Papers › Distill Visual Chart Reasoning Ability from LLMs to MLLMs

Distill Visual Chart Reasoning Ability from LLMs to MLLMs

24 Oct 2024arXiv:2410.18798archive 2025-07-28

wei he, Zhiheng Xi, Wanxu Zhao, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang

Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs). Recent studies highlight that these abilities consist of two main parts: recognizing key information from visual inputs and conducting reasoning over it. Thus, a promising approach to enhance MLLMs is to construct relevant training data focusing on the two aspects. However, collecting and annotating complex charts and questions is costly and time-consuming, and ensuring the quality of annotated answers remains a challenge. In this paper, we propose Code-as-Intermediary Translation (CIT), a cost-effective, efficient and easily scalable data synthesis method for distilling visual reasoning abilities from LLMs to MLLMs. The code serves as an intermediary that translates visual chart representations into textual representations, enabling LLMs to understand cross-modal information. Specifically, we employ text-based synthesizing techniques to construct chart-plotting code and produce ReachQA, a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs to enhance both recognition and reasoning abilities. Experiments show that when fine-tuned with our data, models not only perform well on chart-related benchmarks, but also demonstrate improved multimodal reasoning abilities on general mathematical benchmarks like MathVista. The code and dataset are publicly available at https://github.com/hewei2001/ReachQA.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.18798")

Code

Syntology Ran 0 of 13 code samples harvested from 1 repository linked to this paper; 13 have no recorded run.

By repository: official repository: 13 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hewei2001/reachqa officialmentioned in papermentioned on GitHub report
princeton-nlp/CharXiv mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 0 ran; 0 honoured the contract we drafted; 13 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

13unverified

Licence: 13 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hewei2001/reachqa. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

create_chat_response hewei2001/reachqa/utils/openai_utils.py official repository unverified no licence file found · pointer only · af6a0fc9903f51d4 · report
create_chat_response_by_messages hewei2001/reachqa/utils/openai_utils.py official repository unverified no licence file found · pointer only · 965a7683faa03bf9 · report
create_json_mode_chat_response_by_messages hewei2001/reachqa/utils/openai_utils.py official repository unverified no licence file found · pointer only · c4113cface723033 · report
extract_decision hewei2001/reachqa/batch_filter_QA.py official repository unverified no licence file found · pointer only · 7cd243b2d264c131 · report
extract_python_code_block hewei2001/reachqa/openai_generate_code.py official repository unverified no licence file found · pointer only · 7c45fbb8ee3f6b2b · report
extract_rating hewei2001/reachqa/batch_filter_image.py official repository unverified no licence file found · pointer only · 9dad39546954330c · report
get_chart_note hewei2001/reachqa/utils/chart_notes.py official repository unverified no licence file found · pointer only · 51a34bdea2f554b0 · report
load_datasets hewei2001/reachqa/swift_infer_dataset.py official repository unverified no licence file found · pointer only · 93aa2fdc7356d575 · report
load_swift_outputs hewei2001/reachqa/openai_llm_evaluation.py official repository unverified no licence file found · pointer only · f1d27a598bf0c523 · report
load_vlmevalkit_outputs hewei2001/reachqa/openai_llm_evaluation.py official repository unverified no licence file found · pointer only · 94874ae0d42c0dd1 · report
post_process_model_response hewei2001/reachqa/openai_generate_code.py official repository unverified no licence file found · pointer only · a4d5ecf8ca46fdf1 · report
post_process_model_response hewei2001/reachqa/openai_llm_evaluation.py official repository unverified no licence file found · pointer only · 4d1a3a68e63960b3 · report
simulate_code hewei2001/reachqa/openai_generate_code.py official repository unverified no licence file found · pointer only · 4e745eb2738b7b9d · report

Tasks

Multimodal ReasoningVisual Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections