SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.04072 · 2023

Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 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/2311.04072.json · badge: /api/ran/2311.04072.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
rucaibox/figa canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rucaibox/figa/modeling_llama.py
pointer only (licence: NONE) · get_code("9b4dff79d5e6102c")
How it ran

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

atoi Ran
ran, honoured the contract we drafted
rucaibox/figa/utils/zero_to_fp32.py
pointer only (licence: NONE); the stored copy get_code serves, from harshmaru7/DilatedConv, is pointer only (licence: NONE) · get_code("6dbf1b2a5b901370")
How it ran

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

default_compute_objective Ran
ran, honoured the contract we drafted
rucaibox/figa/trainer_utils.py
pointer only (licence: NONE) · get_code("90a5eb11d360639f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/figa 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_last_checkpoint Ran
ran; our contract draft was wrong, not the code
rucaibox/figa/trainer_utils.py
pointer only (licence: NONE) · get_code("9f1130d32c6430f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/figa 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_model_state_file Ran
ran; our contract draft was wrong, not the code
rucaibox/figa/utils/zero_to_fp32.py
pointer only (licence: NONE); the stored copy get_code serves, from rucaibox/lc-rec, is pointer only (licence: NONE) · get_code("3a53f3109825e747")
How it ran

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

natural_keys Ran
ran; our contract draft was wrong, not the code
rucaibox/figa/utils/zero_to_fp32.py
pointer only (licence: NONE) · get_code("7052cf0436949e37")
How it ran

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

rotate_half Ran
ran; our contract draft was wrong, not the code
rucaibox/figa/modeling_llama.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

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

default_hp_space_optuna Not yet run
unverified (harvested, no recorded run)
rucaibox/figa/trainer_utils.py
pointer only (licence: NONE) · get_code("cf0fe571e5b667a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rucaibox/figa 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 5 the same month, 5 later) and 2 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
rotate_half 360 other papers
39 dated earlier, 7 the same month, 311 later, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
apply_rotary_pos_emb 47 other papers
18 dated earlier, 3 the same month, 26 later
2305.14167 (2023-05)
DetGPT: Detect What You Need via Reasoning
2305.16103 (2023-05)
ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst
2305.16355 (2023-05)
PandaGPT: One Model To Instruction-Follow Them All
and 44 more not named here
atoi 13 other papers
7 dated earlier, 1 the same month, 5 later
1511.07122 (2015-11)
Multi-Scale Context Aggregation by Dilated Convolutions
1908.03706 (2019-08)
Exploiting temporal consistency for real-time video depth estimation
2104.08773 (2021-04)
Cross-Task Generalization via Natural Language Crowdsourcing Instructions
and 10 more not named here
natural_keys 12 other papers
6 dated earlier, 1 the same month, 5 later
1511.07122 (2015-11)
Multi-Scale Context Aggregation by Dilated Convolutions
1908.03706 (2019-08)
Exploiting temporal consistency for real-time video depth estimation
2203.03339 (2022-03)
L2CS-Net: Fine-Grained Gaze Estimation in Unconstrained Environments
and 9 more not named here
get_model_state_file 5 other papers
2 dated earlier, 1 the same month, 2 later
2308.14034 (2023-08)
Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum
2310.09168 (2023-10)
EXPLORE-INSTRUCT: Enhancing Domain-Specific Instruction Coverage through Active Exploration
2311.09049 (2023-11)
Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
and 2 more not named here
get_last_checkpoint 4 other papers
3 dated earlier, 1 same year, order not determinable
2202.13669 (2022-02)
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
2212.02623 (2022-12)
Unifying Vision, Text, and Layout for Universal Document Processing
2023.findings-emnlp.107 (2023 (year only))
Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document
and 1 more not named here

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

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate to implement and train, thus recent studies explore how to develop alternative alignment approaches based on supervised fine-tuning (SFT). A major limitation of SFT is that it essentially does imitation learning, which cannot fully understand what are the expected behaviors. To address this issue, we propose an improved alignment approach named FIGA. Different from prior methods, we incorporate fine-grained (i.e., token or phrase level) quality signals that are derived by contrasting good and bad responses. Our approach has made two major contributions. Firstly, we curate a refined alignment dataset that pairs initial responses and the corresponding revised ones. Secondly, we devise a new loss function can leverage fine-grained quality signals to instruct the learning of LLMs for alignment. Extensive experiments have demonstrated the effectiveness of our approaches by comparing a number of competitive baselines.

For agents

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

get_harvested_code_for_paper("2311.04072")
get_code_for_paper("2311.04072")
have("2311.04072")

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

curl https://syntology.ai/api/ran/2311.04072.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.04072.svg)](https://syntology.ai/paper/2311.04072)

Connect an agent — have() is free.