SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.20906 · 2024

Automated Review Generation Method Based on Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 10 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
tju-ecat-ai/automaticreviewgeneration canonical 10 of 12
FunctionStatusWhere it lives
GetResult Ran tju-ecat-ai/automaticreviewgeneration/DataMining/MainContributeCatalystDetailStatisticsNew.py
code served (permissive licence) · get_code("353f992ada2aa64b")
calculate_linewidths Ran tju-ecat-ai/automaticreviewgeneration/DataMining/BubblePlotAll.py
code served (permissive licence) · get_code("090c0e4832fe5b1a")
calculate_relative_score_diff Ran tju-ecat-ai/automaticreviewgeneration/QualityEvaluation/ComparedScore.py
code served (permissive licence) · get_code("ffa6d186e0b4fc1f")
calculate_yearly_frequency Ran tju-ecat-ai/automaticreviewgeneration/DataMining/PlotGanttTypeAll.py
code served (permissive licence) · get_code("1e0efb58887cbed2")
create_analysis_df Ran tju-ecat-ai/automaticreviewgeneration/ReviewComposition/Advanced_ComparedScore.py
code served (permissive licence) · get_code("5d086858b4ba9be5")
extract_element Ran tju-ecat-ai/automaticreviewgeneration/DataMining/AveragedTop5.py
code served (permissive licence) · get_code("2bb840a90716d658")
get_text Ran tju-ecat-ai/automaticreviewgeneration/DataMining/MainContributeCatalystDetailStatisticsNew.py
code served (permissive licence) · get_code("e525116fe4648434")
outliers_iqr Ran tju-ecat-ai/automaticreviewgeneration/DataMining/BubblePlotAll.py
code served (permissive licence) · get_code("2ba37728ec3e26a8")
process_json Ran tju-ecat-ai/automaticreviewgeneration/ReviewComposition/Advanced_ComparedScore.py
code served (permissive licence) · get_code("6f352bd68526a5d4")
truncate_at_first_digit Ran tju-ecat-ai/automaticreviewgeneration/DataMining/MainContributeCatalystDetailStatisticsNew.py
code served (permissive licence) · get_code("615041a63880f3f5")
GetResponseFromClaudeViaWebAgent Not yet run tju-ecat-ai/automaticreviewgeneration/DataMining/AnswerIntegration.py
code served (permissive licence) · get_code("468592d930975a2b")
process_file Not yet run tju-ecat-ai/automaticreviewgeneration/ReviewComposition/Advanced_ComparedScore.py
code served (permissive licence) · get_code("8f9db599f9f467a3")

Repositories linked to this paper

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

Abstract

Literature research, vital for scientific work, faces the challenge of surging information volumes exceeding researchers' processing capabilities. We present an automated review generation method based on large language models (LLMs) to overcome efficiency bottlenecks and reduce cognitive load. Our statistically validated evaluation framework demonstrates that the generated reviews match or exceed manual quality, offering broad applicability across research fields without requiring users' domain knowledge. Applied to propane dehydrogenation (PDH) catalysts, our method swiftly analyzed 343 articles, averaging seconds per article per LLM account, producing comprehensive reviews spanning 35 topics, with extended analysis of 1041 articles providing insights into catalysts' properties. Through multi-layered quality control, we effectively mitigated LLMs' hallucinations, with expert verification confirming accuracy and citation integrity while demonstrating hallucination risks reduced to below 0.5\% with 95\% confidence. Released Windows application enables one-click review generation, enhancing research productivity and literature recommendation efficiency while setting the stage for broader scientific explorations.

For agents

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

get_harvested_code_for_paper("2407.20906")
get_code_for_paper("2407.20906")
have("2407.20906")

Connect an agent — have() is free.