Related papers: Logicbreaks: A Framework for Understanding Subvers…

In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (LLMs). Despite rigorous pretraining and finetuning focused on…

We introduce a modular prompting framework that supports safer and more adaptive use of large language models (LLMs) across dynamic, user-centered tasks. Grounded in human learning theory, particularly the Zone of Proximal Development…

Large Language Models (LLMs) are reported to hold undesirable attestation bias on inference tasks: when asked to predict if a premise P entails a hypothesis H, instead of considering H's conditional truthfulness entailed by P, LLMs tend to…

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

A central goal of cognitive science is to provide a computationally explicit account of both the structure of the mind and its development: what are the primitive representational building blocks of cognition, what are the rules via which…

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation…

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and…

The design of safety-critical agents based on large language models (LLMs) requires more than simple prompt engineering. This paper presents a comprehensive information-theoretic analysis of how rule encodings in system prompts influence…

In the U.S. judicial system, a widespread approach to legal interpretation entails assessing how a legal text would be understood by an `ordinary' speaker of the language. Recent scholarship has proposed that legal practitioners leverage…

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

Recent advances in prompt engineering enable large language models (LLMs) to solve multi-hop logical reasoning problems with impressive accuracy. However, there is little existing work investigating the robustness of LLMs with few-shot…

Watermarking the outputs of large language models (LLMs) is critical for provenance tracing, content regulation, and model accountability. Existing approaches often rely on access to model internals or are constrained by static rules and…

In this paper, we evaluate the capability of transformer-based language models in making inferences over uncertain text that includes uncertain rules of reasoning. We cover both Pre-trained Language Models (PLMs) and generative Large…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

Legal syllogism is a form of deductive reasoning commonly used by legal professionals to analyze cases. In this paper, we propose legal syllogism prompting (LoT), a simple prompting method to teach large language models (LLMs) for legal…

In this paper, we address the problem of giving names to predicates in logic rules using Large Language Models (LLMs). In the context of Inductive Logic Programming, various rule generation methods produce rules containing unnamed…

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

Large Language Models (LLMs) have achieved remarkable success in various domains but remain vulnerable to adversarial jailbreak attacks. Existing prompt-defense strategies, including parameter-modifying and parameter-free approaches, face…

Background and Context. The increasing integration of large language models (LLMs) in computing education presents an emerging challenge in understanding how students use LLMs and craft prompts to solve computational tasks. Prior research…