Knowledge Tree
CoT
Facts (10)
Sources
Survey and analysis of hallucinations in large language models frontiersin.org Sep 29, 2025 3 facts
claimHallucination scores for language models change little across prompting techniques such as Zero-shot, Few-shot, CoT, and Instruction formats because the prompts are semantically equivalent and decoding is low-entropy, causing outputs to be dominated by the models' learned alignment policies.
claimStructured prompt strategies, such as chain-of-thought (CoT) prompting, significantly reduce hallucinations in prompt-sensitive scenarios, although intrinsic model limitations persist in some cases.
procedureThe experimental pipeline evaluates hallucinations in open-source LLMs by integrating benchmark datasets, varied prompt strategies (zero-shot, few-shot, CoT), and text generation via HuggingFace.
Medical Hallucination in Foundation Models and Their Impact on ... medrxiv.org Nov 2, 2025 2 facts
procedureThe 'CoT' (Chain-of-Thought) evaluation method involves appending the phrase 'Let’s think step by step.' to each question to encourage the LLM to articulate its reasoning process explicitly.
procedureThe Similarity Score calculation process involves three steps: (1) Embedding Generation: Encoding the original medical question, the correct option, and the model's generated output using UMLSBERT for each method (Base, System Prompt, CoT, MedRAG, Internet Search). (2) Cosine Similarity Calculation: Calculating the cosine similarity for model outputs against the correct option (Answer Similarity) and the original question (Question Similarity). (3) Combined Similarity Score: Computing the average of the Answer Similarity and the Question Similarity.
The Synergy of Symbolic and Connectionist AI in LLM ... arxiv.org 2 facts
claimChain-of-Thought (CoT) prompting improves problem-solving accuracy and reliability in LLMs by enabling coherent, step-by-step elaboration of thought processes.
claimThe Chain-of-Thought (CoT) method enhances the cognitive task performance of LLM-empowered agents by guiding the models to generate text about intermediate reasoning steps.
The construction and refined extraction techniques of knowledge ... nature.com Feb 10, 2026 1 fact
procedureThe ablation study framework for evaluating knowledge extraction models includes five variants: (1) Full Model, which integrates BM-LoRA, TL-LoRA, TA-LoRA, RAG, and CoT; (2) w/o TA-LoRA, which excludes the Task-Adaptive LoRA module; (3) w/o RAG, which disables Retrieval-Augmented Generation; (4) w/o CoT, which removes Chain-of-Thought prompting; and (5) Rule-based Only, which uses only rule-based systems and ontological constraints.
A framework to assess clinical safety and hallucination rates of LLMs ... nature.com May 13, 2025 1 fact
claimChain of Thought (CoT) prompting generally enhances the reasoning abilities of large language models.
Medical Hallucination in Foundation Models and Their ... medrxiv.org Mar 3, 2025 1 fact
procedureThe Med-HALT benchmark evaluation procedure for embedding generation involves encoding the original medical question, the correct ground truth option, and the model's generated output for each method (Base, System Prompt, CoT, MedRAG, Internet Search) into embeddings using UMLSBERT.