As large language models (LLMs) become integral to various applications, ensuring both
their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into …

Background Search engines often serve as a primary resource for patients to obtain drug
information. However, the search engine market is rapidly changing due to the introduction …

Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of
the large language model (LLM) parametric knowledge with non-preferred features is …

Beyond maximum likelihood estimation (MLE), the standard objective of a language model
(LM) that optimizes good examples probabilities, many studies have explored ways that also …

Large Language Models (LLMs) require careful safety alignment to prevent malicious
outputs. While significant research focuses on mitigating harmful content generation, the …

The task of multi-objective alignment aims at balancing and controlling the different
alignment objectives (eg, helpfulness, harmlessness and honesty) of large language models …

While recent advancements in large language model (LLM) alignment have enabled the
effective identification of malicious objectives involving scene nesting and keyword rewriting …

Decision-making under full alignment requires balancing between reasoning and
faithfulness-a challenge for large language models (LLMs). This study explores whether …

Human-like chatbots–machines that can act as humans to chat about any topic–need to
listen, understand, reason, respond, and interactively learn to optimize the whole process …

Large Language Models (LLMs) require careful safety alignment to prevent malicious
outputs. While significant research focuses on mitigating harmful content generation, the …