This survey summarises the most recent methods for building and assessing helpful, honest,
and harmless neural language models, considering small, medium, and large-size models …

Social identity biases, particularly the tendency to favor one's own group (ingroup solidarity)
and derogate other groups (outgroup hostility), are deeply rooted in human psychology and …

Large Language Models (LLMs) are widely adopted for assisting in software development
tasks, yet their performance evaluations have narrowly focused on the functional correctness …

Large language models (LLMs) are susceptible to persuasion, which can pose risks when
models are faced with an adversarial interlocutor. We take a first step towards defending …

In the last year, Large Language Models (LLMs) have transformed the way of tackling
problems, opening up new perspectives in various works and research fields, due to their …

The vast majority of discourse around AI development assumes that subservient," moral"
models aligned with" human values" are universally beneficial--in short, that good AI is …

Large language models (LLMs) have demonstrated remarkable capabilities across a wide
range of natural language processing tasks. However, their tendency to exhibit sycophantic …

Large language models (LLMs) can produce erroneous responses that sound fluent and
convincing, raising the risk that users will rely on these responses as if they were correct …

Prompt leakage poses a compelling security and privacy threat in LLM applications.
Leakage of system prompts may compromise intellectual property, and act as adversarial …

The development of Large Language Models (LLMs) has notably transformed numerous
sectors, offering impressive text generation capabilities. Yet, the reliability and truthfulness of …