Related papers: Eliciting Secret Knowledge from Language Models

Step-by-step decision planning with large language models (LLMs) is gaining attention in AI agent development. This paper focuses on decision planning with uncertainty estimation to address the hallucination problem in language models.…

Users often make ambiguous requests that require clarification. We study the problem of asking clarification questions in an information retrieval setting, where systems often face ambiguous search queries and it is challenging to turn the…

The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively assists human understanding by developing and leveraging a…

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

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…

Often, multilingual language models are trained with the objective to map semantically similar content (in different languages) in the same latent space. In this paper, we show a nuance in this training objective, and find that by changing…

Knowledge Distillation (KD) accelerates training of large language models (LLMs) but poses intellectual property protection and LLM diversity risks. Existing KD detection methods based on self-identity or output similarity can be easily…

This study explores the idea of AI Personality or AInality suggesting that Large Language Models (LLMs) exhibit patterns similar to human personalities. Assuming that LLMs share these patterns with humans, we investigate using…

While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that…

Assessments of algorithmic bias in large language models (LLMs) are generally catered to uncovering systemic discrimination based on protected characteristics such as sex and ethnicity. However, there are over 180 documented cognitive…

Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI. Various deep learning (DL)-based models have been proposed for this task, training on image evaluation data to extract objective low-level…

Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks. Current research focuses on enhancing their performance within their existing knowledge. Despite their…

A key distinguishing feature of conversational recommender systems over traditional recommender systems is their ability to elicit user preferences using natural language. Currently, the predominant approach to preference elicitation is to…

Confirmation bias, the tendency to seek evidence that supports rather than challenges one's belief, hinders one's reasoning ability. We examine whether large language models (LLMs) exhibit confirmation bias by adapting the rule-discovery…

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that assess model behavior…

Vision-language models (VLMs) pre-trained on web-scale datasets have demonstrated remarkable capabilities on downstream tasks when fine-tuned with minimal data. However, many VLMs rely on proprietary data and are not open-source, which…

When answering questions, LLMs can convey not only an answer, but a level of confidence about the answer being correct. This includes explicit confidence markers (e.g. giving a numeric score) as well as implicit markers, like an…

Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidden from users, and sensitive data passes through shared contexts. We test whether models…

The widespread adoption of chat interfaces based on Large Language Models (LLMs) raises concerns about promoting superficial learning and undermining the development of critical thinking skills. Instead of relying on LLMs purely for…