Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) demonstrate exceptional instruct-following ability to complete downstream tasks. |
| Approach: | They propose a black-box combinatorial optimization framework that iteratively improves lexical choices in prompts by a search strategy related to word influence. |
| Outcome: | The proposed framework recovers the model's ability to instruct-follow and solve downstream tasks even when the variations are imperceptible to humans. |
Similar Papers
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)
Copied to clipboard
Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu
| Challenge: | Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations. |
| Approach: | They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability. |
| Outcome: | The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants . |
Exploring the Sensitivity of LLMs’ Decision-Making Capabilities: Insights from Prompt Variations and Hyperparameters (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Prior studies have compared the decision-making abilities of large language models with those of humans from a psychological perspective. |
| Approach: | They examine LLMs' performance on the Horizon decision-making task studied by Binz and Schulz (2023) they observe that the decision- making abilities fluctuate based on input prompts and temperature settings. |
| Outcome: | The results show that LLMs display a human-like exploration–exploitation tradeoff after simple adjustments to the prompt. |
The language of prompting: What linguistic properties make a prompt successful? (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that pretraining and instruction-tuned LLMs can achieve impressive performance on a multitude of tasks. |
| Approach: | They propose to use a standard for prompting research to better understand linguistic properties of LLMs. |
| Outcome: | The proposed standard would improve the performance of pre-trained and instruction-tuned LLMs on a multitude of tasks. |
What Did I Do Wrong? Quantifying LLMs’ Sensitivity and Consistency to Prompt Engineering (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have significantly improved productivity in a number of routine tasks. |
| Approach: | They propose two metrics for classification tasks, namely *sensitivity* and *consistency*, which are complementary to task performance. |
| Outcome: | The proposed metrics are complementary to task performance and can be used to guide prompt engineering and obtain LLMs that balance robustness and performance. |
POSIX: A Prompt Sensitivity Index For Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are sensitive to minor variations in prompts, such as spelling errors, alteration of wording or the prompt template. |
| Approach: | They propose a PrOmpt Sensitivity IndeX to measure prompt sensitivity . they use this to compare prompt sensitability of various open source LLMs . |
| Outcome: | The proposed method can measure and compare prompt sensitivity of open source LLMs. |
SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization (2025.acl-long)
Copied to clipboard
Wendi Cui, Jiaxin Zhang, Zhuohang Li, Hao Sun, Damien Lopez, Kamalika Das, Bradley A. Malin, Sricharan Kumar
| Challenge: | Existing approaches separate the optimization of prompt instructions and in-context learning examples, leading to incohesive, suboptimal results. |
| Approach: | They propose a framework that refines both prompt instructions and in-context learning examples. |
| Outcome: | The proposed framework outperforms state-of-the-art prompt optimization methods on 35 benchmark tasks. |
Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | a high prompt sensitivity has been widely accepted as a core limitation of large language models . a recent study suggests that prompt senescence may be an artifact of evaluation processes . |
| Approach: | They examine whether prompt sensitivity is an inherent weakness or an artifact of evaluation . they find that heuristic evaluation methods overlook semantically correct responses . large language models have achieved remarkable success across a wide range of tasks . |
| Outcome: | The proposed model is more robust to prompt templates than previously thought . the authors show that prompt sensitivity may be an artifact of evaluation rather than a flaw . |
ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent research has neglected instances-level prompt variations and their implications on subjective evaluations. |
| Approach: | They propose a framework to evaluate and comprehend prompt sensitivity in large language models. |
| Outcome: | The proposed framework evaluates and comprehends prompt sensitivity in large language models. |
Tokenization is Sensitive to Language Variation (2025.findings-acl)
Copied to clipboard
| Challenge: | Variation in language is often linked to regional, social, and contextual factors. |
| Approach: | They propose a method to estimate tokenizer impact on downstream LLM performance . they pre-train BERT models with the popular Byte-Pair Encoding algorithm . |
| Outcome: | The proposed model improves on Rényi efficiency and other metrics on language variation. |
The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used to label data across many domains and for myriad tasks. |
| Approach: | They ask large language models to label data using a series of decisions by practitioners . they find that even the smallest perturbations can change the LLM's answer . |
| Outcome: | The proposed model can be used to quickly get a response for arbitrary tasks. |