arXiv:2607. 28889v1 Announce Type: cross Abstract: Qualitative researchers increasingly encounter interaction corpora whose scale exceeds what manual coding alone can address, and large language models (LLMs) are frequently proposed as analytic assistants.
The paper introduces Agent-as-Peer-Debriefing, a multi‑agent framework that incorporates peer debriefing into qualitative data analysis with large language models. A Hierarchical Coding Agent generates codes and reflections, which are then refined by three Peer‑Debriefing Agents applying Theory‑Driven, Data‑Driven, or Applied perspectives. Experiments on three datasets show that perspective‑based refinement aligns more closely with human codes than a single‑LLM baseline, and that the choice of perspective offers meaningful trade‑offs.
arXiv:2601. 17717v3 Announce Type: replace Abstract: Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities.
arXiv:2610.02679v1 Announce Type: new Abstract: Data journalism, the practice of using data analysis to surface newsworthy stories, depends increasingly on the ability of reporters and investigative...
arXiv:2610.08364v1 Announce Type: new Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions fr...
arXiv:2608.22417v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support text analysis in qualitative research, yet evidence on their performance in inductive con...
QuAD is a framework that quantitatively assesses the quality of qualitative response datasets before analysis. It compares an intrinsic cluster distribution derived from the responses with an extrinsic, researcher-defined analytical lens based on metadata, using a four‑quadrant assessment that considers lens‑level relations and within‑cluster variation. The method employs a content‑aware multi‑agent system with two‑stage instruction generation and adaptive anchors to improve scoring consistency, and is validated through synthetic experiments and a real‑world social survey case study.
The paper investigates how large language models (LLMs) can perform multi-coder qualitative coding by independently coding, debating, and reconciling disagreements. It quantifies the effectiveness of this approach across diverse datasets, identifying key factors—such as codebook length, data similarity, and agent disagreement—that influence coding accuracy. The study finds that intense, unresolved debates improve accuracy but that LLMs still lack adaptive responsiveness to context, leading to design recommendations for automated coding systems.
arXiv:2607. 11890v1 Announce Type: cross Abstract: Open-ended surveys offer valuable insights, but they are notoriously difficult to analyze at scale.
The paper introduces CARE‑SD, a four‑module architecture designed to enhance the reasoning and explanation capabilities of small language models (SLMs) for analyzing self‑disclosure in cybersecurity interview transcripts. By integrating context‑adaptive processing, hierarchical disclosure reasoning, explanation‑consistency verification, and cross‑batch reconciliation, CARE‑SD improves the accuracy and evidence reliability of SLMs, raising Llama 3B’s Macro‑F1 from 0.80 to 0.88 and cutting unsupported claims by 60%. The study demonstrates that a 3B model can match the performance of a 20B reference model, highlighting the architecture’s effectiveness without needing larger models.
arXiv:2606. 06946v1 Announce Type: cross Abstract: We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA).
arXiv:2602. 18446v2 Announce Type: replace-cross Abstract: Users increasingly rely on Large Language Models (LLMs) for Deep Research, using them to synthesize diverse sources into structured reports that support understanding and action.