Related papers: Censored LLMs as a Natural Testbed for Secret Know…
Large language models (LLMs) have demonstrated robust capabilities across various natural language tasks. However, producing outputs that are consistently honest and helpful remains an open challenge. To overcome this challenge, this paper…
Despite advancements in large language models (LLMs), non-factual responses still persist in fact-seeking question answering. Unlike extensive studies on post-hoc detection of these responses, this work studies non-factuality prediction…
Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…
Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…
Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereotypes, which are challenging to be comprehensively collected…
The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…
Eliciting information to reduce uncertainty about a latent entity is a critical task in many application domains, e.g., assessing individual student learning outcomes, diagnosing underlying diseases, or learning user preferences. Though…
Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find…
Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across…
Many studies have demonstrated that large language models (LLMs) can produce harmful responses, exposing users to unexpected risks when LLMs are deployed. Previous studies have proposed comprehensive taxonomies of the risks posed by LLMs,…
Previous works on Large Language Models (LLMs) have mainly focused on evaluating their helpfulness or harmlessness. However, honesty, another crucial alignment criterion, has received relatively less attention. Dishonest behaviors in LLMs,…
Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We…
A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…
Neural language models (LMs) can be used to evaluate the truth of factual statements in two ways: they can be either queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these…
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…
Advances in large language models have raised concerns about their potential use in generating compelling election disinformation at scale. This study presents a two-part investigation into the capabilities of LLMs to automate stages of an…
The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…
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…
This paper is under review in AI and Ethics This study examines whether large language models (LLMs) can reliably answer scientific questions and demonstrates how easily they can be influenced by fringe scientific material. The authors…
Pre-trained large language models (LLMs) can now be easily adapted for specific business purposes using custom prompts or fine tuning. These customizations are often iteratively re-engineered to improve some aspect of performance, but after…