paper-with-me

Papers

Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Tasks

2024-01-26 · Zackary Okun Dunivin

Qualitative coding, or content analysis, extracts meaning from text to discern quantitative patterns across a corpus of texts. Recently, advances in the interpretive abilities of large language models (LLMs) offer potential for automating the coding process (applying category labels to texts), thereby enabling human researchers to concentrate on more creative research aspects, while delegating these interpretive tasks to AI. Our case study comprises a set of socio-historical codes on dense, paragraph-long passages representative of a humanistic study. We show that GPT-4 is capable of human-equivalent interpretations, whereas GPT-3.5 is not. Compared to our human-derived gold standard, GPT-4 delivers excellent intercoder reliability (Cohen's $\kappa \geq 0.79$) for 3 of 9 codes, and substantial reliability ($\kappa \geq 0.6$) for 8 of 9 codes. In contrast, GPT-3.5 greatly underperforms for all codes ($mean(\kappa) = 0.34$; $max(\kappa) = 0.55$). Importantly, we find that coding fidelity improves considerably when the LLM is prompted to give rationale justifying its coding decisions (chain-of-thought reasoning). We present these and other findings along with a set of best practices for adapting traditional codebooks for LLMs. Our results indicate that for certain codebooks, state-of-the-art LLMs are already adept at large-scale content analysis. Furthermore, they suggest the next generation of models will likely render AI coding a viable option for a majority of codebooks.

📄 PDF Abstract BibTeX arXiv:2401.15170

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

2026-03-12 · Xuanlang Dai, Yujie Zhou, Long Xing, Jiazi Bu 외 arxiv

Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasoning. However, this paradigm suffers from t…

Spatial Reasoning

Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning

2024-01-31 · Tinghui Zhu, Kai Zhang, Jian Xie, Yu Su

Recent advancements have significantly augmented the reasoning capabilities of Large Language Models (LLMs) through various methodologies, especially chain-of-thought (CoT) reasoning. However, previous methods fail to ad…

ThoughtSource: A central hub for large language model reasoning data

2023-01-27 · Simon Ott, Konstantin Hebenstreit, Valentin Liévin, Christoffer Egeberg Hother 외

Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail at complex reasoning, their reasoning p…

Language ModelingLanguage ModellingLarge Language ModelMath+1

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

2024-06-13 · Xuan Zhang, Chao Du, Tianyu Pang, Qian Liu 외

The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However, research indicates that these paths ar…

Arithmetic ReasoningFact VerificationLogical ReasoningQuestion Answering

LLM-Assisted Automated Deductive Coding of Dialogue Data: Leveraging Dialogue-Specific Characteristics to Enhance Contextual Understanding

2025-04-28 · Ying Na, Shihui Feng

Dialogue data has been a key source for understanding learning processes, offering critical insights into how students engage in collaborative discussions and how these interactions shape their knowledge construction. Th…