Image de couverture de livre

Prompting Science Report 4: Playing Pretend: Expert Personas Don't Improve Factual Accuracy

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Basil, Savir, Shapiro, Ina, Shapiro, Dan, Mollick, Ethan, Mollick, Lilach, Meincke, Lennart
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Prompting Science Report 1: Prompt Engineering is Complicated and Contingent
par: Meincke, Lennart, et autres
Publié: (2025)

Prompting Science Report 2: The Decreasing Value of Chain of Thought in Prompting
par: Meincke, Lennart, et autres
Publié: (2025)

Prompting Science Report 3: I'll pay you or I'll kill you -- but will you care?
par: Meincke, Lennart, et autres
Publié: (2025)

Instructors as Innovators: A future-focused approach to new AI learning opportunities, with prompts
par: Mollick, Ethan, et autres
Publié: (2024)

Prompting Diverse Ideas: Increasing AI Idea Variance
par: Meincke, Lennart, et autres
Publié: (2024)

AI Agents and Education: Simulated Practice at Scale
par: Mollick, Ethan, et autres
Publié: (2024)

Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
par: Madhwal, Dhruv, et autres
Publié: (2026)

What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts
par: Yang, Chenyang, et autres
Publié: (2025)

You Don't Need Prompt Engineering Anymore: The Prompting Inversion
par: Khan, Imran
Publié: (2025)

Types for Grassroots Logic Programs
par: Shapiro, Ehud
Publié: (2026)

Why Don't Prompt-Based Fairness Metrics Correlate?
par: Zayed, Abdelrahman, et autres
Publié: (2024)

Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
par: Lumer, Elias, et autres
Publié: (2026)

Don't Touch My Diacritics
par: Gorman, Kyle, et autres
Publié: (2024)

Don't Pay Attention
par: Hammoud, Mohammad, et autres
Publié: (2025)

Show, Don't Tell: Evaluating Large Language Models Beyond Textual Understanding with ChildPlay
par: de Carvalho, Gonçalo Hora, et autres
Publié: (2024)

Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
par: Sinha, Aarush
Publié: (2025)

Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models
par: Yu, Zhiyuan, et autres
Publié: (2024)

Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI
par: Shapiro, Ehud
Publié: (2026)

GLP: A Grassroots, Multiagent, Concurrent, Logic Programming Language
par: Shapiro, Ehud
Publié: (2025)

Fine-Tune, Don't Prompt, Your Language Model to Identify Biased Language in Clinical Notes
par: Landi, Isotta, et autres
Publié: (2026)

The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
par: Chen, Yanjun, et autres
Publié: (2024)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
par: Hassid, Michael, et autres
Publié: (2025)

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
par: Wang, Chenlong, et autres
Publié: (2025)

If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
par: Hernandez, Adriano
Publié: (2024)

Institutional-Level Monitoring of Immune Checkpoint Inhibitor IrAEs Using a Novel Natural Language Processing Algorithmic Pipeline
par: Shapiro, Michael, et autres
Publié: (2024)

Don't Throw Away Your Pretrained Model
par: Feng, Shangbin, et autres
Publié: (2025)

Don't Say No: Jailbreaking LLM by Suppressing Refusal
par: Zhou, Yukai, et autres
Publié: (2024)

Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo
par: Sundararajan, Barkavi, et autres
Publié: (2024)

Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation
par: Samarinas, Chris, et autres
Publié: (2025)

Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
par: Zhao, Ziyi, et autres
Publié: (2026)

Reasoning Models Don't Always Say What They Think
par: Chen, Yanda, et autres
Publié: (2025)

Hard Non-Monotonic Attention for Character-Level Transduction
par: Wu, Shijie, et autres
Publié: (2018)

FS-RAG: A Frame Semantics Based Approach for Improved Factual Accuracy in Large Language Models
par: Madabushi, Harish Tayyar
Publié: (2024)

Hatevolution: What Static Benchmarks Don't Tell Us
par: Di Bonaventura, Chiara, et autres
Publié: (2025)

Think, But Don't Overthink: Reproducing Recursive Language Models
par: Wang, Daren
Publié: (2026)

Don't Forget to Connect! Improving RAG with Graph-based Reranking
par: Dong, Jialin, et autres
Publié: (2024)

Reasoning Models Reason Well, Until They Don't
par: Rameshkumar, Revanth, et autres
Publié: (2025)

Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning
par: Ji, Ke, et autres
Publié: (2025)

Improving Expert Radiology Report Summarization by Prompting Large Language Models with a Layperson Summary
par: Zhao, Xingmeng, et autres
Publié: (2024)

Don't Throw Away Data: Better Sequence Knowledge Distillation
par: Wang, Jun, et autres
Publié: (2024)