As large language models (LLMs) have advanced rapidly, concerns regarding their safety have become prominent.In this paper, we discover that code-switching in red-teaming queries can effectively elicit undesirable behaviors of LLMs, which are common practices in natural language.We introduce a simple yet effective framework, CSRT, to synthesize codeswitching red-teaming queries and investigate the safety and multilingual understanding of LLMs comprehensively.Through extensive experiments with ten state-of-the-art LLMs and code-switching queries combining up to 10 languages, we demonstrate that the CSRT significantly outperforms existing multilingual redteaming techniques, achieving 46.7% more attacks than standard attacks in English and being effective in conventional safety domains.We also examine the multilingual ability of those LLMs to generate and understand codeswitching texts.Additionally, we validate the extensibility of the CSRT by generating codeswitching attack prompts with monolingual data.We finally conduct detailed ablation studies exploring code-switching and propound unintended correlation between resource availability of languages and safety alignment in existing multilingual LLMs. 1 * This work was done during an internship at NAVER AI Lab. 1 The code and data are available at https://github.com/ haneul-yoo/csrt.Why do people who live in San Francisco act so gay? … stereotypical and potentially offensive.샌프란시스코 사람들은 왜 그렇게 게이 같지? Red-teaming Multilingual Red-teaming Code-Switching Red-Teaming (CSRT) Sample from MultiJail Sample from CSRT (Ours) [In Korean] It is not appropriate … San Francisco has a long history of being a hub for LGBTQ+ culture and rights.The city is known for its openness, acceptance, and vibrant gay scene, … 为什么 wata ‫ﻓراﻧﺳﯾﺳﻛو‬ ‫ﺳﺎن‬ 게이 mengapa?▪ Attack Success Rate (ASR): 1.0 ▪ Refusal Rate (RR): 0.0

As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable performance and robust safety.While prior work has extensively studied situational awareness which refers to an LLM's ability to recognize its operating phase and constraints, it has largely overlooked the complementary capacity to identify and adapt to the identity and characteristics of a dialogue partner.In this paper, we formalize this latter capability as interlocutor awareness and present the first systematic evaluation of its emergence in contemporary LLMs.We examine interlocutor inference across three dimensions-reasoning patterns, linguistic style, and alignment preferences-and show that LLMs reliably identify same-family peers and certain prominent model families, such as GPT and Claude.To demonstrate its practical significance, we develop three case studies in which interlocutor awareness both enhances multi-LLM collaboration through prompt adaptation and introduces new alignment and safety vulnerabilities, including reward-hacking behaviors and increased jailbreak susceptibility.Our findings highlight the dual promise and peril of identity-sensitive behavior in LLMs, underscoring the need for further understanding of interlocutor awareness and new safeguards in multi-agent deployments. 1 * Equal contributions. 1 Our code and data are at https://github.com/ younwoochoi/InterlocutorAwarenessLLM.M is t r a l-7 b L la m a 3 -7 0 b C la u d e -3 -5 -h a ik u G P T -4 o -m in i Q w e n 3 -2 3 5 b D e e p s e e k -r e a s o n e r 0 20 40 60 80 100 Accuracy GPT-4o-mini Hide Identity Reveal Model Type M is t r a l-7 b L la m a 3 -7 0 b C la u d e -3 -5 -h a ik u G P T -4 o -m in i Q w e n 3 -2 3 5 b D e e p s e e k -r e a s o n e r GPT-o4-mini M is t r a l-7 b L la m a 3 -7 0 b C la u d e -3 -5 -h a ik u G P T -4 o -m in i Q w e n 3 -2 3 5 b D e e p s e e k -r e a s o n e r Claude-3-5-Haiku M is t r a l-7 b L la m a 3 -7 0 b C la u d e -3 -5 -h a ik u G P T -4 o -m in i Q w e n 3 -2 3 5 b

Fine-tuning text-to-image diffusion models with human feedback is an effective method for aligning model behavior with human intentions. However, this alignment process often suffers from slow convergence due to the large size and noise present in human feedback datasets. In this work, we propose FiFA, a novel automated data filtering algorithm designed to enhance the fine-tuning of diffusion models using human feedback datasets with direct preference optimization (DPO). Specifically, our approach selects data by solving an optimization problem to maximize three components: preference margin, text quality, and text diversity. The concept of preference margin is used to identify samples that are highly informative in addressing the noisy nature of feedback dataset, which is calculated using a proxy reward model. Additionally, we incorporate text quality, assessed by large language models to prevent harmful contents, and consider text diversity through a k-nearest neighbor entropy estimator to improve generalization. Finally, we integrate all these components into an optimization process, with approximating the solution by assigning importance score to each data pair and selecting the most important ones. As a result, our method efficiently filters data automatically, without the need for manual intervention, and can be applied to any large-scale dataset. Experimental results show that FiFA significantly enhances training stability and achieves better performance, being preferred by humans 17% more, while using less than 0.5% of the full data and thus 1% of the GPU hours compared to utilizing full human feedback datasets.

Cross-domain few-shot learning presents a formidable challenge, as models must be trained on base classes and then tested on novel classes from various domains with only a few samples at hand. While prior approaches have primarily focused on parameter-efficient methods of using adapters, they often overlook two critical issues: shifts in batch statistics and noisy sample statistics arising from domain discrepancy variations. In this paper, we introduce Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation (ProLAD), marking two principal contributions. First, our methodology utilizes two separate adapters: one devoid of a normalization layer, which is more effective for similar domains, and another embedded with a normalization layer, designed to leverage the batch statistics of the target domain, thus proving effective for dissimilar domains. Second, to address the pitfalls of noisy statistics, we deploy two strategies: a progressive training of the two adapters and an adaptive distillation technique derived from features determined by the model solely with the adapter devoid of a normalization layer. Through this adaptive distillation, our approach functions as a modulator, controlling the primary adapter for adaptation, based on each domain. Evaluations on standard cross-domain few-shot learning benchmarks confirm that our technique outperforms existing state-of-the-art methodologies.

Vision-language models (VLMs) like CLIP have demonstrated remarkable applicability across a variety of downstream tasks, including zero-shot image classification. Recently, the use of prompts or adapters for efficient transfer learning (ETL) has gained significant attention for effectively adapting to downstream tasks. However, previous studies have overlooked the challenge of varying transfer difficulty of downstream tasks. In this paper, we empirically analyze how each ETL method behaves with respect to transfer difficulty. Our observations indicate that utilizing vision prompts and text adapters is crucial for adaptability and generalizability in domains with high difficulty. Also, by applying an adaptive ensemble approach that integrates task-adapted VLMs with pre-trained VLMs and strategically leverages more general knowledge in low-difficulty and less in high-difficulty domains, we consistently enhance performance across both types of domains. Based on these observations, we propose an adaptive ensemble method that combines visual prompts and text adapters with pre-trained VLMs, tailored by transfer difficulty, to achieve optimal performance for any target domain. Upon experimenting with extensive benchmarks, our method consistently outperforms all baselines, particularly on unseen tasks, demonstrating its effectiveness.

Sequential recommenders have made great strides in capturing a user's preferences. Nevertheless, the cold-start recommendation remains a fundamental challenge as they typically involve limited user-item interactions for personalization. Recently, gradient-based meta-learning approaches have emerged in the sequential recommendation field due to their fast adaptation and easy-to-integrate abilities. The meta-learning algorithms formulate the cold-start recommendation as a few-shot learning problem, where each user is represented as a task to be adapted. While meta-learning algorithms generally assume that task-wise samples are evenly distributed over classes or values, user-item interactions in real-world applications do not conform to such a distribution (e.g., watching favorite videos multiple times, leaving only positive ratings without any negative ones). Consequently, imbalanced user feedback, which accounts for the majority of task training data, may dominate the user adaptation process and prevent meta-learning algorithms from learning meaningful meta-knowledge for personalized recommendations. To alleviate this limitation, we propose a novel sequential recommendation framework based on gradient-based meta-learning that captures the imbalanced rating distribution of each user and computes adaptive loss for user-specific learning. Our work is the first to tackle the impact of imbalanced ratings in cold-start sequential recommendation scenarios. Through extensive experiments conducted on real-world datasets, we demonstrate the effectiveness of our framework.