Chain-of-Thought (CoT) prompting has been shown to enhance the multi-step reasoning capabilities of Large Language Models (LLMs). However, debates persist about whether LLMs exhibit abstract generalization or rely on shallow heuristics when given CoT prompts. To understand the factors influencing CoT reasoning we provide a detailed case study of the symbolic reasoning task of decoding shift ciphers, where letters are shifted forward some number of steps in the alphabet. GPT-4 achieves zero accuracy on most shift ciphers with standard prompting, but with CoT its accuracy improves to an average of 32%. By focusing on a single relatively simple task, we are able to identify three factors that systematically affect CoT performance: the probability of the task's expected output (probability), what the model has implicitly learned during pre-training (memorization), and the number of intermediate operations involved in reasoning (noisy reasoning). We show that these factors can drastically influence the task accuracy; e.g., varying the output's probability of occurrence can shift accuracy from 26% to 70%. We also demonstrate that it is essential for the model to explicitly produce intermediate steps as output that can be conditioned on to increase the probability of the correct answer. Our experiments indicate that as long as the model does so, the validity of the demonstrations in the prompt does not matter. Overall, we conclude that CoT prompting performance reflects both memorization and a probabilistic version of genuine reasoning.

While Large Language Models (LLMs) have achieved remarkable success across various applications, they also raise concerns regarding self-cognition. In this paper, we perform a pioneering study to explore self-cognition in LLMs. Specifically, we first construct a pool of self-cognition instruction prompts to evaluate where an LLM exhibits self-cognition and four well-designed principles to quantify LLMs' self-cognition. Our study reveals that 4 of the 48 models on Chatbot Arena--specifically Command R, Claude3-Opus, Llama-3-70b-Instruct, and Reka-core--demonstrate some level of detectable self-cognition. We observe a positive correlation between model size, training data quality, and self-cognition level. Additionally, we also explore the utility and trustworthiness of LLM in the self-cognition state, revealing that the self-cognition state enhances some specific tasks such as creative writing and exaggeration. We believe that our work can serve as an inspiration for further research to study the self-cognition in LLMs.

Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with higher expenses, while less capable models are more cost-effective. To address this dilemma, we propose several efficient router models that dynamically select between a stronger and a weaker LLM during inference, aiming to optimize the balance between cost and response quality. We develop a training framework for these routers leveraging human preference data and data augmentation techniques to enhance performance. Our evaluation on widely-recognized benchmarks shows that our approach significantly reduces costs--by over 2 times in certain cases--without compromising the quality of responses. Interestingly, our router models also demonstrate significant transfer learning capabilities, maintaining their performance even when the strong and weak models are changed at test time. This highlights the potential of these routers to provide a cost-effective yet high-performance solution for deploying LLMs.

Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape. The advancement of generative artificial intelligence has positioned Multi-modal Large Language Models (MLLMs) as crucial tools for managing healthcare data. MLLMs can support multi-modal inputs and generate diverse types of content by leveraging large-scale training on vast amounts of multi-modal data. However, critical challenges persist in developing medical MLLMs, including healthcare data security and freshness issues, affecting the output quality of MLLMs. In this paper, we propose a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLMs framework for healthcare data management. This framework leverages a hierarchical cross-chain architecture to facilitate secure data training. Moreover, it enhances the output quality of MLLMs through hybrid RAG, which employs multi-modal metrics to filter various unimodal RAG results and incorporates these retrieval results as additional inputs to MLLMs. Additionally, we employ age of information to indirectly evaluate the data freshness impact of MLLMs and utilize contract theory to incentivize healthcare data holders to share fresh data, mitigating information asymmetry in data sharing. Finally, we utilize a generative diffusion model-based reinforcement learning algorithm to identify the optimal contract for efficient data sharing. Numerical results demonstrate the effectiveness of the proposed schemes, which achieve secure and efficient healthcare data management.

Despite the rapid development of Chinese vision-language models (VLMs), most existing Chinese vision-language (VL) datasets are constructed on Western-centric images from existing English VL datasets. The cultural bias in the images makes these datasets unsuitable for evaluating VLMs in Chinese culture. To remedy this issue, we present a new Chinese Vision- Language Understanding Evaluation (CVLUE) benchmark dataset, where the selection of object categories and images is entirely driven by Chinese native speakers, ensuring that the source images are representative of Chinese culture. The benchmark contains four distinct VL tasks ranging from image-text retrieval to visual question answering, visual grounding and visual dialogue. We present a detailed statistical analysis of CVLUE and provide a baseline performance analysis with several open-source multilingual VLMs on CVLUE and its English counterparts to reveal their performance gap between English and Chinese. Our in-depth category-level analysis reveals a lack of Chinese cultural knowledge in existing VLMs. We also find that fine-tuning on Chinese culture-related VL datasets effectively enhances VLMs' understanding of Chinese culture.

The development of autonomous agents increasingly relies on Multimodal Language Models (MLMs) to perform tasks described in natural language with GUI environments, such as websites, desktop computers, or mobile phones. Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexities of constructing tasks and evaluators. To overcome these limitations, we introduce Crab, the first agent benchmark framework designed to support cross-environment tasks, incorporating a graph-based fine-grained evaluation method and an efficient mechanism for task and evaluator construction. Our framework supports multiple devices and can be easily extended to any environment with a Python interface. Leveraging Crab, we developed a cross-platform Crab Benchmark-v0 comprising 100 tasks in computer desktop and mobile phone environments. We evaluated four advanced MLMs using different single and multi-agent system configurations on this benchmark. The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 35.26%. All framework code, agent code, and task datasets are publicly available at https://github.com/camel-ai/crab.

Large language models have demonstrated their capabilities in storyline creation and human-like character role-playing. Current language model agents mainly focus on reasonable behaviors from the level of individuals, and their behaviors might be hard to constraint on the level of the whole storyline. In this paper we introduce IBSEN, a director-actor coordinate agent framework that generates drama scripts and makes the plot played by agents more controllable. The director agent writes plot outlines that the user desires to see, instructs the actor agents to role-play their characters, and reschedules the plot when human players participate in the scenario to ensure the plot is progressing towards the objective. To evaluate the framework, we create a novel drama plot that involves several actor agents and check the interactions between them under the instruction of the director agent. Evaluation results show that our framework could generate complete, diverse drama scripts from only a rough outline of plot objectives, meanwhile maintaining the characteristics of characters in the drama. Our codes and prompts are available at https://github.com/OpenDFM/ibsen.

We consider the task of generating segmentation masks for the target object from an object manipulation instruction, which allows users to give open vocabulary instructions to domestic service robots. Conventional segmentation generation approaches often fail to account for objects outside the camera's field of view and cases in which the order of vertices differs but still represents the same polygon, which leads to erroneous mask generation. In this study, we propose a novel method that generates segmentation masks from open vocabulary instructions. We implement a novel loss function using optimal transport to prevent significant loss where the order of vertices differs but still represents the same polygon. To evaluate our approach, we constructed a new dataset based on the REVERIE dataset and Matterport3D dataset. The results demonstrated the effectiveness of the proposed method compared with existing mask generation methods. Remarkably, our best model achieved a +16.32% improvement on the dataset compared with a representative polygon-based method.

Black-box tuning has attracted recent attention due to that the structure or inner parameters of advanced proprietary models are not accessible. Proxy-tuning [1] provides a test-time output adjustment for tuning black-box language models. It applies the difference of the output logits before and after tuning a smaller white-box "proxy" model to improve the black-box model. However, this technique serves only as a decoding-time algorithm, leading to an inconsistency between training and testing which potentially limits overall performance. To address this problem, we introduce Consistent Proxy Tuning (CPT), a simple yet effective black-box tuning method. Different from Proxy-tuning, CPT additionally exploits the frozen large black-box model and another frozen small white-box model, ensuring consistency between training-stage optimization objective and test-time proxies. This consistency benefits Proxy-tuning and enhances model performance. Note that our method focuses solely on logit-level computation, which makes it model-agnostic and applicable to any task involving logit classification. Extensive experimental results demonstrate the superiority of our CPT in both black-box tuning of Large-Language Models (LLMs) and Vision-Language Models (VLMs) across various datasets.

Training an agent to achieve particular goals or perform desired behaviors is often accomplished through reinforcement learning, especially in the absence of expert demonstrations. However, supporting novel goals or behaviors through reinforcement learning requires the ad-hoc design of appropriate reward functions, which quickly becomes intractable. To address this challenge, we propose Text-Aware Diffusion for Policy Learning (TADPoLe), which uses a pretrained, frozen text-conditioned diffusion model to compute dense zero-shot reward signals for text-aligned policy learning. We hypothesize that large-scale pretrained generative models encode rich priors that can supervise a policy to behave not only in a text-aligned manner, but also in alignment with a notion of naturalness summarized from internet-scale training data. In our experiments, we demonstrate that TADPoLe is able to learn policies for novel goal-achievement and continuous locomotion behaviors specified by natural language, in both Humanoid and Dog environments. The behaviors are learned zero-shot without ground-truth rewards or expert demonstrations, and are qualitatively more natural according to human evaluation. We further show that TADPoLe performs competitively when applied to robotic manipulation tasks in the Meta-World environment.