Social chatbots have become essential intelligent companions in daily scenarios ranging from emotional support to personal interaction. However, conventional chatbots with passive response mechanisms usually rely on users to initiate or sustain dialogues by bringing up new topics, resulting in diminished engagement and shortened dialogue duration. In this paper, we present PaRT, a novel framework enabling context-aware proactive dialogues for social chatbots through personalized real-time retrieval and generation. Specifically, PaRT first integrates user profiles and dialogue context into a large language model (LLM), which is initially prompted to refine user queries and recognize their underlying intents for the upcoming conversation. Guided by refined intents, the LLM generates personalized dialogue topics, which then serve as targeted queries to retrieve relevant passages from RedNote. Finally, we prompt LLMs with summarized passages to generate knowledge-grounded and engagement-optimized responses. Our approach has been running stably in a real-world production environment for more than 30 days, achieving a 21.77\% improvement in the average duration of dialogues.

The rapid advancement of Large Language Models (LLMs) has enhanced software development processes, minimizing the time and effort required for coding and enhancing developer productivity. However, despite their potential benefits, code generated by LLMs has been shown to generate insecure code in controlled environments, raising critical concerns about their reliability and security in real-world applications. This paper uses predefined security parameters to evaluate the security compliance of LLM-generated code across multiple models, such as ChatGPT, DeepSeek, Claude, Gemini and Grok. The analysis reveals critical vulnerabilities in authentication mechanisms, session management, input validation and HTTP security headers. Although some models implement security measures to a limited extent, none fully align with industry best practices, highlighting the associated risks in automated software development. Our findings underscore that human expertise is crucial to ensure secure software deployment or review of LLM-generated code. Also, there is a need for robust security assessment frameworks to enhance the reliability of LLM-generated code in real-world applications.

The advent of Large Language Models (LLMs) and generative AI is fundamentally transforming information retrieval and processing on the Internet, bringing both great potential and significant concerns regarding content authenticity and reliability. This paper presents a novel quantitative approach to shed light on the complex information dynamics arising from the growing use of generative AI tools. Despite their significant impact on the digital ecosystem, these dynamics remain largely uncharted and poorly understood. We propose a stochastic model to characterize the generation, indexing, and dissemination of information in response to new topics. This scenario particularly challenges current LLMs, which often rely on real-time Retrieval-Augmented Generation (RAG) techniques to overcome their static knowledge limitations. Our findings suggest that the rapid pace of generative AI adoption, combined with increasing user reliance, can outpace human verification, escalating the risk of inaccurate information proliferation across digital resources. An in-depth analysis of Stack Exchange data confirms that high-quality answers inevitably require substantial time and human effort to emerge. This underscores the considerable risks associated with generating persuasive text in response to new questions and highlights the critical need for responsible development and deployment of future generative AI tools.

Classical Chinese, as the core carrier of Chinese culture, plays a crucial role in the inheritance and study of ancient literature. However, existing natural language processing models primarily optimize for Modern Chinese, resulting in inadequate performance on Classical Chinese. This paper presents a comprehensive solution for Classical Chinese language processing. By continuing pre-training and instruction fine-tuning on the LLaMA3-8B-Chinese model, we construct a large language model, WenyanGPT, which is specifically designed for Classical Chinese tasks. Additionally, we develop an evaluation benchmark dataset, WenyanBENCH. Experimental results on WenyanBENCH demonstrate that WenyanGPT significantly outperforms current advanced LLMs in various Classical Chinese tasks. We make the model's training data, instruction fine-tuning data\footnote, and evaluation benchmark dataset publicly available to promote further research and development in the field of Classical Chinese processing.

We present ReasonIR-8B, the first retriever specifically trained for general reasoning tasks. Existing retrievers have shown limited gains on reasoning tasks, in part because existing training datasets focus on short factual queries tied to documents that straightforwardly answer them. We develop a synthetic data generation pipeline that, for each document, our pipeline creates a challenging and relevant query, along with a plausibly related but ultimately unhelpful hard negative. By training on a mixture of our synthetic data and existing public data, ReasonIR-8B achieves a new state-of-the-art of 29.9 nDCG@10 without reranker and 36.9 nDCG@10 with reranker on BRIGHT, a widely-used reasoning-intensive information retrieval (IR) benchmark. When applied to RAG tasks, ReasonIR-8B improves MMLU and GPQA performance by 6.4% and 22.6% respectively, relative to the closed-book baseline, outperforming other retrievers and search engines. In addition, ReasonIR-8B uses test-time compute more effectively: on BRIGHT, its performance consistently increases with longer and more information-rich rewritten queries; it continues to outperform other retrievers when combined with an LLM reranker. Our training recipe is general and can be easily extended to future LLMs; to this end, we open-source our code, data, and model.

This project introduces BrAIcht, an AI conversational agent that creates dialogues in the distinctive style of the famous German playwright Bertolt Brecht. BrAIcht is fine-tuned using German LeoLM, a large language model with 7 billion parameters and a modified version of the base Llama2 suitable for German language tasks. For fine-tuning, 29 plays of Bertolt Brecht and 907 of other German plays that are stylistically similar to Bertolt Brecht are used to form a more di-erse dataset. Due to the limited memory capacity, a parameterefficient fine-tuning technique called QLoRA is implemented to train the large language model. The results, based on BLEU score and perplexity, show very promising performance of BrAIcht in generating dialogues in the style of Bertolt Brecht.

The lack of standardized evaluation benchmarks in the medical domain for text inputs can be a barrier to widely adopting and leveraging the potential of natural language models for health-related downstream tasks. This paper revisited an openly available MIMIC-IV benchmark for electronic health records (EHRs) to address this issue. First, we integrate the MIMIC-IV data within the Hugging Face datasets library to allow an easy share and use of this collection. Second, we investigate the application of templates to convert EHR tabular data to text. Experiments using fine-tuned and zero-shot LLMs on the mortality of patients task show that fine-tuned text-based models are competitive against robust tabular classifiers. In contrast, zero-shot LLMs struggle to leverage EHR representations. This study underlines the potential of text-based approaches in the medical field and highlights areas for further improvement.

Learning from few demonstrations to develop policies robust to variations in robot initial positions and object poses is a problem of significant practical interest in robotics. Compared to imitation learning, which often struggles to generalize from limited samples, reinforcement learning (RL) can autonomously explore to obtain robust behaviors. Training RL agents through direct interaction with the real world is often impractical and unsafe, while building simulation environments requires extensive manual effort, such as designing scenes and crafting task-specific reward functions. To address these challenges, we propose an integrated real-to-sim-to-real pipeline that constructs simulation environments based on expert demonstrations by identifying scene objects from images and retrieving their corresponding 3D models from existing libraries. We introduce a projection-based reward model for RL policy training that is supervised by a vision-language model (VLM) using human-guided object projection relationships as prompts, with the policy further fine-tuned using expert demonstrations. In general, our work focuses on the construction of simulation environments and RL-based policy training, ultimately enabling the deployment of reliable robotic control policies in real-world scenarios.

Recent advances in Large Language Models (LLMs) have shown promising potential for human activity recognition (HAR) using ambient sensors, especially through natural language reasoning and zero-shot learning. However, existing datasets such as CASAS, ARAS, and MARBLE were not originally designed with LLMs in mind and therefore lack the contextual richness, complexity, and annotation granularity required to fully exploit LLM capabilities. In this paper, we introduce MuRAL, the first Multi-Resident Ambient sensor dataset with natural Language, comprising over 21 hours of multi-user sensor data collected from 21 sessions in a smart-home environment. MuRAL is annotated with fine-grained natural language descriptions, resident identities, and high-level activity labels, all situated in dynamic, realistic multi-resident settings. We benchmark MuRAL using state-of-the-art LLMs for three core tasks: subject assignment, action description, and activity classification. Our results demonstrate that while LLMs can provide rich semantic interpretations of ambient data, current models still face challenges in handling multi-user ambiguity and under-specified sensor contexts. We release MuRAL to support future research on LLM-powered, explainable, and socially aware activity understanding in smart environments. For access to the dataset, please reach out to us via the provided contact information. A direct link for dataset retrieval will be made available at this location in due course.

Previous detoxification methods are typically model-specific, addressing only individual models or model families, and require careful hyperparameter tuning due to the trade-off between detoxification efficacy and language modeling performance. Specifically, we propose a novel and efficient dataset distillation technique for detoxification using contrastive decoding. This approach distills detoxifying representations in the form of synthetic text data, enabling universal detoxification of any LLM through fine-tuning with the distilled text. Our experiments demonstrate that the detoxifying text distilled from GPT -2 can effectively detoxify larger models, including OPT, Falcon, and LLaMA-2. Additionally, analysis of the detoxifying text reveals a reduction in politically biased content, providing insights into the attributes necessary for effective detoxification of LLMs. Our codes are available at https://github.com/EminLU/UniDetox. Fascinated by the remarkable capabilities of Large Language Models (LLMs), numerous researchers and developers are dedicating their efforts to building new models. Today, many off-the-shelf pre-trained LLMs are publicly available (Radford et al., 2019; Zhang et al., 2022; Almazrouei et al., 2023; Touvron et al., 2023), and practitioners employ them in a wide range of applications. While this trend is expected to drive innovation across various fields, it simultaneously raises significant concerns regarding the unintended harmful behaviors exhibited by LLMs. LLMs, developed through pre-training on a large-scale corpus, often unintentionally acquire toxic content present in their training datasets (Gehman et al., 2020; Webster et al., 2020; Nozza et al., 2021). Due to these concerns, there have been efforts to introduce comprehensive regulations to mitigate the toxicity of LLMs; however, there is currently no standardized approach capable of consistently removing toxic content across diverse models. By developing a universal detoxification approach, we can form the basis for broadly applicable regulations and ensure consistent toxicity mitigation across a wide variety of LLMs. While numerous studies have explored the detoxification of LLMs, there is currently no post-hoc approach that can be seamlessly applied across models with varying architectures, sizes, or tok-enizers. Existing post-hoc detoxification strategies include decoding-time control (Liu et al., 2021; Zhang & Wan, 2023), word embedding/logits modification (Gehman et al., 2020; Han et al., 2024), and model editing (Ilharco et al., 2023; Wang et al., 2024). Crucially, this equilibrium point varies across models, necessitating individual hyperparameter optimization for each model, as we will thoroughly investigate in our experiments.