LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research

• URL: http://arxiv.org/abs/2509.24294v1
• Date: Mon, 29 Sep 2025 05:16:09 GMT
• Title: LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research
• Authors: Xinyu Pi, Qisen Yang, Chuong Nguyen,
• Abstract summary: Grounded theory offers deep insights from qualitative data, but reliance on expert-intensive manual coding presents a major scalability bottleneck.<n>We introduce LOGOS, a novel, end-to-end framework that fully automates the grounded theory workflow.<n> LOGOS integrates LLM-driven coding, semantic clustering, graph reasoning, and a novel iterative refinement process to build highly reusable codebooks.
• Score: 9.819685510441902
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Grounded theory offers deep insights from qualitative data, but its reliance on expert-intensive manual coding presents a major scalability bottleneck. Current computational tools stop short of true automation, keeping researchers firmly in the loop. We introduce LOGOS, a novel, end-to-end framework that fully automates the grounded theory workflow, transforming raw text into a structured, hierarchical theory. LOGOS integrates LLM-driven coding, semantic clustering, graph reasoning, and a novel iterative refinement process to build highly reusable codebooks. To ensure fair comparison, we also introduce a principled 5-dimensional metric and a train-test split protocol for standardized, unbiased evaluation. Across five diverse corpora, LOGOS consistently outperforms strong baselines and achieves a remarkable $88.2\%$ alignment with an expert-developed schema on a complex dataset. LOGOS demonstrates a powerful new path to democratize and scale qualitative research without sacrificing theoretical nuance.

Related papers

• Core-based Hierarchies for Efficient GraphRAG [0.0]
  GraphRAG organizes documents into a knowledge graph with hierarchical communities that can be summarized.<n>Current GraphRAG approaches rely on Leiden clustering for community detection, but we prove that on sparse knowledge graphs, where average degree is constant and most nodes have low degree, modularity optimization admits exponentially many near-optimal partitions.<n>To address this, we propose replacing Leiden with k-core decomposition, which yields a deterministic, density-aware hierarchy in linear time.
  arXiv  Detail & Related papers  (2026-03-05T14:17:30Z)
• NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code [49.610331036334316]
  We introduce NERFIFY, a framework that reliably converts NeRF research papers into trainable Nerfstudio plugins.<n>Code, data and implementations will be publicly released.
  arXiv  Detail & Related papers  (2026-02-28T20:57:32Z)
• Beyond Quantity: Trajectory Diversity Scaling for Code Agents [51.71414642763219]
  Trajectory Diversity Scaling is a data synthesis framework for code agents that scales performance through diversity rather than raw volume.<n> TDScaling integrates four innovations: (1) a Business Cluster mechanism that captures real-service logical dependencies; (2) a blueprint-driven multi-agent paradigm that enforces trajectory coherence; and (3) an adaptive evolution mechanism that steers toward long-tail scenarios.
  arXiv  Detail & Related papers  (2026-02-03T07:43:03Z)
• InfoSynth: Information-Guided Benchmark Synthesis for LLMs [69.80981631587501]
  Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation.<n>Traditional benchmark creation relies on manual human effort, a process that is both expensive and time-consuming.<n>This work introduces Info Synth, a novel framework for automatically generating and evaluating reasoning benchmarks.
  arXiv  Detail & Related papers  (2026-01-02T05:26:27Z)
• DeepCode: Open Agentic Coding [11.7906174865581]
  DeepCode is a fully autonomous framework for document-to-codebase synthesis.<n>It orchestrates four information operations to maximize task-relevant signals under finite context budgets.<n>Extensive evaluations on the PaperBench benchmark demonstrate that DeepCode achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T16:07:13Z)
• From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence [150.3696990310269]
  Large language models (LLMs) have transformed automated software development by enabling direct translation of natural language descriptions into functional code.<n>We provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs.<n>We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder)
  arXiv  Detail & Related papers  (2025-11-23T17:09:34Z)
• CodeAD: Synthesize Code of Rules for Log-based Anomaly Detection with LLMs [34.176333157032076]
  We present CodeAD, a novel framework that automatically synthesizes lightweight Python rule functions for LogAD using large language models (LLMs)<n>CodeAD employs an agentic workflow that iteratively generates, tests, repairs, and refines the rules until it meets correctness and abstraction requirements.<n>Our comprehensive experiments on three public datasets demonstrate that CodeAD achieves an average absolute improvement of 3.6% F1 score over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-10-27T04:08:49Z)
• Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers [103.4410890572479]
  We introduce the Loong Project: an open-source framework for scalable synthetic data generation and verification.<n>LoongBench is a curated seed dataset containing 8,729 human-vetted examples across 12 domains.<n>LoongEnv is a modular synthetic data generation environment that supports multiple prompting strategies to produce new question-answer-code triples.
  arXiv  Detail & Related papers  (2025-09-03T06:42:40Z)
• VERIRL: Boosting the LLM-based Verilog Code Generation via Reinforcement Learning [32.974199255760944]
  We introduce a reinforcement learning framework tailored for Verilog code generation.<n>To tackle the problem of sparse and noisy reward signals, we propose a Trace-back based Rescore mechanism.<n>To mitigate catastrophic forgetting and overfitting during RL fine-tuning, we introduce a sample-balanced weighting strategy.
  arXiv  Detail & Related papers  (2025-08-25T20:20:44Z)
• Automated Validation of LLM-based Evaluators for Software Engineering Artifacts [0.7548538278943616]
  REFINE (Ranking Evaluators for FIne grained Nuanced Evaluation) is an automated framework for benchmarking large language models (LLMs)<n> REFINE applies novel generation techniques to automatically synthesize artifacts with progressively reduced quality.<n>It quantifies each candidate evaluator configuration by measuring how closely its rankings align with expected ordering.
  arXiv  Detail & Related papers  (2025-08-04T18:52:01Z)
• Is Compression Really Linear with Code Intelligence? [60.123628177110206]
  textitFormat Annealing is a lightweight, transparent training methodology designed to assess the intrinsic capabilities of pre-trained models equitably.<n>Our empirical results reveal a fundamental logarithmic relationship between measured code intelligence and bits-per-character (BPC)<n>Our work provides a more nuanced understanding of compression's role in developing code intelligence and contributes a robust evaluation framework in the code domain.
  arXiv  Detail & Related papers  (2025-05-16T16:59:14Z)
• CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code [0.0]
  This study explores the efficiency of Large Language Models (LLMs) in generating solver-specific Linear Programming (LP) code.<n>We propose CHORUS, a retrieval-augmented generation framework for synthesizing Gurobi-based LP code from natural language problem statements.<n> Experiments on the NL4-Code benchmark show that CHORUS improves the performance of open-source LLMs by a significant margin compared to baseline and conventional RAG.
  arXiv  Detail & Related papers  (2025-05-02T16:36:57Z)
• Synthetic Data Generation Using Large Language Models: Advances in Text and Code [0.0]
  Large language models (LLMs) are transforming synthetic training data generation in both natural language and code domains.<n>We highlight key techniques such as prompt-based generation, retrieval-augmented pipelines, and iterative self-refinement.<n>We discuss the accompanying challenges, including factual inaccuracies in generated text, insufficient stylistic or distributional realism, and risks of bias amplification.
  arXiv  Detail & Related papers  (2025-03-18T08:34:03Z)
• OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models [76.59316249991657]
  Large language models (LLMs) for code have become indispensable in various domains, including code generation, reasoning tasks and agent systems.<n>While open-access code LLMs are increasingly approaching the performance levels of proprietary models, high-quality code LLMs remain limited.<n>We introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community.
  arXiv  Detail & Related papers  (2024-11-07T17:47:25Z)
• Reward Generalization in RLHF: A Topological Perspective [11.860984070348348]
  We introduce a theory of reward generalization in reinforcement learning from human feedback.<n>At the macro level, we portray the RLHF information flow as an autoencoding process over behavior distributions.<n>At the micro level, we present induced Bayesian networks to model the impact of dataset topologies on reward generalization.
  arXiv  Detail & Related papers  (2024-02-15T18:39:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.