Language agents have achieved considerable performance on various complex tasks. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework that does not rely on large-scale annotated data and synthetic trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. We even notice that AutoAct, when using the Llama-2-13b model, can achieve performance comparable to that of the zero-shot GPT-3.5-Turbo agent. Code will be available at https://github.com/zjunlp/AutoAct.
Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. However, a primary limitation lies in the significant computational demands during training, arising from their extensive parameterization. This challenge is further intensified by the dynamic nature of the world, necessitating frequent updates to LLMs to correct outdated information or integrate new knowledge, thereby ensuring their continued relevance. Note that many applications demand continual model adjustments post-training to address deficiencies or undesirable behaviors. There is an increasing interest in efficient, lightweight methods for on-the-fly model modifications. To this end, recent years have seen a burgeoning in the techniques of knowledge editing for LLMs, which aim to efficiently modify LLMs' behaviors within specific domains while preserving overall performance across various inputs. In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches. Drawing inspiration from educational and cognitive research theories, we propose a unified categorization criterion that classifies knowledge editing methods into three groups: resorting to external knowledge, merging knowledge into the model, and editing intrinsic knowledge. Furthermore, we introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches. Additionally, we provide an in-depth analysis of knowledge location, which can give a deeper understanding of the knowledge structures inherent within LLMs. Finally, we discuss several potential applications of knowledge editing, outlining its broad and impactful implications.
Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities. Usually, answer calibration strategies such as step-level or path-level calibration play a vital role in multi-step reasoning. While effective, there remains a significant gap in our understanding of the key factors that drive their success. In this paper, we break down the design of recent answer calibration strategies and present a unified view which establishes connections between them. We then conduct a thorough evaluation on these strategies from a unified view, systematically scrutinizing step-level and path-level answer calibration across multiple paths. Our study holds the potential to illuminate key insights for optimizing multi-step reasoning with answer calibration.
Ocean science, which delves into the oceans that are reservoirs of life and biodiversity, is of great significance given that oceans cover over 70% of our planet's surface. Recently, advances in Large Language Models (LLMs) have transformed the paradigm in science. Despite the success in other domains, current LLMs often fall short in catering to the needs of domain experts like oceanographers, and the potential of LLMs for ocean science is under-explored. The intrinsic reason may be the immense and intricate nature of ocean data as well as the necessity for higher granularity and richness in knowledge. To alleviate these issues, we introduce OceanGPT, the first-ever LLM in the ocean domain, which is expert in various ocean science tasks. We propose DoInstruct, a novel framework to automatically obtain a large volume of ocean domain instruction data, which generates instructions based on multi-agent collaboration. Additionally, we construct the first oceanography benchmark, OceanBench, to evaluate the capabilities of LLMs in the ocean domain. Though comprehensive experiments, OceanGPT not only shows a higher level of knowledge expertise for oceans science tasks but also gains preliminary embodied intelligence capabilities in ocean technology. Codes, data and checkpoints will soon be available at https://github.com/zjunlp/KnowLM.
Large Language Models (LLMs), such as ChatGPT/GPT-4, have garnered widespread attention owing to their myriad of practical applications, yet their adoption has been constrained by issues of fact-conflicting hallucinations across web platforms. The assessment of factuality in text, produced by LLMs, remains inadequately explored, extending not only to the judgment of vanilla facts but also encompassing the evaluation of factual errors emerging in complex inferential tasks like multi-hop, and etc. In response, we introduce FactCHD, a fact-conflicting hallucination detection benchmark meticulously designed for LLMs. Functioning as a pivotal tool in evaluating factuality within "Query-Respons" contexts, our benchmark assimilates a large-scale dataset, encapsulating a broad spectrum of factuality patterns, such as vanilla, multi-hops, comparison, and set-operation patterns. A distinctive feature of our benchmark is its incorporation of fact-based chains of evidence, thereby facilitating comprehensive and conducive factual reasoning throughout the assessment process. We evaluate multiple LLMs, demonstrating the effectiveness of the benchmark and current methods fall short of faithfully detecting factual errors. Furthermore, we present TRUTH-TRIANGULATOR that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2, aiming to yield more credible detection through the amalgamation of predictive results and evidence. The benchmark dataset and source code will be made available in https://github.com/zjunlp/FactCHD.
In this paper, we focus on editing Multimodal Large Language Models (MLLMs). Compared to editing single-modal LLMs, multimodal model editing is more challenging, which demands a higher level of scrutiny and careful consideration in the editing process. To facilitate research in this area, we construct a new benchmark, dubbed MMEdit, for editing multimodal LLMs and establishing a suite of innovative metrics for evaluation. We conduct comprehensive experiments involving various model editing baselines and analyze the impact of editing different components for multimodal LLMs. Empirically, we notice that previous baselines can implement editing multimodal LLMs to some extent, but the effect is still barely satisfactory, indicating the potential difficulty of this task. We hope that our work can provide the NLP community with insights. Code and dataset are available in https://github.com/zjunlp/EasyEdit.
This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's personality often manifests in the form of their expressed opinions, thereby showcasing different personality traits. Specifically, we construct a new benchmark dataset PersonalityEdit to address this task. Drawing on the theory in Social Psychology, we isolate three representative traits, namely Neuroticism, Extraversion, and Agreeableness, as the foundation for our benchmark. We then gather data using GPT-4, generating responses that not only align with a specified topic but also embody the targeted personality trait. We conduct comprehensive experiments involving various baselines and discuss the representation of personality behavior in LLMs. Our intriguing findings uncover potential challenges of the proposed task, illustrating several remaining issues. We anticipate that our work can provide the NLP community with insights. Code and datasets will be released at https://github.com/zjunlp/EasyEdit.
As the cost associated with fine-tuning Large Language Models (LLMs) continues to rise, recent research efforts have pivoted towards developing methodologies to edit implicit knowledge embedded within LLMs. Yet, there's still a dark cloud lingering overhead -- will knowledge editing trigger butterfly effect? since it is still unclear whether knowledge editing might introduce side effects that pose potential risks or not. This paper pioneers the investigation into the potential pitfalls associated with knowledge editing for LLMs. To achieve this, we introduce new benchmark datasets and propose innovative evaluation metrics. Our results underline two pivotal concerns: (1) Knowledge Conflict: Editing groups of facts that logically clash can magnify the inherent inconsistencies in LLMs-a facet neglected by previous methods. (2) Knowledge Distortion: Altering parameters with the aim of editing factual knowledge can irrevocably warp the innate knowledge structure of LLMs. Experimental results vividly demonstrate that knowledge editing might inadvertently cast a shadow of unintended consequences on LLMs, which warrant attention and efforts for future works. Code will be released at https://github.com/zjunlp/PitfallsKnowledgeEditing.