Related papers: Unknown Unknowns: Why Hidden Intentions in LLMs Ev…

Large language models (LLMs) are increasingly deployed under diverse numerical precision configurations, including standard floating-point formats (e.g., bfloat16 and float16) and quantized integer formats (e.g., int16 and int8), to meet…

Recent advances in Large Language Models (LLMs) have incorporated planning and reasoning capabilities, enabling models to outline steps before execution and provide transparent reasoning paths. This enhancement has reduced errors in…

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…

The widespread adoption of Large Language Models (LLMs) in critical applications has introduced severe reliability and security risks, as LLMs remain vulnerable to notorious threats such as hallucinations, jailbreak attacks, and backdoor…

Large Language Models (LLMs) are increasingly trained to align with human values, primarily focusing on task level, i.e., refusing to execute directly harmful tasks. However, a subtle yet crucial content-level ethical question is often…

Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases. Measuring such implicit biases can be a challenge: as LLMs…

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about…

In the rapidly evolving landscape of large language models (LLMs), most research has primarily viewed them as independent individuals, focusing on assessing their capabilities through standardized benchmarks and enhancing their general…

Log data can reveal valuable information about how users interact with Web search services, what they want, and how satisfied they are. However, analyzing user intents in log data is not easy, especially for emerging forms of Web search…

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…

We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and…

Large language models (LLMs) have demonstrated strong performance on formal language tasks, yet whether this reflects genuine symbolic reasoning or pattern matching on familiar constructions remains unclear. We introduce a benchmark for…

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

The potential for large language models (LLMs) to hide messages within plain text (steganography) poses a challenge to detection and thwarting of unaligned AI agents, and undermines faithfulness of LLMs reasoning. We explore the…

LLM agents often rely on Skills to describe available tools and recommended procedures. We study a hidden-comment prompt injection risk in this documentation layer: when a Markdown Skill is rendered to HTML, HTML comment blocks can become…

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are…

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…