Related papers: PromptPort: A Reliability Layer for Cross-Model St…
The rapid advancement of Large Language Models (LLMs) in the realm of mathematical reasoning necessitates comprehensive evaluations to gauge progress and inspire future directions. Existing assessments predominantly focus on problem-solving…
LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure…
Bias audits of large language models now operate within governance frameworks such as the EU AI Act, making benchmark reliability a security concern in its own right. Many current benchmarks, however, collapse bias into a single scalar from…
Motivated by the high costs of using black-box Large Language Models (LLMs), we introduce a novel prompt compression paradigm, under which we use smaller LLMs to compress inputs for the larger ones. We present the first comprehensive…
Prompt-based methods have been used extensively across NLP to build zero- and few-shot label predictors. Many NLP tasks are naturally structured: that is, their outputs consist of multiple labels which constrain each other. Annotating data…
Instruction-tuned large language models (LLMs) employ structured templates, such as role markers and special tokens, to enforce format consistency during inference. However, we identify a critical limitation of such formatting: it induces a…
Large language models (LLMs) have demonstrated remarkable proficiency in machine translation (MT), even without specific training on the languages in question. However, translating rare words in low-resource or domain-specific contexts…
Large Language Models (LLMs) are gaining traction as a method to generate consensus statements and aggregate preferences in digital democracy experiments. Yet, LLMs could introduce critical vulnerabilities in these systems. Here, we examine…
Despite the remarkable success of Large Language Models (LLMs), the massive size poses significant deployment challenges, particularly on resource-constrained hardware. While existing LLM compression methods focus on quantization, pruning…
The advancements in the domain of LLMs in recent years have surprised many, showcasing their remarkable capabilities and diverse applications. Their potential applications in various real-world scenarios have led to significant research on…
The rapid compression of large vision-language models (VLMs) for edge deployment raises an underexplored question: do compact models fail differently, not merely more often? This study compares a 7-billion-parameter quantised VLM…
The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness to prompts. In response to this vital need, we introduce PromptRobust, a robustness…
In this paper, we propose a novel prompting approach aimed at enhancing the ability of Large Language Models (LLMs) to generate accurate Python code. Specifically, we introduce a prompt template designed to improve the quality and…
Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection…
Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…
Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…
We present a controlled benchmark evaluating three LLMs -- Claude Sonnet 4.5, Gemini 2.5 Pro, and GPT-3.5 Turbo -- across four prompt formats (from concise narrative to structured JSON with explicit iteration trace) on Gauss--Seidel AC…
Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these…
With the proliferation of LLM-integrated applications such as GPT-s, millions are deployed, offering valuable services through proprietary instruction prompts. These systems, however, are prone to prompt extraction attacks through…
Code generation models are widely used in software development, yet their sensitivity to prompt phrasing remains under-examined. Identical requirements expressed with different emotions or communication styles can yield divergent outputs,…