Related papers: LLM Hypnosis: Exploiting User Feedback for Unautho…
Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…
Pre-trained language models (LMs) are used for knowledge intensive tasks like question answering, but their knowledge gets continuously outdated as the world changes. Prior work has studied targeted updates to LMs, injecting individual…
Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…
Large Language Models (LLMs) have shown impressive potential to simulate human behavior. We identify a fundamental challenge in using them to simulate experiments: when LLM-simulated subjects are blind to the experimental design (as is…
The capabilities of Large Language Models (LLMs) are routinely evaluated by other LLMs trained to predict human preferences. This framework--known as LLM-as-a-judge--is highly scalable and relatively low cost. However, it is also vulnerable…
Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to targeted adversarial…
Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs…
We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large…
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…
Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte…
This study proposes a novel methodology for generating personalized fake news debunking messages by prompting Large Language Models (LLMs) with persona-based inputs aligned to the Big Five personality traits: Extraversion, Agreeableness,…
The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be…
Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can…
Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…
Vision-language artificial intelligence models (VLMs) possess medical knowledge and can be employed in healthcare in numerous ways, including as image interpreters, virtual scribes, and general decision support systems. However, here, we…
As Large Language Models (LLMs) become increasingly embedded in empirical research workflows, their use as analytical tools for quantitative or qualitative data raises pressing concerns for scientific integrity. This opinion paper draws a…
Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences. However, RM-based preference-tuning is vulnerable to reward hacking, whereby LM policies learn undesirable behaviors from flawed RMs. By…
Being able to predict people's opinions on issues and behaviors in realistic scenarios can be helpful in various domains, such as politics and marketing. However, conducting large-scale surveys like the European Social Survey to solicit…
Recent state-of-the-art recommender systems predominantly rely on either implicit or explicit feedback from users to suggest new items. While effective in recommending novel options, many recommender systems often use uninterpretable…
Instruction tuning aligns the response of large language models (LLMs) with human preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling…