Related papers: ChainForge: A Visual Toolkit for Prompt Engineerin…
Large Language models (LLMs) have demonstrated significant potential in text-to-SQL reasoning tasks, yet a substantial performance gap persists between existing open-source models and their closed-source counterparts. In this paper, we…
Large Language Models (LLMs) have demonstrated impressive capabilities in automated code generation but frequently produce code that fails formal verification, an essential requirement for hardware and safety-critical domains. To overcome…
Developing effective prompts demands significant cognitive investment to generate reliable, high-quality responses from Large Language Models (LLMs). By deploying case-specific prompt engineering techniques that streamline frequently…
Materials discovery and design are essential for advancing technology across various industries by enabling the development of application-specific materials. Recent research has leveraged Large Language Models (LLMs) to accelerate this…
Large Language Models (LLMs) have emerged as a promising alternative to traditional static program analysis methods, such as symbolic execution, offering the ability to reason over code directly without relying on theorem provers or SMT…
Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to propose multiple tokens for batched verification. However,…
With the advent of large language models (LLMs) and multimodal large language models (MLLMs), the potential of retrieval-augmented generation (RAG) has attracted considerable research attention. Various novel algorithms and models have been…
Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning without automated experimental verification. We propose MIND, an LLM-driven framework for…
The creation of systematic literature reviews (SLR) is critical for analyzing the landscape of a research field and guiding future research directions. However, retrieving and filtering the literature corpus for an SLR is highly…
Large language models (LLMs) have a substantial capacity for high-level analogical reasoning: reproducing patterns in linear text that occur in their training data (zero-shot evaluation) or in the provided context (few-shot in-context…
Large language models (LLM) are perceived to offer promising potentials for automating security tasks, such as those found in security operation centers (SOCs). As a first step towards evaluating this perceived potential, we investigate the…
Hidden LLM prompts have appeared in online documents with increasing frequency. Their goal is to trigger indirect prompt injection attacks while remaining undetected from human oversight, to manipulate LLM-powered automated document…
Large Language Models (LLMs), such as \texttt{ChatGPT}, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response…
Prompt engineering is a technique that involves augmenting a large pre-trained model with task-specific hints, known as prompts, to adapt the model to new tasks. Prompts can be created manually as natural language instructions or generated…
In the current media landscape, understanding the framing of information is crucial for critical consumption and informed decision making. Framing analysis is a valuable tool for identifying the underlying perspectives used to present…
The analysis of students' emotions and behaviors is crucial for enhancing learning outcomes and personalizing educational experiences. Traditional methods often rely on intrusive visual and physiological data collection, posing privacy…
Large Language Models (LLMs) can aid synthesis planning in chemistry, but standard prompting methods often yield hallucinated or outdated suggestions. We study LLM interactions with a reaction knowledge graph by casting reaction path…
Existing large language models (LLMs) are advancing rapidly and produce outstanding results in image generation tasks, yet their content safety checks remain vulnerable to prompt-based jailbreaks. Through preliminary testing on platforms…
Large language models (LLMs) are a new and powerful tool for a wide span of applications involving natural language and demonstrate impressive code generation abilities. The goal of this work is to automatically generate tests and use these…
While different language models are ubiquitous in NLP, it is hard to contrast their outputs and identify which contexts one can handle better than the other. To address this question, we introduce LMdiff, a tool that visually compares…