LLM Prompting

LLM: Large Language Model

Follow this topic Ask about this topic

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.

Mar 7, 2026

Do Deployment Constraints Make LLMs Hallucinate Citations? An Empirical Study across Four Models and Five Prompting Regimes

LLMs are increasingly used to draft academic text and to support software engineering (SE) evidence synthesis, but they often hallucinate bibliographic references that look legitimate. We study how deployment-motivated prompting constraints affect citation verifiability in a closed-book setting. Using 144 claims (24 in SE&CS) and a deterministic verification pipeline (Crossref + Semantic Scholar), we evaluate two proprietary models (Claude Sonnet, GPT-4o) and two open-weight models (LLaMA~~3.1-8B, Qwen~~2.5-14B) across five regimes: Baseline, Temporal (publication-year window), Survey-style breadth, Non-Disclosure policy, and their combination. Across 17,443 generated citations, no model exceeds a citation-level existence rate of 0.475; Temporal and Combo conditions produce the steepest drops while outputs remain format-compliant (well-formed bibliographic fields). Unresolved outcomes dominate (36-61%); a 100-citation audit indicates that a substantial fraction of Unresolved cases are fabricated. Results motivate post-hoc citation verification before LLM outputs enter SE literature reviews or tooling pipelines.

Chen Zhao, Yuan Tang, Yitian Qian

New York University, United States · Carnegie Mellon University, United States · Boston University, United States

Hallucination in Language Models LLM Prompting Citation Verification LLM Hallucination Detection

Mar 6, 2026

Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls

Test-time adaptation enables large language models (LLMs) to modify their behavior at inference without updating model parameters. A common approach is many-shot prompting, where large numbers of in-context learning (ICL) examples are injected as an input-space test-time update. Although performance can improve as more demonstrations are added, the reliability and limits of this update mechanism remain poorly understood, particularly for open-source models. We present an empirical study of many-shot prompting across tasks and model backbones, analyzing how performance varies with update magnitude, example ordering, and selection policy. We further study Dynamic and Reinforced ICL as alternative test-time update strategies that control which information is injected and how it constrains model behavior. We find that many-shot prompting is effective for structured tasks where demonstrations provide high information gain, but is highly sensitive to selection strategy and often shows limited benefits for open-ended generation tasks. Overall, we characterize the practical limits of prompt-based test-time adaptation and outline when input-space updates are beneficial versus harmful.

Shubhangi Upasani, Chen Wu, Jay Rainton +4

SambaNova Systems, Inc · Stanford University

Inference-Time Adaptation of Language Models LLM Prompting In-Context Learning

Mar 4, 2026

Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models

As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customize LLM behavior, we argue that text-only prompting does not constitute a suitable control interface for scalable, stable, and inference-only customization. This position paper argues that model providers should expose vector prompt inputs as part of the public interface for customizing LLMs. We support this position with diagnostic evidence showing that vector prompt tuning continues to improve with increasing supervision whereas text-based prompt optimization saturates early, and that vector prompts exhibit dense, global attention patterns indicative of a distinct control mechanism. We further discuss why inference-only customization is increasingly important under realistic deployment constraints, and why exposing vector prompts need not fundamentally increase model leakage risk under a standard black-box threat model. We conclude with a call to action for the community to rethink prompt interfaces as a core component of LLM customization.

Liangwei Yang, Shiyu Wang, Haolin Chen +12

Salesforce AI Research, Palo Alto, CA, United States.

LLM Prompting Prompt Tuning

Mar 4, 2026

The Arrival of AGI? When Expert Personas Exceed Expert Benchmarks

Do expert personas improve language model performance? The Wharton Generative AI Lab reports that they do not, broadcasting to millions via social media the recommendation that practitioners abandon a technique recommended by Anthropic, Google, and OpenAI. We demonstrate that this null finding was structurally predictable. Five core mechanisms precluded detection before data collection began: baseline contamination elevating the starting point to near-ceiling, system prompt hierarchy subordinating experimental manipulation, impossible expert specifications collapsing to generic competence, format constraints suppressing reasoning processes, and provider exclusion limiting generalizability. Controlled trials correcting these limitations reveal what the original design obscured. To test this, we selected the GPQA Diamond hardest questions to prevent baseline pattern matching, forcing reliance on genuine expert reasoning. On items with valid key answers, expert personas achieve ceiling accuracy. They eliminated all baseline errors through confidence amplification. Furthermore, forensic examination of model divergence identified that half of the hardest GPQA items contain chemically or logically indefensible answers. The model's CoT revealed reasoning away from impossible answers, yielding penalization for accurate chemistry. These findings recontextualize the original null results. Methodologically sound persona research faces measurement constraints imposed by benchmark validity limitations. Answering the persona question requires evaluation infrastructure the field does not yet possess.

Drake Mullens, Stella Shen

Tarleton State University · University of Texas at Tyler

LLM Prompting Language Model Generation Evaluation Benchmark Validity

Mar 4, 2026

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Think about how human handles complex reading tasks: marking key points, inferring their relationships, and structuring information to guide understanding and responses. Likewise, can a large language model benefit from text structure to enhance text-processing performance? To explore it, in this work, we first introduce Structure of Thought (SoT), a prompting technique that explicitly guides models to construct intermediate text structures, consistently boosting performance across eight tasks and three model families. Building upon this insight, we present T2S-Bench, the first benchmark designed to evaluate and improve text-to-structure capabilities of models. T2S-Bench includes 1.8K samples across 6 scientific domains and 32 structural types, rigorously constructed to ensure accuracy, fairness, and quality. Evaluation on 45 mainstream models reveals substantial improvement potential: the average accuracy on the multi-hop reasoning task is only 52.1%, and even the most advanced model achieves 58.1% node accuracy in end-to-end extraction. Furthermore, on Qwen2.5-7B-Instruct, SoT alone yields an average +5.7% improvement across eight diverse text-processing tasks, and fine-tuning on T2S-Bench further increases this gain to +8.6%. These results highlight the value of explicit text structuring and the complementary contributions of SoT and T2S-Bench. Dataset and eval code have been released at https://t2s-bench.github.io/T2S-Bench-Page/.

Qinsi Wang, Hancheng Ye, Jinhee Kim +12

Duke University · UT Austin · Meta

Structured Reasoning LLM Reasoning LLM Evaluation LLM Prompting LLM Information Extraction

Mar 3, 2026

Evaluating Prompting Strategies for Chart Question Answering with Large Language Models

Prompting strategies affect LLM reasoning performance, but their role in chart-based QA remains underexplored. We present a systematic evaluation of four widely used prompting paradigms (Zero-Shot, Few-Shot, Zero-Shot Chain-of-Thought, and Few-Shot Chain-of-Thought) across GPT-3.5, GPT-4, and GPT-4o on the ChartQA dataset. Our framework operates exclusively on structured chart data, isolating prompt structure as the only experimental variable, and evaluates performance using two metrics: Accuracy and Exact Match. Results from 1,200 diverse ChartQA samples show that Few-Shot Chain-of-Thought prompting consistently yields the highest accuracy (up to 78.2%), particularly on reasoning-intensive questions, while Few-Shot prompting improves format adherence. Zero-Shot performs well only with high-capacity models on simpler tasks. These findings provide actionable guidance for selecting prompting strategies in structured data reasoning tasks, with implications for both efficiency and accuracy in real-world applications.

Ruthuparna Naikar, Ying Zhu

Georgia State University, Atlanta GA, USA

LLM Prompting Chart QA Few-Shot Prompting CoT Reasoning

Mar 2, 2026

Not All Queries Need Rewriting: When Prompt-Only LLM Refinement Helps and Hurts Dense Retrieval

Prompt-only, single-step LLM query rewriting, where a rewrite is generated from the query alone without retrieval feedback, is commonly used in production RAG pipelines, but its effect on dense retrieval is poorly understood. We present a systematic empirical study across three BEIR benchmarks, two dense retrievers, and multiple training configurations, and find strongly domain-dependent behavior: rewriting degrades nDCG@10 by 9.0 percent on FiQA, improves it by 5.1 percent on TREC-COVID, and has no significant effect on SciFact. We identify a consistent mechanism: degradations co-occur with reduced lexical alignment between rewritten queries and relevant documents, as rewriting replaces domain-specific terms in already well-matched queries. In contrast, improvements arise when rewriting shifts queries toward corpus-preferred terminology and resolves inconsistent nomenclature. Lexical substitution occurs in 95 percent of rewrites across all outcome groups, showing that effectiveness depends on the direction of substitution rather than substitution itself. We also study selective rewriting and find that simple feature-based gating can reduce worst-case regressions but does not reliably outperform never rewriting, with even oracle selection offering only modest gains. Overall, these results show that prompt-only rewriting can be harmful in well-optimized verticals and suggest that domain-adaptive post-training is a safer strategy when supervision or implicit feedback is available.

Varun Kotte

Adobe

Query Reformulation Dense Retrieval LLM Prompting IR Evaluation

Feb 26, 2026

Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift

The rapid evolution of large language models (LLMs) has transformed prompt engineering from a localized craft into a systems-level governance challenge. As models scale and update across generations, prompt behavior becomes sensitive to shifts in instruction-following policies, alignment regimes, and decoding strategies, a phenomenon we characterize as GPT-scale model drift. Under such conditions, surface-level formatting conventions and ad hoc refinement are insufficient to ensure stable, interpretable control. This paper reconceptualizes Natural Language Declarative Prompting (NLD-P) as a declarative governance method rather than a rigid field template. NLD-P is formalized as a modular control abstraction that separates provenance, constraint logic, task content, and post-generation evaluation, encoded directly in natural language without reliance on external orchestration code. We define minimal compliance criteria, analyze model-dependent schema receptivity, and position NLD-P as an accessible governance framework for non-developer practitioners operating within evolving LLM ecosystems. Portions of drafting and editorial refinement employed a schema-bound LLM assistant configured under NLD-P. All conceptual framing, methodological claims, and final revisions were directed, reviewed, and approved by the human author under a documented human-in-the-loop protocol. The paper concludes by outlining implications for declarative control under ongoing model evolution and identifying directions for future empirical validation.

Hyunwoo Kim, Hanau Yi, Jaehee Bae +1

ddai Inc.

LLM Prompting Prompt Engineering

Feb 25, 2026

Scaling In, Not Up? Testing Thick Citation Context Analysis with GPT-5 and Fragile Prompts

This paper tests whether large language models (LLMs) can support interpretative citation context analysis (CCA) by scaling in thick, text-grounded readings of a single hard case rather than scaling up typological labels. It foregrounds prompt-sensitivity analysis as a methodological issue by varying prompt scaffolding and framing in a balanced 2x3 design. Using footnote 6 in Chubin and Moitra (1975) and Gilbert's (1977) reconstruction as a probe, I implement a two-stage GPT-5 pipeline: a citation-text-only surface classification and expectation pass, followed by cross-document interpretative reconstruction using the citing and cited full texts. Across 90 reconstructions, the model produces 450 distinct hypotheses. Close reading and inductive coding identify 21 recurring interpretative moves, and linear probability models estimate how prompt choices shift their frequencies and lexical repertoire. GPT-5's surface pass is highly stable, consistently classifying the citation as "supplementary". In reconstruction, the model generates a structured space of plausible alternatives, but scaffolding and examples redistribute attention and vocabulary, sometimes toward strained readings. Relative to Gilbert, GPT-5 detects the same textual hinges yet more often resolves them as lineage and positioning than as admonishment. The study outlines opportunities and risks of using LLMs as guided co-analysts for inspectable, contestable interpretative CCA, and it shows that prompt scaffolding and framing systematically tilt which plausible readings and vocabularies the model foregrounds.

Arno Simons

Technische Universität Berlin

Scientific Communication Prompt Sensitivity LLM Prompting

Feb 24, 2026

SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference

Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large language model (LLM)-based methods have shown successes in generating specifications such as postconditions, but existing single-pass prompting often yields inaccurate results. In this paper, we present SpecMind, a novel framework for postcondition generation that treats LLMs as interactive and exploratory reasoners rather than one-shot generators. SpecMind employs feedback-driven multi-turn prompting approaches, enabling the model to iteratively refine candidate postconditions by incorporating implicit and explicit correctness feedback, while autonomously deciding when to stop. This process fosters deeper code comprehension and improves alignment with true program behavior via exploratory attempts. Our empirical evaluation shows that SpecMind significantly outperforms state-of-the-art approaches in both accuracy and completeness of generated postconditions.

Cuong Chi Le, Minh V. T Pham, Tung Vu Duy +4

The University of Texas at Dallas · FPT Software AI Center · VinUniversity +1

LLM Self-Refinement LLM Prompting

Feb 23, 2026

Examining and Addressing Barriers to Diversity in LLM-Generated Ideas

Ideas generated by independent samples of humans tend to be more diverse than ideas generated from independent LLM samples, raising concerns that widespread reliance on LLMs could homogenize ideation and undermine innovation at a societal level. Drawing on cognitive psychology, we identify (both theoretically and empirically) two mechanisms undermining LLM idea diversity. First, at the individual level, LLMs exhibit fixation just as humans do, where early outputs constrain subsequent ideation. Second, at the collective level, LLMs aggregate knowledge into a unified distribution rather than exhibiting the knowledge partitioning inherent to human populations, where each person occupies a distinct region of the knowledge space. Through four studies, we demonstrate that targeted prompting interventions can address each mechanism independently: Chain-of-Thought (CoT) prompting reduces fixation by encouraging structured reasoning (only in LLMs, not humans), while ordinary personas (versus "creative entrepreneurs" such as Steve Jobs) improve knowledge partitioning by serving as diverse sampling cues, anchoring generation in distinct regions of the semantic space. Combining both approaches produces the highest idea diversity, outperforming humans. These findings offer a theoretically grounded framework for understanding LLM idea diversity and practical strategies for human-AI collaborations that leverage AI's efficiency without compromising the diversity essential to a healthy innovation ecosystem.

Yuting Deng, Melanie Brucks, Olivier Toubia

Columbia Business School

Diverse Text Generation LLM Prompting Human-AI Co-Creation

Feb 23, 2026

Structured Prompt Language: Declarative Context Management for LLMs

We present SPL (Structured Prompt Language), a declarative SQL-inspired language that treats large language models as generative knowledge bases and their context windows as constrained resources. SPL provides explicit WITH BUDGET/LIMIT token management, an automatic query optimizer, EXPLAIN transparency analogous to SQL's EXPLAIN ANALYZE, and native integration of retrieval-augmented generation (RAG) and persistent memory in a single declarative framework. SPL-flow extends SPL into resilient agentic pipelines with a three-tier provider fallback strategy (Ollama -> OpenRouter -> self-healing retry) fully transparent to the .spl script. Five extensions demonstrate the paradigm's breadth: (1) Text2SPL (multilingual NL->SPL translation); (2) Mixture-of-Models (MoM) routing that dispatches each PROMPT to a domain-specialist model at runtime; (3) Logical Chunking, an intelligent strategy for documents exceeding a single context window--expressed naturally through SPL's existing CTE syntax with no new constructs, decomposing a large query into a Map-Reduce pipeline that reduces attention cost from O(N^2) to O(N^2/k) and runs identically on cloud (parallel) or local hardware (sequential); (4) SPL-flow, a declarative agentic orchestration layer with resilient three-tier provider fallback; and (5) BENCHMARK for parallel multi-model comparison with automatic winner persistence. We provide a formal EBNF grammar, two pip-installable Python packages (spl-llm, spl-flow), and comparison against Prompty, DSPy, and LMQL. SPL reduces prompt boilerplate by 65% on average, surfaces a 68x cost spread across model tiers as a pre-execution signal, and runs the identical .spl script at $0.002 on OpenRouter or at zero marginal cost on a local Ollama instance--without modification.

Wen G. Gong

LLM Prompting LLM Context Management LLM Routing Knowledge Augmentation for Language Models

Feb 23, 2026

How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding

With the widespread adoption of large language models (LLMs) in natural language processing, prompt engineering and retrieval-augmented generation (RAG) have become mainstream to enhance LLMs' performance on complex tasks. However, LLMs generate outputs autoregressively, leading to inevitable output uncertainty. Since model performance is highly sensitive to prompt design, precise uncertainty measurement is crucial for reliable prompt optimization. For multi-class multiple-choice (understanding) tasks, conventional uncertainty measures (e.g., entropy) based on output probabilities treat all classes equally and ignore class prior differences in pretraining corpora. This failure to distinguish spurious confidence (from priors) from true certainty (from contextual understanding) results in poor confidence calibration. To address this, we propose Log-Scale Focal Uncertainty (LSFU), a first-token-based metric inspired by focal loss. LSFU incorporates label prior probabilities as a risk-modulation factor to suppress noise from high-frequency classes and emphasize risk for low-frequency long-tail classes, with a dynamic weighting mechanism unifying the measurement scale. Based on LSFU, we further propose the uncertainty-calibrated prompt optimization framework (UCPOF), which leverages the first token of model outputs to select high-quality exemplars and dynamically optimize prompts. Comprehensive evaluations show UCPOF improves average accuracy by 6.03% over few-shot baselines, surpasses always-on full RAG by 5.75% in overall average accuracy, and reduces the average retrieval trigger rate by 50.66%. By adaptively triggering RAG only for high-uncertainty samples, our framework significantly lowers computational costs while maintaining state-of-the-art performance.

Wei Chen, Guoyang Ju, Yuanyuan Qi

China Jiliang University, Hangzhou, China

LLM Input Optimization LLM Prompting LLM Uncertainty Estimation Language Model Calibration Efficient Language Model Inference Retrieval-Augmented Generation

Feb 19, 2026

Exploring LLMs for User Story Extraction from Mockups

User stories are one of the most widely used artifacts in the software industry to define functional requirements. In parallel, the use of high-fidelity mockups facilitates end-user participation in defining their needs. In this work, we explore how combining these techniques with large language models (LLMs) enables agile and automated generation of user stories from mockups. To this end, we present a case study that analyzes the ability of LLMs to extract user stories from high-fidelity mockups, both with and without the inclusion of a glossary of the Language Extended Lexicon (LEL) in the prompts. Our results demonstrate that incorporating the LEL significantly enhances the accuracy and suitability of the generated user stories. This approach represents a step forward in the integration of AI into requirements engineering, with the potential to improve communication between users and developers.

Diego Firmenich, Leandro Antonelli, Bruno Pazos +2

Departamento de Informática, Facultad de Ingeniería, Universidad Nacional de la Patagonia, Argentina · LIFIA, Facultad de Informática, Universidad Nacional de La Plata, Argentina · CAETI, Facultad de Tecnología Informática - Universidad Abierta Interamericana +3

Requirements Engineering Text Generation LLM Prompting Knowledge Augmentation for Language Models

Feb 18, 2026

Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

Prompting schemes such as Chain of Thought, Tree of Thoughts, and Graph of Thoughts can significantly enhance the reasoning capabilities of large language models. However, most existing schemes require users to define static, problem-specific reasoning structures that lack adaptability to dynamic or unseen problem types. Additionally, these schemes are often under-optimized in terms of hyperparameters, prompts, runtime, and prompting cost. To address these limitations, we introduce Framework of Thoughts (FoT)--a general-purpose foundation framework for building and optimizing dynamic reasoning schemes. FoT comes with built-in features for hyperparameter tuning, prompt optimization, parallel execution, and intelligent caching, unlocking the latent performance potential of reasoning schemes. We demonstrate FoT's capabilities by implementing three popular schemes--Tree of Thoughts, Graph of Thoughts, and ProbTree--within FoT. We empirically show that FoT enables significantly faster execution, reduces costs, and achieves better task scores through optimization. We release our codebase to facilitate the development of future dynamic and efficient reasoning schemes.

Felix Fricke, Simon Malberg, Georg Groh

School of Computation, Information and Technology Technical University of Munich

Inference-Time Optimization Tree of Thoughts LLM Prompting Efficient Language Model Inference LLM Reasoning

Feb 17, 2026

Transforming GenAI Policy to Prompting Instruction: An RCT of Scalable Prompting Interventions in a CS1 Course

Despite universal GenAI adoption, students cannot distinguish task performance from actual learning and lack skills to leverage AI for learning, leading to worse exam performance when AI use remains unreflective. Yet few interventions teaching students to prompt AI as a tutor rather than solution provider have been validated at scale through randomized controlled trials (RCTs). To bridge this gap, we conducted a semester-long RCT (N=979) with four ICAP framework-based instructional conditions varying in engagement intensity with a pre-test, immediate and delayed post-test and surveys. Mixed methods analysis results showed: (1) All conditions significantly improved prompting skills, with gains increasing progressively from Condition 1 to Condition 4, validating ICAP's cognitive engagement hierarchy; (2) for students with similar pre-test scores, higher learning gain in immediate post-test predict higher final exam score, though no direct between-group differences emerged; (3) Our interventions are suitable and scalable solutions for diverse educational contexts, resources and learners. Together, this study makes empirical and theoretical contributions: (1) theoretically, we provided one of the first large-scale RCTs examining how cognitive engagement shapes learning in prompting literacy and clarifying the relationship between learning-oriented prompting skills and broader academic performance; (2) empirically, we offered timely design guidance for transforming GenAI classroom policies into scalable, actionable prompting literacy instruction to advance learning in the era of Generative AI.

Ruiwei Xiao, Runlong Ye, Xinying Hou +4

Carnegie Mellon University, Pittsburgh, PA, United States · University of Toronto, Toronto, ON, Canada · University of Michigan, Ann Arbor, MI, United States +1

Generative AI in Education AI Literacy LLM Prompting Computer Science Education

Feb 16, 2026

LLMStructBench: Benchmarking Large Language Model Structured Data Extraction

We present LLMStructBench, a novel benchmark for evaluating Large Language Models (LLMs) on extracting structured data and generating valid JavaScript Object Notation (JSON) outputs from natural-language text. Our open dataset comprises diverse, manually verified parsing scenarios of varying complexity and enables systematic testing across 22 models and five prompting strategies. We further introduce complementary performance metrics that capture both token-level accuracy and document-level validity, facilitating rigorous comparison of model, size, and prompting effects on parsing reliability. In particular, we show that choosing the right prompting strategy is more important than standard attributes such as model size. This especially ensures structural validity for smaller or less reliable models but increase the number of semantic errors. Our benchmark suite is an step towards future research in the area of LLM applied to parsing or Extract, Transform and Load (ETL) applications.

Sönke Tenckhoff, Mario Koddenbrock, Erik Rodner

KI-Werkstatt / FB2, University of Applied Sciences Berlin

LLM Information Extraction Document Parsing Benchmarks Structured Output Generation LLM Evaluation LLM Prompting

Feb 16, 2026

Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought

Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks, exhibiting emergent properties such as semantic prompt comprehension, In-Context Learning (ICL), and Chain-of-Thought (CoT) reasoning. Despite their empirical success, the theoretical mechanisms driving these phenomena remain poorly understood. This study dives into the foundations of these observations by addressing three critical questions: (1) How do LLMs accurately decode prompt semantics despite being trained solely on a next-token prediction objective? (2) Through what mechanism does ICL facilitate performance gains without explicit parameter updates? and (3) Why do intermediate reasoning steps in CoT prompting effectively unlock capabilities for complex, multi-step problems? Our results demonstrate that, through the autoregressive process, LLMs are capable of exactly inferring the transition probabilities between tokens across distinct tasks using provided prompts. We show that ICL enhances performance by reducing prompt ambiguity and facilitating posterior concentration on the intended task. Furthermore, we find that CoT prompting activates the model's capacity for task decomposition, breaking complex problems into a sequence of simpler sub-tasks that the model has mastered during the pretraining phase. By comparing their individual error bounds, we provide novel theoretical insights into the statistical superiority of advanced prompt engineering techniques.

Yuling Jiao, Yanming Lai, Huazhen Lin +3

School of Artificial Intelligence, Wuhan University · National Center for Applied Mathematics in Hubei, Wuhan University · Hubei Key Laboratory of Computational Science, Wuhan University +6

LLM Prompting In-Context Learning CoT Reasoning Implicit Reasoning in Language Models Task Decomposition

Feb 4, 2026

Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on reliability. We evaluate three task-equivalent prompting regimes: Direct, Assistive, and Incremental, across different model scales and multi-hop QA benchmarks. We find that although accuracy gains from decomposition diminish in frontier models, disagreements between prompting regimes remain highly indicative of potential errors. Because factual knowledge is typically stable while hallucinations are stochastic, cross-regime agreement provides a precise signal of internal uncertainty. We leverage this signal to implement a training-free abstention policy that requires no retrieval or fine-tuning. Our results show that disagreement-based abstention outperforms standard uncertainty baselines as an error detector, improving both F1 and AUROC across settings. This demonstrates that decomposition-based prompting can serve as a practical diagnostic probe for model reliability in closed-book QA.

Dhruv Madhwal, Lyuxin David Zhang, Dan Roth +2

Arizona State University · University of Pennsylvania · Oracle AI

LLM Prompting Question Decomposition LLM Reliability LLM Hallucination Detection LLM Uncertainty Estimation LLM Abstention

Feb 2, 2026

Measuring Pragmatic Influence in Large Language Model Instructions

It is not only what we ask large language models (LLMs) to do that matters, but also how we ask them. Phrases like This is urgent'' or As your supervisor'' can shift model behavior without altering task content. We study this effect as pragmatic framing, contextual cues that shape directive interpretation rather than task specification. While prior work exploits such cues for prompt optimization or probes them as security vulnerabilities, pragmatic framing itself has received comparatively little attention as a target of controlled measurement in instruction following. To support its systematic study as a measurable property, we introduce a framework that combines three components: directive-framing decomposition separating framing context from task specification; a taxonomy organizing 400 instantiations of framing into 13 strategies across 4 mechanism clusters; and priority-based measurement that quantifies influence through observable shifts in directive prioritization. Evaluating five open-weight LLMs across different families and scales, we find that pragmatic framing produces systematic shifts in directive prioritization, and the effectiveness ranking of different strategies proves highly consistent across models. This reveals that susceptibility to pragmatic framing is a structured behavioral property of instruction-tuned systems. Measuring this susceptibility is a prerequisite for any deliberate response to it, and this work provides the framework to do so.

Yilin Geng, Omri Abend, Eduard Hovy +1

University of Melbourne · Hebrew University of Jerusalem

LLM Evaluation LLM Prompting Instruction Following Framing Effects in Language Models

Jan 5, 2026

Not All Needles Are Found: How Fact Distribution and Don't Make It Up Prompts Shape Retrieval, Reasoning, and Hallucination in Long-Context LLMs

As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctuates significantly depending on how information is distributed in real-world corpora. We investigate how fact placement, corpus-level distributions, and anti-hallucination ("Don't Make It Up") prompts influence model behavior by introducing a model-agnostic extended needle-in-a-haystack benchmark designed for scalability, which we apply to evaluate Gemini-2.5-flash, ChatGPT-5-mini, Claude-4.5-haiku, and Deepseek-v3.2-chat. Unlike prior work, we separately evaluate literal extraction, logical inference, and hallucination risk. We identify two critical failure modes: Distributional Collapse, where performance degrades significantly when evidence is dispersed; and a Safety Tax, where anti-hallucination prompts cause over-conservative refusal of present facts and evidence, sharply reducing accuracy. Our results suggest that many failures stem from ineffective context utilization, as models struggle to prioritize relevant information even when it is present. These findings highlight the need for model-specific robustness and effective context management to ensure reliable deployment in long-horizon agentic workflows.

Amirali Ebrahimzadeh, Seyyed M. Salili

Department of Electrical Engineering & Computer Science, University of Michigan, Ann Arbor, MI 48109, USA · Independent Researcher, Ann Arbor, MI 48106, USA

Long-Context Retrieval LLM Hallucination Mitigation Language Model Safety Evaluation LLM Prompting Hallucination in Language Models LLM Reliability+1

Oct 20, 2025

Rethinking On-policy Optimization for Query Augmentation

Recent advances in large language models (LLMs) have led to a surge of interest in query augmentation for information retrieval (IR). Two main approaches have emerged. The first prompts LLMs to generate answers or pseudo-documents that serve as new queries, relying purely on the model's parametric knowledge or contextual information. The second applies reinforcement learning (RL) to fine-tune LLMs for query rewriting, directly optimizing retrieval metrics. While having respective advantages and limitations, the two approaches have not been compared under consistent experimental conditions. In this work, we present the first systematic comparison of prompting-based and RL-based query augmentation across diverse benchmarks, including evidence-seeking, ad hoc, and tool retrieval. Our key finding is that under a compute-aware comparison setting, simple, training-free query augmentation often performs on par with, or even surpasses, more expensive RL-based counterparts, especially when using powerful LLMs. Motivated by this discovery, we introduce a novel hybrid method, On-policy Pseudo-document Query Expansion (OPQE), in which the LLM policy learns to generate a pseudo-document that maximizes retrieval performance, rather than rewriting the query, thus merging the flexibility and generative structure of prompting with the targeted optimization of RL. We show OPQE outperforms both standalone prompting and RL-based rewriting, demonstrating that a synergistic approach yields the best results. We open source our implementation to facilitate reproducibility.

Zhichao Xu, Shengyao Zhuang, Xueguang Ma +6

University of Utah · 2The University of Queensland · University of Waterloo +5

RL for Language Models LLM Prompting Information Retrieval Query Expansion

Oct 1, 2025

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

Post-training alignment often reduces LLM diversity, leading to a phenomenon known as mode collapse. Unlike prior work that attributes this effect to algorithmic limitations, we identify a fundamental, pervasive data-level driver: typicality bias in preference data, whereby annotators systematically favor familiar text as a result of well-established findings in cognitive psychology. We formalize this bias theoretically, verify it on preference datasets empirically, and show that it plays a central role in mode collapse. Motivated by this analysis, we introduce Verbalized Sampling, a simple, training-free prompting strategy to circumvent mode collapse. VS prompts the model to verbalize a probability distribution over a set of responses (e.g., "Generate 5 jokes about coffee and their corresponding probabilities"). Comprehensive experiments show that VS significantly improves performance across creative writing (poems, stories, jokes), dialogue simulation, open-ended QA, and synthetic data generation, without sacrificing factual accuracy and safety. For instance, in creative writing, VS increases diversity by 1.6-2.1x over direct prompting. We further observe an emergent trend that more capable models benefit more from VS. In sum, our work provides a new data-centric perspective on mode collapse and a practical inference-time remedy that helps unlock pre-trained generative diversity.

Jiayi Zhang, Simon Yu, Derek Chong +4

Northeastern University · Stanford University · West Virginia University

LLM Prompting Model Collapse Diverse Text Generation Language Model Post-Training Output Diversity in Language Models

Aug 19, 2025

Towards AI-Assisted Research Writing: Benchmarking LLMs for AI/ML Introduction Generation

As researchers increasingly adopt LLMs as writing assistants, generating high-quality research paper introductions remains both challenging and essential. We introduce Scientific Introduction Generation (SciIG), a task that evaluates LLMs' ability to produce coherent introductions from titles, abstracts, and related works. Curating new datasets from NAACL 2025 and ICLR 2025 papers, we assess five state-of-the-art models, including both open-source (DeepSeek-v3, Gemma-3-12B, LLaMA 4-Maverick, MistralAI Small 3.1) and closed-source GPT-4o systems, across multiple dimensions: lexical overlap, semantic similarity, content coverage, faithfulness, consistency, citation correctness, and narrative quality. Our comprehensive framework combines automated metrics with LLM-as-a-judge evaluations. Results demonstrate LLaMA-4 Maverick's superior performance on most metrics, particularly in semantic similarity and faithfulness. Moreover, three-shot prompting consistently outperforms fewer-shot approaches. These findings provide practical insights into developing effective research writing assistants and set realistic expectations for LLM-assisted academic writing. To foster re- producibility and future research, we publicly release all code and datasets.

Krishna Garg, Firoz Shaik, Sambaran Bandyopadhyay +1

University of Illinois Chicago · Adobe Research

LLM Evaluation Language Model Generation Evaluation LLM Prompting AI-Assisted Scientific Research Generative AI Evaluation

Aug 8, 2025

Scaling Personality Control in LLMs with Big Five Scaler Prompts

We present Big5-Scaler, a prompt-based framework for conditioning large language models (LLMs) with controllable Big Five personality traits. By embedding numeric trait values into natural language prompts, our method enables fine-grained personality control without additional training. We evaluate Big5-Scaler across trait expression, dialogue generation, and human trait imitation tasks. Results show that it induces consistent and distinguishable personality traits across models, with performance varying by prompt type and scale. Our analysis highlights the effectiveness of concise prompts and lower trait intensities, providing a efficient approach for building personality-aware dialogue agents.

Gunhee Cho, Yun-Gyung Cheong

Sungkyunkwan University, South Korea

Persona-Conditioned Generation Controllable Text Generation Personality Modeling in Language Models LLM Prompting

Aug 6, 2025

Experimental Analysis of Productive Interaction Strategy with ChatGPT: User Study on Function and Project-level Code Generation Tasks

The application of Large Language Models (LLMs) is growing in the productive completion of Software Engineering tasks. Yet, studies investigating productive prompting techniques often employed a limited problem space, focusing primarily on well-known prompting patterns and targeting function-level SE practices. We identify significant gaps in real-world workflows that involve complexities beyond class-level (e.g., multi-class dependencies) and different features that can impact Human-LLM Interaction (HLI) processes in code generation. To address these issues, we designed an experiment to comprehensively analyze HLI features related to code generation productivity. Our study presents two project-level benchmark tasks that extend beyond function-level evaluations. We conducted a user study with 36 participants from diverse backgrounds, asking them to solve the assigned tasks by interacting with the GPT assistant using specific prompting patterns. We also examined participants' experiences and behavioral features during interactions by analyzing screen recordings and GPT chat logs. Our empirical investigation, based on statistical guidance, revealed (1) that three out of 15 HLI features emerged as consistently supported factors for productivity; (2) five primary guidelines for enhancing productivity for HLI processes; and (3) a taxonomy of 29 runtime and logic errors that can occur during HLI processes, along with suggested mitigation plans.

Sangwon Hyun, Hyunjun Kim, Jinhyuk Jang +2

Adelaide University, Adelaide, SA, Australia · Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

LLM Prompting Code Generation Code Generation Evaluation Human-AI Collaboration LLM Code Generation

Aug 1, 2025

Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications

The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice. This has catalyzed a shift from single-step answer generation to the development of LLMs explicitly designed for medical reasoning. This paper provides the first systematic review of this emerging field. We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies (e.g., supervised fine-tuning, reinforcement learning) and test-time mechanisms (e.g., prompt engineering, multi-agent systems). We analyze how these techniques are applied across different data modalities (text, image, code) and in key clinical applications such as diagnosis, education, and treatment planning. Furthermore, we survey the evolution of evaluation benchmarks from simple accuracy metrics to sophisticated assessments of reasoning quality and visual interpretability. Based on an analysis of 60 seminal studies from 2022-2025, we conclude by identifying critical challenges, including the faithfulness-plausibility gap and the need for native multimodal reasoning, and outlining future directions toward building efficient, robust, and sociotechnically responsible medical AI.

Zizhan Ma, Wenxuan Wang, Meidan Ding +7

The Chinese University of Hong Kong · Renmin University of China · Shenzhen University +3

LLM Prompting RL for Language Model Reasoning Multimodal Reasoning Clinical Language Model Evaluation Medical LLMs

Jul 29, 2025

Introducing HALC: A general pipeline for the systematic and reliable construction of prompts for automated coding with LLMs in the computational social sciences

LLMs are seeing widespread use for task automation, including automated coding in the social sciences. However, even though researchers have proposed different prompting strategies, their effectiveness varies across LLMs and tasks. Often trial and error practices are still widespread. Our study aims to fill this gap and evaluate how LLMs can be used in a systematic and transparent way to produce reliable codings in content analyses. We propose HALC-a general pipeline that allows for the systematic and reliable construction of prompts for any given coding task and model. We develop this pipeline based on current literature and findings of a prestudy investigating consistency and influencing factors of LLM codings. We also apply HALC on two other datasets covering different thematic contexts, document types, languages, and coding units to test its applicability. Based on more than three million LLM requests, our results demonstrate that the pipeline is capable of identifying prompts for reliable codings in different settings. We also discuss shortcomings and further potential for development.

Andreas Reich, Claudia Thoms, Tobias Schrimpf

LLM Prompting LLM-Assisted Annotation Computational Social Science

Jun 28, 2025

Structured Prompting and Automated Evaluation in Fixed Synthetic Japanese-Language Counseling Dialogues

Large language models (LLMs) may support counseling training, yet evidence from Japanese-language interactions and automated quality ratings remains limited. We examined 18 fixed Japanese-language counseling transcripts generated through artificial intelligence (AI)-to-AI interactions under three counselor conditions: GPT-minimal (GPT-4-turbo with a minimal role instruction), GPT-SMDP (GPT-4-turbo with the Structured Multi-step Dialogue Prompt [SMDP]), and Claude-SMDP (Claude-3-Opus with SMDP). Fifteen counseling experts rated transcripts on four adapted global scales from the Motivational Interviewing Treatment Integrity coding manual and an overall-quality item; three newer LLMs independently rated the same transcripts in three iterations. In this fixed stimulus set, SMDP-condition dialogues received higher expert ratings for cultivating change talk, partnership, empathy, and overall quality than GPT-minimal dialogues; the two SMDP counselor models did not differ. LLM ratings were reproducible but generally more lenient than expert-reference ratings, particularly for softening sustain talk and overall quality. Simulated-client naturalness was below the scale midpoint. These findings provide an expert-referenced benchmark for Japanese-language AI counseling simulations and show that reproducible LLM ratings should not be treated as calibrated counseling-quality evidence without expert validation. This study does not test clinical effectiveness or human-client outcomes.

Keita Kiuchi, Yoshikazu Fujimoto, Hideyuki Goto +5

Japan National Institute of Occupational Safety and Health, Kanagawa, Japan · Kaze To Taiyo, Tokyo, Japan · Saga Occupational Health Association, Saga, Japan +5

Mental Health Counseling LLM-as-a-Judge Emotional Support Conversation LLM Prompting Clinical Language Model Evaluation

Jun 25, 2025

$π$ -CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering

Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often falling into circular reasoning patterns or deviating from the logical path entirely. This limitation is particularly acute in retrieval-augmented generation (RAG) settings, where obtaining the right context is critical. We introduce Prolog-Initialized Chain-of-Thought (

π

-CoT), a novel prompting strategy that combines logic programming's structural rigor with language models' flexibility.

π

-CoT reformulates multi-hop questions into Prolog queries decomposed as single-hop sub-queries. These are resolved sequentially, producing intermediate artifacts, with which we initialize the subsequent CoT reasoning procedure. Extensive experiments demonstrate that

π

-CoT matches or outperforms standard RAG and in-context CoT on multi-hop question-answering benchmarks, with the largest gains on questions for which retrieval surfaces the necessary evidence.

Chao Wan, Albert Gong, Mihir Mishra +3

Cornell University.

Multi-Hop QA LLM Prompting LLM Reasoning CoT Reasoning Retrieval-Augmented Generation