LLM Prompting

LLM: Large Language Model

The field studies how the wording and structure of inputs affect what language models understand, generate, and reliably follow. Common approaches include zero- and few-shot in-context learning, chain-of-thought and task decomposition, retrieval-augmented context, and structured prompts using schemas, roles, or constraints. Researchers also develop automated prompt search, feedback-driven refinement, and methods that adapt examples or context to each input, testing them on tasks such as reasoning, classification, code generation, and information extraction. Prompting can improve performance without changing model weights, but its effects vary across models and tasks: added instructions can hurt, and gains in accuracy may trade off with reliability, diversity, safety, or cost.

Latest papers

431 papers34 papers in the last four weeks, down 13% on the four weeks before. 0.2% of all new papers.

Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models
Apr 14, 2026Lei Lin, Jizhao Zhu, Yong Liu +3Structured Reasoning in Language Models Constraint-Guided Reasoning in Language Models
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China · Shenyang Aerospace University · ZGC LAB, Beijing,China +1
From Words to Widgets for Controllable LLM Generation
Apr 13, 2026Chao Zhang, Yiren Liu, Lunyiu Nie +3LLM Prompting Controllable Text Generation
Cornell University Ithaca, NY, USA · University of Illinois Urbana-Champaign Champaign, IL, USA · The University of Texas at Austin Austin, TX, USA +1
STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
Apr 9, 2026Samah Fodeh, Ganesh Puthiaraju, Elyas Irankhah +5Structured Prediction Distributionally Robust Optimization
Yale University, New Haven, CT, USA. · Medical Oncology, Yale School of Medicine, New Haven, CT, USA.
Dynamic Context Evolution for Scalable Synthetic Data Generation
Apr 8, 2026Ryan Lingo, Rajeev ChhajerRepetition in Language Generation Output Diversity in Language Models
Honda Research Institute, USA, Inc.
Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
Apr 8, 2026Haoyue Liu, Zhichao Wang, Yongxin Guo +2LLM Input Optimization LLM Prompting
The Chinese University of Hong Kong, Shenzhen · Taobao and Tmall Group
DiffuMask: Diffusion Language Model for Token-level Prompt Pruning
Apr 8, 2026Caleb Zheng, Jyotika Singh, Fang Tu +6Prompt Compression LLM Context Compression
University of Washington · Oracle AI
AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis
Apr 7, 2026Dong She, Xianrong Yao, Liqun Chen +3VLM Evaluation VLM Calibration
School of Future Technology,South China University of Technology,Guangzhou
The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior
Apr 7, 2026Ameen Patel, Felix Lee, Kyle Liang +1LLM Prompting LLM Safety
Irvington High School · Glen A. Wilson High School · Del Norte High School +1
Optimizing LLM Prompt Engineering with DSPy Based Declarative Learning
Apr 6, 2026Shiek Ruksana, Sailesh Kiran Kurra, Thipparthi Sanjay BaradwajLLM Prompting Prompt Optimization
Vasavi College of Engineering, Hyderabad, TS, India · Amazon, Texas, United States of America · Vasavi College of Engineering, Telangana, India
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Apr 5, 2026Hanchen Li, Runyuan He, Qizheng Zhang +11LLM Input Optimization LLM Prompting
UC Berkeley · Stanford University · Independent +1
When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
Apr 4, 2026Hope McGovern, Caroline Craig, Thomas Lippincott +1Analogical Reasoning for Language Models LLM Reasoning
Cambridge University · Northeastern University · Athenahealth +1
The Format Tax
Apr 4, 2026Ivan Yee Lee, Loris D'Antoni, Taylor Berg-KirkpatrickLLM Prompting Structured Output Generation
UC San Diego
Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation
Apr 3, 2026Prakhar Bansal, Shivangi AgarwalKnowledge Augmentation for Language Models Retrieval-Augmented Generation
The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure
Apr 3, 2026David A. CookLLM Prompting Prompt Engineering
Mayo Clinic College of Medicine and Science | Mayo Clinic Division of General Internal Medicine, Rochester, MN, USA
Social Meaning in Large Language Models: Structure, Magnitude, and Pragmatic Prompting
Apr 2, 2026Roland MühlenberndPragmatic Reasoning in Language Models Language Model Calibration
Leibniz-Centre General Linguistics, Berlin, Germany
Do We Need Frontier Models to Verify Mathematical Proofs?
Apr 2, 2026Aaditya Naik, Guruprerana Shabadi, Rajeev Alur +1LLM Input Optimization Reasoning Verification
University of Pennsylvania, U.S.A.
Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models
Apr 2, 2026Minda Zhao, Yutong Yang, Chufei Peng +5LLM Prompting Framing Effects in Language Models
Harvard University. · Bryn Mawr College.
Adam's Law: Textual Frequency Law on Large Language Models
Apr 2, 2026Hongyuan Adam Lu, Z. L., Victor Wei +5LLM Prompting LLM Fine-Tuning
FaceMind Corporation · The Chinese University of Hong Kong
Analysis of LLM Performance on AWS Bedrock: Receipt-item Categorisation Case Study
Apr 2, 2026Gabby Sanchez, Sneha Oommen, Cassandra T. Britto +3LLM Evaluation Classification
RMIT University, Melbourne, Australia
ReFormeR: Learning and Applying Explicit Query Reformulation Patterns
Apr 1, 2026Amin Bigdeli, Mert Incesu, Negar Arabzadeh +2Query Reformulation LLM Prompting
University of Waterloo, Waterloo, Ontario, Canada · University of Toronto, Toronto, Ontario, Canada · University of California, Berkeley, Berkeley, California, USA
Information Extraction from Electricity Invoices with General-Purpose Large Language Models
Apr 1, 2026Javier Gómez, Javier SánchezDocument Information Extraction LLM Information Extraction
Centro de Tecnologías de la Imagen (CTIM) Instituto Universitario de Cibernética, Empresas y Sociedad (IUCES) Universidad de Las Palmas de Gran Canaria 35017 Las Palmas de Gran Canaria, Spain · Centro de Tecnologías de la Imagen (CTIM) Instituto Universitario de Cibernética, Empresas y Sociedad (IUCES) University of Las Palmas de Gran Canaria 35017 Las Palmas de Gran Canaria, Spain
Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs
Mar 31, 2026Zhuowen Liang, Xiaotian Lin, Zhengxuan Zhang +3Question Answering Document QA
The Hong Kong University of Science and Technology (Guangzhou) · EvenUp, USA
"I Just Need GPT to Refine My Prompts": Rethinking Onboarding and Help-Seeking with Generative 3D Modeling Tools
Mar 31, 2026Kanak Gautam, Poorvi Bhatia, Parmit K. ChilanaHuman-AI Interaction LLM Prompting
Computing Science, Simon Fraser University, Burnaby, British Columbia, Canada
From Reviews to Requirements: Can LLMs Generate Human-Like User Stories?
Mar 30, 2026Shadman Sakib, Oishy Fatema Akhand, Tasnia Tasneem +1Requirements Engineering Text Generation
Department of Computer Science and Engineering, Islamic University of Technology (IUT), Gazipur, Bangladesh
Beyond the Answer: Decoding the Behavior of LLMs as Scientific Reasoners
Mar 30, 2026Rohan Pandey, Eric Ye, Michael LiLLM Prompting LLM Interpretability
Carnegie Mellon University
Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3
Mar 29, 2026Natapong NitarachLLM Reasoning LLM Prompting
Umwelt Engineering: Designing the Cognitive Worlds of Linguistic Agents
Mar 29, 2026Rodney Jehu-AppiahLLM Prompting Software Engineering Agents
Improving Attributed Long-form Question Answering with Intent Awareness
Mar 28, 2026Xinran Zhao, Aakanksha Naik, Jay DeYoung +4Long-Form Document Generation Text Generation
Allen Institute for AI · Carnegie Mellon University · University of Washington
Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation
Mar 28, 2026Hung Ming LiuLost-in-the-Middle Effect Information Retrieval
PARRAWA AI
RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models
Mar 27, 2026Rahul SoniLLM Input Optimization LLM Prompting
Independent Researcher

Apr 14, 2026J/K move · Enter open · S save

Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models

Lei Lin, Jizhao Zhu, Yong Liu, Donghong Sun+2

Computer Network Information Center, Chinese Academy of Sciences, Beijing, China · Shenyang Aerospace University · ZGC LAB, Beijing,China+1

Structured Reasoning in Language Models Constraint-Guided Reasoning in Language Models Inductive Reasoning in Language Models LLM Prompting Efficient Language Model Reasoning Large Reasoning Models

Open paper AskPDF arXiv

This paper addresses two limitations of large language models (LLMs) in solving complex problems: (1) their reasoning processes exhibit Bayesian-like stochastic generation, where each token is sampled from a context-dependent probability distribution, leading to inherently random decision trajectories rather than deterministic planning; (2) the reasoning and decision-making mechanisms are statically decoupled, meaning dynamically retrieved domain knowledge fails to dynamically adjust the underlying reasoning strategy. These dual deficiencies result in initial decisions lacking strategic anchoring and reasoning chains often failing to converge on correct solutions, as stochastic generation lacks mechanisms for trajectory correction or knowledge-guided optimization during sequential reasoning. To resolve these issues, we propose a problem-solving method integrated into the LLM's generation process to guide reasoning. This method, compatible with numerous LLMs and featuring reusable solutions, is grounded in a novel Heuristic-Classification-of-Thoughts prompting schema (HCoT). HCoT synergizes the LLM's reasoning ability with a structured problem space via a heuristic classification model that controls the reasoning process and provides reusable abstract solutions. Evaluated on two complex inductive reasoning tasks with ill-defined search spaces, HCoT outperforms existing approaches (e.g., Tree-of-Thoughts and Chain-of-Thoughts prompting) in performance. On the well-structured 24 Game task, HCoT demonstrates significantly higher token efficiency compared to the state-of-the-art Tree-of-Thoughts-Breadth-First-Search. In terms of both accuracy and token usage, HCoT achieves a Pareto frontier balance, offering a strong trade-off between performance and computational cost.