristic rules to detect the incorrect translations and assigns a penalty term to the reward scores of them. Experimental results show that the proposed QE-based feedback training achieves consistent and significant improvements across various settings, further verified through human preference studies. Our subsequent analysis demonstrates the high data efficiency of the proposed QE-based feedback training: it outperforms systems using larger parallel corpora by a small amount of monolingual data. Our code is available at: https: //github.com/zwhe99/FeedbackMT

For agents

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

get_harvested_code_for_paper("2401.12873")
get_code_for_paper("2401.12873")
have("2401.12873")

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

curl https://syntology.ai/api/ran/2401.12873.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.12873.svg)](https://syntology.ai/paper/2401.12873)

Connect an agent — have() is free.