The latest generative large language models (LLMs) have found their application in data augmentation tasks, where small numbers of text samples are LLM-paraphrased and then used to fine-tune the model. However, more research is needed to assess how different prompts, seed data selection strategies, filtering methods, or model settings affect the quality of paraphrased data (and downstream models). In this study, we investigate three text diversity incentive methods well established in crowdsourcing: taboo words, hints by previous outlier solutions, and chaining on previous outlier solutions. Using these incentive methods as part of instructions to LLMs augmenting text datasets, we measure their effects on generated texts' lexical diversity and downstream model performance. We compare the effects over 5 different LLMs and 6 datasets. We show that diversity is most increased by taboo words, while downstream model performance is highest when previously created paraphrases are used as hints.

Recent zero-shot evaluations have highlighted important limitations in the abilities of language models (LMs) to perform meaning extraction. However, it is now well known that LMs can demonstrate radical improvements in the presence of experimental contexts such as in-context examples and instructions. How well does this translate to previously studied meaning-sensitive tasks? We present a case-study on the extent to which experimental contexts can improve LMs' robustness in performing property inheritance -- predicting semantic properties of novel concepts, a task that they have been previously shown to fail on. Upon carefully controlling the nature of the in-context examples and the instructions, our work reveals that they can indeed lead to non-trivial property inheritance behavior in LMs. However, this ability is inconsistent: with a minimal reformulation of the task, some LMs were found to pick up on shallow, non-semantic heuristics from their inputs, suggesting that the computational principles of semantic property inference are yet to be mastered by LMs.

Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favor of functional programming (FP), e.g., HumanEval and MBPP. To address this, our study introduces a pioneering OOP-focused benchmark, featuring 431 Python programs that encompass essential OOP concepts and features like classes and encapsulation methods. We propose a novel evaluation metric, pass@o, tailored for OOP, enhancing traditional pass@k measures. Our evaluation of 23 leading large language models (LLMs), including both general and code-specialized models, reveals three key insights: 1) pass@o offers a more relevant and comprehensive assessment for OOP code generation; 2) Despite excelling in FP, code-specialized LLMs like WizardCoder lag in OOP compared to models like ChatGPT; 3) The poor performance of all advanced LLMs on our OOP benchmark highlights a critical need for improvements in this field. Our benchmark and scripts are publicly released at: https://github.com/alphadl/OOP-eval.

Large Language Models (LLMs) have demonstrated remarkable capabilities for reinforcement learning (RL) models, such as planning and reasoning capabilities. However, the problems of LLMs and RL model collaboration still need to be solved. In this study, we employ a teacher-student learning framework to tackle these problems, specifically by offering feedback for LLMs using RL models and providing high-level information for RL models with LLMs in a cooperative multi-agent setting. Within this framework, the LLM acts as a teacher, while the RL model acts as a student. The two agents cooperatively assist each other through a process of recursive help, such as "I help you help I help." The LLM agent supplies abstract information to the RL agent, enabling efficient exploration and policy improvement. In turn, the RL agent offers feedback to the LLM agent, providing valuable, real-time information that helps generate more useful tokens. This bi-directional feedback loop promotes optimization, exploration, and mutual improvement for both agents, enabling them to accomplish increasingly challenging tasks. Remarkably, we propose a practical algorithm to address the problem and conduct empirical experiments to evaluate the effectiveness of our method.

Large Language Models (LLMs) have achieved remarkable results in the machine translation evaluation task, yet there remains a gap in knowledge regarding how they utilize the provided data to conduct evaluations. This study aims to explore how LLMs leverage source and reference information in evaluating translations, with the ultimate goal of better understanding the working mechanism of LLMs. To this end, we design the controlled experiments across various input modes and model types, and employ both coarse-grained and fine-grained prompts to discern the utility of source versus reference information. Surprisingly, we find that reference information significantly enhances the evaluation accuracy, while source information sometimes is counterproductive, indicating a lack of cross-lingual capability when using LLMs to evaluate translations. We further conduct a meta-evaluation for translation error detection of LLMs, observing a similar phenomenon. These findings also suggest a potential research direction for LLMs that fully exploits the cross-lingual capability of LLMs to achieve better performance in machine translation evaluation tasks.

Aligning large language models (LLMs) with human values, particularly in the face of stealthy and complex jailbreaks, presents a formidable challenge. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis Prompting (IAPrompt). The principle behind is to trigger LLMs' inherent self-correct and improve ability through a two-stage process: 1) essential intention analysis, and 2) policy-aligned response. Notably, IAPrompt is an inference-only method, thus could enhance the safety of LLMs without compromising their helpfulness. Extensive experiments on SAP200 and DAN benchmarks across Vicuna, ChatGLM, MPT, DeepSeek, and GPT-3.5 show that IAPrompt could consistently and significantly reduce the harmfulness in response (averagely -46.5% attack success rate) and maintain the general helpfulness. Further analyses present some insights into how our method works. To facilitate reproducibility, We release our code and scripts at: https://github.com/alphadl/SafeLLM_with_IntentionAnalysis

Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks. Despite this, their application to information retrieval (IR) tasks is still challenging due to the infrequent occurrence of many IR-specific concepts in natural language. While prompt-based methods can provide task descriptions to LLMs, they often fall short in facilitating comprehensive understanding and execution of IR tasks, thereby limiting LLMs' applicability. To address this gap, in this work, we explore the potential of instruction tuning to enhance LLMs' proficiency in IR tasks. We introduce a novel instruction tuning dataset, INTERS, encompassing 21 tasks across three fundamental IR categories: query understanding, document understanding, and query-document relationship understanding. The data are derived from 43 distinct datasets with manually written templates. Our empirical results reveal that INTERS significantly boosts the performance of various publicly available LLMs, such as LLaMA, Mistral, and Phi, in search-related tasks. Furthermore, we conduct a comprehensive analysis to ascertain the effects of base model selection, instruction design, volume of instructions, and task variety on performance. We make our dataset and the models fine-tuned on it publicly accessible at https://github.com/DaoD/INTERS.

Machine learning (ML), especially with the emergence of large language models (LLMs), has significantly transformed various industries. However, the transition from ML model prototyping to production use within software systems presents several challenges. These challenges primarily revolve around ensuring safety, security, and transparency, subsequently influencing the overall robustness and trustworthiness of ML models. In this paper, we introduce ML-On-Rails, a protocol designed to safeguard ML models, establish a well-defined endpoint interface for different ML tasks, and clear communication between ML providers and ML consumers (software engineers). ML-On-Rails enhances the robustness of ML models via incorporating detection capabilities to identify unique challenges specific to production ML. We evaluated the ML-On-Rails protocol through a real-world case study of the MoveReminder application. Through this evaluation, we emphasize the importance of safeguarding ML models in production.

While Large Language Models (LLMs) based agents have successfully mimicked human behaviors in various scenarios, the realm of complex, multi-character social interactions within extended contexts remains underexplored. The challenge is compounded by privacy concerns, making it difficult to capture and utilize intricate real-life interactions. More importantly, the absence of quantitative evaluation methods hampers the pursuit of high-quality agent interactions, often leading to interactions that are limited in informativeness and expressiveness, characterized by superficial small talk without clear intentions. In this work, we leverage the rules of Tabletop Role-Playing Games (TRPG) to create an environment conducive to complex, context-rich interactions, emphasizing informativeness and expressiveness. This virtual setting alleviates privacy concerns and motivates agents to engage in meaningful, high-quality interactions as part of their in-game objectives. To assess these interactions, we introduce the Agent interaction Evaluation framework (AntEval), targeting the qualitative evaluation of interaction informativeness and expressiveness. Specifically, we propose two novel evaluation metrics: Information Exchanging Precision (IEP) and Interaction Expressiveness Gap (IEG). These metrics are designed to assess interactions in scenarios focused on information exchange and intention expression, respectively. Our experimental results demonstrate the effectiveness of these metrics in evaluating interaction quality. Notably, we identify significant areas for improvement in LLMs regarding social interactions, as highlighted by our metrics. We believe AntEval will guide further exploration in complex agent interactions, bringing them closer to emulating real human behavior and enhancing their integration and utility in real-world applications.

In this paper, we introduce Kun, a novel approach for creating high-quality instruction-tuning datasets for large language models (LLMs) without relying on manual annotations. Adapting a self-training algorithm based on instruction back-translation and answer polishment, Kun leverages unlabelled data from diverse sources such as Wudao, Wanjuan, and SkyPile to generate a substantial dataset of over a million Chinese instructional data points. This approach significantly deviates from traditional methods by using a self-curation process to refine and select the most effective instruction-output pairs. Our experiments with the 6B-parameter Yi model across various benchmarks demonstrate Kun's robustness and scalability. Our method's core contributions lie in its algorithmic advancement, which enhances data retention and clarity, and its innovative data generation approach that substantially reduces the reliance on costly and time-consuming manual annotations. This methodology presents a scalable and efficient solution for improving the instruction-following capabilities of LLMs, with significant implications for their application across diverse fields. The code and dataset can be found at https://github.com/Zheng0428/COIG-Kun