Large Language Model (LLM)-based agents have demonstrated remarkable effectiveness. However, their performance can be compromised in data science scenarios that require real-time data adjustment, expertise in optimization due to complex dependencies among various tasks, and the ability to identify logical errors for precise reasoning. In this study, we introduce the Data Interpreter, a solution designed to solve with code that emphasizes three pivotal techniques to augment problem-solving in data science: 1) dynamic planning with hierarchical graph structures for real-time data adaptability;2) tool integration dynamically to enhance code proficiency during execution, enriching the requisite expertise;3) logical inconsistency identification in feedback, and efficiency enhancement through experience recording. We evaluate the Data Interpreter on various data science and real-world tasks. Compared to open-source baselines, it demonstrated superior performance, exhibiting significant improvements in machine learning tasks, increasing from 0.86 to 0.95. Additionally, it showed a 26% increase in the MATH dataset and a remarkable 112% improvement in open-ended tasks. The solution will be released at https://github.com/geekan/MetaGPT.

In the realm of personalization, integrating diverse information sources such as consumption signals and content-based representations is becoming increasingly critical to build state-of-the-art solutions. In this regard, two of the biggest trends in research around this subject are Graph Neural Networks (GNNs) and Foundation Models (FMs). While GNNs emerged as a popular solution in industry for powering personalization at scale, FMs have only recently caught attention for their promising performance in personalization tasks like ranking and retrieval. In this paper, we present a graph-based foundation modeling approach tailored to personalization. Central to this approach is a Heterogeneous GNN (HGNN) designed to capture multi-hop content and consumption relationships across a range of recommendable item types. To ensure the generality required from a Foundation Model, we employ a Large Language Model (LLM) text-based featurization of nodes that accommodates all item types, and construct the graph using co-interaction signals, which inherently transcend content specificity. To facilitate practical generalization, we further couple the HGNN with an adaptation mechanism based on a two-tower (2T) architecture, which also operates agnostically to content type. This multi-stage approach ensures high scalability; while the HGNN produces general purpose embeddings, the 2T component models in a continuous space the sheer size of user-item interaction data. Our comprehensive approach has been rigorously tested and proven effective in delivering recommendations across a diverse array of products within a real-world, industrial audio streaming platform.

The development of generative large language models (G-LLM) opened up new opportunities for the development of new types of knowledge-based systems similar to ChatGPT, Bing, or Gemini. Fine-tuning (FN) and Retrieval-Augmented Generation (RAG) are the techniques that can be used to implement domain adaptation for the development of G-LLM-based knowledge systems. In our study, using ROUGE, BLEU, METEOR scores, and cosine similarity, we compare and examine the performance of RAG and FN for the GPT-J-6B, OPT-6.7B, LlaMA, LlaMA-2 language models. Based on measurements shown on different datasets, we demonstrate that RAG-based constructions are more efficient than models produced with FN. We point out that connecting RAG and FN is not trivial, because connecting FN models with RAG can cause a decrease in performance. Furthermore, we outline a simple RAG-based architecture which, on average, outperforms the FN models by 16% in terms of the ROGUE score, 15% in the case of the BLEU score, and 53% based on the cosine similarity. This shows the significant advantage of RAG over FN in terms of hallucination, which is not offset by the fact that the average 8% better METEOR score of FN models indicates greater creativity compared to RAG.

With the growing humanlike nature of dialog agents, people are now engaging in extended conversations that can stretch from brief moments to substantial periods of time. Understanding the factors that contribute to sustaining these interactions is crucial, yet existing studies primarily focusing on short-term simulations that rarely explore such prolonged and real conversations. In this paper, we investigate the factors influencing retention rates in real interactions with roleplaying models. By analyzing a large dataset of interactions between real users and thousands of characters, we systematically examine multiple factors and assess their impact on user retention rate. Surprisingly, we find that the degree to which the bot embodies the roles it plays has limited influence on retention rates, while the length of each turn it speaks significantly affects retention rates. This study sheds light on the critical aspects of user engagement with role-playing models and provides valuable insights for future improvements in the development of large language models for role-playing purposes.

Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. However, their predominant use in an offline manner usually suffers from substantial domain gap between the VLN task and the LLM training corpus. This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision, leading to a significant mitigation of the domain gap in a cost-effective manner. Specifically, at each timestep, the LLM is prompted to forecast the navigational chain-of-thought by: 1) acting as a world model to imagine the next observation according to the instruction, 2) selecting the candidate observation that best aligns with the imagination, and 3) determining the action based on the reasoning from the prior steps. Through constructing formalized labels for training, the LLM can learn to generate desired and reasonable chain-of-thought outputs for improving the action decision. Experimental results across various training settings and popular VLN benchmarks (e.g., Room-to-Room (R2R), Room-across-Room (RxR), Room-for-Room (R4R)) show the significant superiority of NavCoT over the direct action prediction variants. Through simple parameter-efficient finetuning, our NavCoT outperforms a recent GPT4-based approach with ~7% relative improvement on the R2R dataset. We believe that NavCoT will help unlock more task-adaptive and scalable LLM-based embodied agents, which are helpful for developing real-world robotics applications. Code is available at https://github.com/expectorlin/NavCoT.

Ensuring factual consistency between the summary and the original document is paramount in summarization tasks. Consequently, considerable effort has been dedicated to detecting inconsistencies. With the advent of Large Language Models (LLMs), recent studies have begun to leverage their advanced language understanding capabilities for inconsistency detection. However, early attempts have shown that LLMs underperform traditional models due to their limited ability to follow instructions and the absence of an effective detection methodology. In this study, we reassess summary inconsistency detection with LLMs, comparing the performances of GPT-3.5 and GPT-4. To advance research in LLM-based inconsistency detection, we propose SIFiD (Summary Inconsistency Detection with Filtered Document) that identify key sentences within documents by either employing natural language inference or measuring semantic similarity between summaries and documents.

Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-output pairs (demonstrations). Nevertheless, the inclusion of demonstrations leads to a quadratic increase in the computational overhead of the self-attention mechanism. Existing solutions attempt to distill lengthy demonstrations into compact vectors. However, they often require task-specific retraining or compromise LLM's in-context learning performance. To mitigate these challenges, we present Meta dEmonstratioN Distillation (MEND), where a language model learns to distill any lengthy demonstrations into vectors without retraining for a new downstream task. We exploit the knowledge distillation to enhance alignment between MEND and LLM, achieving both efficiency and effectiveness simultaneously. MEND is endowed with the meta-knowledge of distilling demonstrations through a two-stage training process, which includes meta-distillation pretraining and fine-tuning. Comprehensive evaluations across seven diverse ICL task partitions using decoder-only (GPT-2) and encoder-decoder (T5) attest to MEND's prowess. It not only matches but often outperforms the Vanilla ICL as well as other state-of-the-art distillation models, while significantly reducing the computational demands. This innovation promises enhanced scalability and efficiency for the practical deployment of large language models

Depression-diagnosis-oriented chat aims to guide patients in self-expression to collect key symptoms for depression detection. Recent work focuses on combining task-oriented dialogue and chitchat to simulate the interview-based depression diagnosis. Whereas, these methods can not well capture the changing information, feelings, or symptoms of the patient during dialogues. Moreover, no explicit framework has been explored to guide the dialogue, which results in some useless communications that affect the experience. In this paper, we propose to integrate Psychological State Tracking (POST) within the large language model (LLM) to explicitly guide depression-diagnosis-oriented chat. Specifically, the state is adapted from a psychological theoretical model, which consists of four components, namely Stage, Information, Summary and Next. We fine-tune an LLM model to generate the dynamic psychological state, which is further used to assist response generation at each turn to simulate the psychiatrist. Experimental results on the existing benchmark show that our proposed method boosts the performance of all subtasks in depression-diagnosis-oriented chat.

Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of inner representations, and discover a salient pattern associated with hallucinations: correct generations tend to have sharper context activations in the hidden states of the in-context tokens, compared to the incorrect ones. Leveraging this insight, we propose an entropy-based metric to quantify the "sharpness" among the in-context hidden states and incorporate it into the decoding process to formulate a constrained decoding approach. Experiments on various knowledge-seeking and hallucination benchmarks demonstrate our approach's consistent effectiveness, for example, achieving up to an 8.6 point improvement on TruthfulQA. We believe this study can improve our understanding of hallucinations and serve as a practical solution for hallucination mitigation. Large language models (LLMs) have made remarkable advancements in recent years, with extensive applications across various domains (OpenAI, 2022; 2023; Kaddour et al., 2023). Despite these advances, LLMs still face notable challenges regarding factuality, which could critically undermine the trustworthiness and reliability of LLMs, as highlighted in recent studies (Chen et al., 2023; Ji et al., 2023; Wang et al., 2023). To address the factuality issue, many efforts have focused on retrieving external knowledge (Ram et al., 2023b; Yu et al., 2023; Jiang et al., 2023) for generation or fact-checking, as well as fine-tuning (Asai et al., 2023) and self-evaluation (Pan et al., 2023; Xiong et al., 2024). However, these methods often require high computational resources or high-quality knowledge bases, which may not be available for domain-specific cases. In contrast, we aim to tackle this challenge from the perspective of model's inner representations, investigating whether the hidden states contain information about hallucination.

Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task changes are completely unpredictable. Given a description of an overarching goal or data theme, which we call a realm, humans can often guess what concepts are associated with it. We show here that the combination of a large language model and an image generation model can similarly provide useful premonitions as to how a continual learning challenge might develop over time. We use the large language model to generate text descriptions of semantically related classes that might potentially appear in the data stream in future. These descriptions are then rendered using Stable Diffusion to generate new labelled image samples. The resulting synthetic dataset is employed for supervised pre-training, but is discarded prior to commencing continual learning, along with the pre-training classification head. We find that the backbone of our pre-trained networks can learn representations useful for the downstream continual learning problem, thus becoming a valuable input to any existing continual learning method. Although there are complexities arising from the domain gap between real and synthetic images, we show that pre-training models in this manner improves multiple Class Incremenal Learning (CIL) methods on fine-grained image classification benchmarks.