With the increasing use of Artificial Intelligence in Natural Language Processing, concerns have been raised regarding the detection of AI-generated text in various domains. This study aims to investigate this issue by proposing a methodology to accurately distinguish AI-generated and human-written book reviews. Our approach utilizes transfer learning, enabling the model to identify generated text across different topics while improving its ability to detect variations in writing style and vocabulary. To evaluate the effectiveness of the proposed methodology, we developed a dataset consisting of real book reviews and AI-generated reviews using the recently proposed Vicuna open-source language model. The experimental results demonstrate that it is feasible to detect the original source of text, achieving an accuracy rate of 96.86%. Our efforts are oriented toward the exploration of the capabilities and limitations of Large Language Models in the context of text identification. Expanding our knowledge in these aspects will be valuable for effectively navigating similar models in the future and ensuring the integrity and authenticity of human-generated content.

Classical Chinese Understanding (CCU) holds significant value in preserving and exploration of the outstanding traditional Chinese culture. Recently, researchers have attempted to leverage the potential of Large Language Models (LLMs) for CCU by capitalizing on their remarkable comprehension and semantic capabilities. However, no comprehensive benchmark is available to assess the CCU capabilities of LLMs. To fill this gap, this paper introduces C$^{3}$bench, a Comprehensive Classical Chinese understanding benchmark, which comprises 50,000 text pairs for five primary CCU tasks, including classification, retrieval, named entity recognition, punctuation, and translation. Furthermore, the data in C$^{3}$bench originates from ten different domains, covering most of the categories in classical Chinese. Leveraging the proposed C$^{3}$bench, we extensively evaluate the quantitative performance of 15 representative LLMs on all five CCU tasks. Our results not only establish a public leaderboard of LLMs' CCU capabilities but also gain some findings. Specifically, existing LLMs are struggle with CCU tasks and still inferior to supervised models. Additionally, the results indicate that CCU is a task that requires special attention. We believe this study could provide a standard benchmark, comprehensive baselines, and valuable insights for the future advancement of LLM-based CCU research. The evaluation pipeline and dataset are available at \url{https://github.com/SCUT-DLVCLab/C3bench}.

Understanding human mobility patterns is essential for various applications, from urban planning to public safety. The individual trajectory such as mobile phone location data, while rich in spatio-temporal information, often lacks semantic detail, limiting its utility for in-depth mobility analysis. Existing methods can infer basic routine activity sequences from this data, lacking depth in understanding complex human behaviors and users' characteristics. Additionally, they struggle with the dependency on hard-to-obtain auxiliary datasets like travel surveys. To address these limitations, this paper defines trajectory semantic inference through three key dimensions: user occupation category, activity sequence, and trajectory description, and proposes the Trajectory Semantic Inference with Large Language Models (TSI-LLM) framework to leverage LLMs infer trajectory semantics comprehensively and deeply. We adopt spatio-temporal attributes enhanced data formatting (STFormat) and design a context-inclusive prompt, enabling LLMs to more effectively interpret and infer the semantics of trajectory data. Experimental validation on real-world trajectory datasets demonstrates the efficacy of TSI-LLM in deciphering complex human mobility patterns. This study explores the potential of LLMs in enhancing the semantic analysis of trajectory data, paving the way for more sophisticated and accessible human mobility research.

The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning and generalization capabilities. Effective planning is crucial for the success of LLM agents in real-world tasks, making it a highly pursued topic in the community. Current planning methods typically translate tasks into executable action sequences. However, determining a feasible or optimal sequence for complex tasks at fine granularity, which often requires compositing long chains of heterogeneous actions, remains challenging. This paper introduces Meta-Task Planning (MTP), a zero-shot methodology for collaborative LLM-based multi-agent systems that simplifies complex task planning by decomposing it into a hierarchy of subordinate tasks, or meta-tasks. Each meta-task is then mapped into executable actions. MTP was assessed on two rigorous benchmarks, TravelPlanner and API-Bank. Notably, MTP achieved an average $\sim40\%$ success rate on TravelPlanner, significantly higher than the state-of-the-art (SOTA) baseline ($2.92\%$), and outperforming $LLM_{api}$-4 with ReAct on API-Bank by $\sim14\%$, showing the immense potential of integrating LLM with multi-agent systems.

Understanding and attributing mental states, known as Theory of Mind (ToM), emerges as a fundamental capability for human social reasoning. While Large Language Models (LLMs) appear to possess certain ToM abilities, the mechanisms underlying these capabilities remain elusive. In this study, we discover that it is possible to linearly decode the belief status from the perspectives of various agents through neural activations of language models, indicating the existence of internal representations of self and others' beliefs. By manipulating these representations, we observe dramatic changes in the models' ToM performance, underscoring their pivotal role in the social reasoning process. Additionally, our findings extend to diverse social reasoning tasks that involve different causal inference patterns, suggesting the potential generalizability of these representations.

The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want the model to reveal confidential information, specific false information, or offensive behavior. To this end, they manipulate their instructions for the LLM by inserting separators or rephrasing them systematically until they reach their goal. Our approach is different. It inserts words from the model vocabulary. We find these words using an optimization procedure and embeddings from another LLM (attacker LLM). We prove our approach by goal hijacking two popular open-source LLMs from the Llama2 and the Flan-T5 families, respectively. We present two main findings. First, our approach creates inconspicuous instructions and therefore it is hard to detect. For many attack cases, we find that even a single word insertion is sufficient. Second, we demonstrate that we can conduct our attack using a different model than the target model to conduct our attack with.

Go-Explore is a powerful family of algorithms designed to solve hard-exploration problems, built on the principle of archiving discovered states, and iteratively returning to and exploring from the most promising states. This approach has led to superhuman performance across a wide variety of challenging problems including Atari games and robotic control, but requires manually designing heuristics to guide exploration, which is time-consuming and infeasible in general. To resolve this, we propose Intelligent Go-Explore (IGE) which greatly extends the scope of the original Go-Explore by replacing these heuristics with the intelligence and internalized human notions of interestingness captured by giant foundation models (FMs). This provides IGE with a human-like ability to instinctively identify how interesting or promising any new state is (e.g. discovering new objects, locations, or behaviors), even in complex environments where heuristics are hard to define. Moreover, IGE offers the exciting and previously impossible opportunity to recognize and capitalize on serendipitous discoveries that cannot be predicted ahead of time. We evaluate IGE on a range of language-based tasks that require search and exploration. In Game of 24, a multistep mathematical reasoning problem, IGE reaches 100% success rate 70.8% faster than the best classic graph search baseline. Next, in BabyAI-Text, a challenging partially observable gridworld, IGE exceeds the previous SOTA with orders of magnitude fewer online samples. Finally, in TextWorld, we show the unique ability of IGE to succeed in settings requiring long-horizon exploration where prior SOTA FM agents like Reflexion completely fail. Overall, IGE combines the tremendous strengths of FMs and the powerful Go-Explore algorithm, opening up a new frontier of research into creating more generally capable agents with impressive exploration capabilities.

The wide acceptance of large language models (LLMs) has unlocked new applications and social risks. Popular countermeasures aim at detecting misinformation, usually involve domain specific models trained to recognize the relevance of any information. Instead of evaluating the validity of the information, we propose to investigate LLM generated text from the perspective of trust. In this study, we define trust as the ability to know if an input text was generated by a LLM or a human. To do so, we design SPOT, an efficient method, that classifies the source of any, standalone, text input based on originality score. This score is derived from the prediction of a given LLM to detect other LLMs. We empirically demonstrate the robustness of the method to the architecture, training data, evaluation data, task and compression of modern LLMs.

Uncertainty quantification in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. In particular, uncertainty can be used to improve the trustworthiness of LLMs by detecting factually incorrect model responses, commonly called hallucinations. Critically, one should seek to capture the model's semantic uncertainty, i.e., the uncertainty over the meanings of LLM outputs, rather than uncertainty over lexical or syntactic variations that do not affect answer correctness. To address this problem, we propose Kernel Language Entropy (KLE), a novel method for uncertainty estimation in white- and black-box LLMs. KLE defines positive semidefinite unit trace kernels to encode the semantic similarities of LLM outputs and quantifies uncertainty using the von Neumann entropy. It considers pairwise semantic dependencies between answers (or semantic clusters), providing more fine-grained uncertainty estimates than previous methods based on hard clustering of answers. We theoretically prove that KLE generalizes the previous state-of-the-art method called semantic entropy and empirically demonstrate that it improves uncertainty quantification performance across multiple natural language generation datasets and LLM architectures.

Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people. Despite the advancements in large language models (LLMs), recent agents built with these often neglect the control over discussion tactics, which are essential in communication scenarios and games. As a variant of the famous communication game Werewolf, One Night Ultimate Werewolf (ONUW) requires players to develop strategic discussion policies due to the potential role changes that increase the uncertainty and complexity of the game. In this work, we first present the existence of the Perfect Bayesian Equilibria (PBEs) in two scenarios of the ONUW game: one with discussion and one without. The results showcase that the discussion greatly changes players' utilities by affecting their beliefs, emphasizing the significance of discussion tactics. Based on the insights obtained from the analyses, we propose an RL-instructed language agent framework, where a discussion policy trained by reinforcement learning (RL) is employed to determine appropriate discussion tactics to adopt. Our experimental results on several ONUW game settings demonstrate the effectiveness and generalizability of our proposed framework.