Our source code for our work is available here.

As language models (LMs) are increasingly adopted across domains, high-quality benchmarking frameworks that accurately estimate performance are essential for guiding deployment decisions. While frameworks such as Holistic Evaluation of Language Models (HELM) enable broad evaluation across tasks, they often rely on fixed prompts that fail to generalize across LMs, yielding unrepresentative performance estimates. Unless we approximate each LM's ceiling (maximum achievable via changes to the prompt), we risk underestimating performance. Declarative prompting frameworks, such as DSPy, offer a scalable alternative to manual prompt engineering by crafting structured prompts that can be optimized per task. However, such frameworks have not been systematically evaluated across established benchmarks. We present a reproducible DSPy+HELM framework that introduces structured prompting methods which elicit reasoning, enabling more accurate LM benchmarking. Using four prompting methods, we evaluate four frontier LMs across seven benchmarks (general/medical domain) against existing HELM baseline scores. We find that without structured prompting: (i) HELM underestimates LM performance (by 4% average), (ii) performance estimates vary more across benchmarks ($+$2% standard deviation), (iii) performance gaps are misrepresented (leaderboard rankings flip on 3/7 benchmarks), and (iv) introducing chain-of-thought reduces LM sensitivity to prompt design (smaller $Δ$ across prompts). To our knowledge, this is the first benchmarking study to systematically integrate structured prompting into an established evaluation framework, demonstrating how scalable performance-ceiling approximation yields more robust, decision-useful benchmarks. We open-source (i) DSPy+HELM Integration (https://github.com/stanford-crfm/helm/pull/3893) and (ii) Prompt Optimization Pipeline (https://github.com/StanfordMIMI/dspy-helm).

With the rapid expansion of unstructured clinical texts in electronic health records (EHRs), clinical named entity recognition (NER) has become a crucial technique for extracting medical information. However, traditional supervised models such as CRF and BioClinicalBERT suffer from high annotation costs. Although zero-shot NER based on large language models (LLMs) reduces the dependency on labeled data, challenges remain in aligning example selection with task granularity and effectively integrating prompt design with self-improvement frameworks. To address these limitations, we propose OEMA, a novel zero-shot clinical NER framework based on multi-agent collaboration. OEMA consists of three core components: (1) a self-annotator that autonomously generates candidate examples; (2) a discriminator that leverages SNOMED CT to filter token-level examples by clinical relevance; and (3) a predictor that incorporates entity-type descriptions to enhance inference accuracy. Experimental results on two benchmark datasets, MTSamples and VAERS, demonstrate that OEMA achieves state-of-the-art performance under exact-match evaluation. Moreover, under related-match criteria, OEMA performs comparably to the supervised BioClinicalBERT model while significantly outperforming the traditional CRF method. OEMA improves zero-shot clinical NER, achieving near-supervised performance under related-match criteria. Future work will focus on continual learning and open-domain adaptation to expand its applicability in clinical NLP.

We focus on native performance of existing LLMs, without training interventions.

In-context learning (ICL) enables Large Language Models (LLMs) to generate predictions based on prompts without additional fine-tuning. While prompt engineering has been widely studied, the impact of role design within prompts remains underexplored. This study examines the influence of role configurations in zero-shot and few-shot learning scenarios using GPT-3.5 and GPT-4o from OpenAI and Llama2-7b and Llama2-13b from Meta. We evaluate the models' performance across datasets, focusing on tasks like sentiment analysis, text classification, question answering, and math reasoning. Our findings suggest the potential of role-based prompt structuring to enhance LLM performance.

Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers often rely on LLMs to assess whether system code implementation satisfy task requirements, thereby enhancing code robustness and accuracy. However, it remains unclear whether LLMs can reliably determine whether the code complies fully with the given task descriptions, which is usually natural language specifications. In this paper, we uncover a systematic failure of LLMs in evaluating whether code aligns with natural language requirements. Specifically, with widely used benchmarks, we employ unified prompts to judge code correctness. Our results reveal that LLMs frequently misclassify correct code implementations as either ``not satisfying requirements'' or containing potential defects. Surprisingly, more complex prompting, especially when leveraging prompt engineering techniques involving explanations and proposed corrections, leads to higher misjudgment rate, which highlights the critical reliability issues in using LLMs as code review assistants. We further analyze the root causes of these misjudgments, and propose two improved prompting strategies for mitigation. For the first time, our findings reveals unrecognized limitations in LLMs to match code with requirements. We also offer novel insights and practical guidance for effective use of LLMs in automated code review and task-oriented agent scenarios.

This paper investigates how prompt engineering techniques impact both accuracy and confidence elicitation in Large Language Models (LLMs) applied to medical contexts. Using a stratified dataset of Persian board exam questions across multiple specialties, we evaluated five LLMs - GPT-4o, o3-mini, Llama-3.3-70b, Llama-3.1-8b, and DeepSeek-v3 - across 156 configurations. These configurations varied in temperature settings (0.3, 0.7, 1.0), prompt styles (Chain-of-Thought, Few-Shot, Emotional, Expert Mimicry), and confidence scales (1-10, 1-100). We used AUC-ROC, Brier Score, and Expected Calibration Error (ECE) to evaluate alignment between confidence and actual performance. Chain-of-Thought prompts improved accuracy but also led to overconfidence, highlighting the need for calibration. Emotional prompting further inflated confidence, risking poor decisions. Smaller models like Llama-3.1-8b underperformed across all metrics, while proprietary models showed higher accuracy but still lacked calibrated confidence. These results suggest prompt engineering must address both accuracy and uncertainty to be effective in high-stakes medical tasks.

Legal contracts possess an inherent, semantically vital structure (e.g., sections, clauses) that is crucial for human comprehension but whose impact on LLM processing remains under-explored. This paper investigates the effects of explicit input text structure and prompt engineering on the performance of GPT-4o and GPT-4.1 on a legal question-answering task using an excerpt of the CUAD. We compare model exact-match accuracy across various input formats: well-structured plain-text (human-generated from CUAD), plain-text cleaned of line breaks, extracted plain-text from Azure OCR, plain-text extracted by GPT-4o Vision, and extracted (and interpreted) Markdown (MD) from GPT-4o Vision. To give an indication of the impact of possible prompt engineering, we assess the impact of shifting task instructions to the system prompt and explicitly informing the model about the structured nature of the input. Our findings reveal that GPT-4o demonstrates considerable robustness to variations in input structure, but lacks in overall performance. Conversely, GPT-4.1's performance is markedly sensitive; poorly structured inputs yield suboptimal results (but identical with GPT-4o), while well-structured formats (original CUAD text, GPT-4o Vision text and GPT-4o MD) improve exact-match accuracy by ~20 percentage points. Optimizing the system prompt to include task details and an advisory about structured input further elevates GPT-4.1's accuracy by an additional ~10-13 percentage points, with Markdown ultimately achieving the highest performance under these conditions (79 percentage points overall exact-match accuracy). This research empirically demonstrates that while newer models exhibit greater resilience, careful input structuring and strategic prompt design remain critical for optimizing the performance of LLMs, and can significantly affect outcomes in high-stakes legal applications.