Building a general-purpose agent is a long-standing vision in the field of artificial intelligence. Existing agents have made remarkable progress in many domains, yet they still struggle to complete long-horizon tasks in an open world. We attribute this to the lack of necessary world knowledge and multimodal experience that can guide agents through a variety of long-horizon tasks. In this paper, we propose a Hybrid Multimodal Memory module to address the above challenges. It 1) transforms knowledge into Hierarchical Directed Knowledge Graph that allows agents to explicitly represent and learn world knowledge, and 2) summarises historical information into Abstracted Multimodal Experience Pool that provide agents with rich references for in-context learning. On top of the Hybrid Multimodal Memory module, a multimodal agent, Optimus-1, is constructed with dedicated Knowledge-guided Planner and Experience-Driven Reflector, contributing to a better planning and reflection in the face of long-horizon tasks in Minecraft. Extensive experimental results show that Optimus-1 significantly outperforms all existing agents on challenging long-horizon task benchmarks, and exhibits near human-level performance on many tasks. In addition, we introduce various Multimodal Large Language Models (MLLMs) as the backbone of Optimus-1. Experimental results show that Optimus-1 exhibits strong generalization with the help of the Hybrid Multimodal Memory module, outperforming the GPT-4V baseline on many tasks.
An emerging topic in large language models (LLMs) is their application to time series forecasting, characterizing mainstream and patternable characteristics of time series. A relevant but rarely explored and more challenging question is whether LLMs can detect and explain time series anomalies, a critical task across various real-world applications. In this paper, we investigate the capabilities of LLMs, specifically GPT-4 and LLaMA3, in detecting and explaining anomalies in time series. Our studies reveal that: 1) LLMs cannot be directly used for time series anomaly detection. 2) By designing prompt strategies such as in-context learning and chain-of-thought prompting, GPT-4 can detect time series anomalies with results competitive to baseline methods. 3) We propose a synthesized dataset to automatically generate time series anomalies with corresponding explanations. By applying instruction fine-tuning on this dataset, LLaMA3 demonstrates improved performance in time series anomaly detection tasks. In summary, our exploration shows the promising potential of LLMs as time series anomaly detectors.
Generative artificial intelligence (GAI) is a promising technique towards 6G networks, and generative foundation models such as large language models (LLMs) have attracted considerable interest from academia and telecom industry. This work considers a novel edge-cloud deployment of foundation models in 6G networks. Specifically, it aims to minimize the service delay of foundation models by radio resource allocation and task offloading, i.e., offloading diverse content generation tasks to proper LLMs at the network edge or cloud. In particular, we first introduce the communication system model, i.e., allocating radio resources and calculating link capacity to support generated content transmission, and then we present the LLM inference model to calculate the delay of content generation. After that, we propose a novel in-context learning method to optimize the task offloading decisions. It utilizes LLM's inference capabilities, and avoids the difficulty of dedicated model training or fine-tuning as in conventional machine learning algorithms. Finally, the simulations demonstrate that the proposed edge-cloud deployment and in-context learning task offloading method can achieve satisfactory generation service quality without dedicated model training or fine-tuning.
Large language model (LLM) has recently been considered a promising technique for many fields. This work explores LLM-based wireless network optimization via in-context learning. To showcase the potential of LLM technologies, we consider the base station (BS) power control as a case study, a fundamental but crucial technique that is widely investigated in wireless networks. Different from existing machine learning (ML) methods, our proposed in-context learning algorithm relies on LLM's inference capabilities. It avoids the complexity of tedious model training and hyper-parameter fine-tuning, which is a well-known bottleneck of many ML algorithms. Specifically, the proposed algorithm first describes the target task via formatted natural language, and then designs the in-context learning framework and demonstration examples. After that, it considers two cases, namely discrete-state and continuous-state problems, and proposes state-based and ranking-based methods to select appropriate examples for these two cases, respectively. Finally, the simulations demonstrate that the proposed algorithm can achieve comparable performance as conventional deep reinforcement learning (DRL) techniques without dedicated model training or fine-tuning. Such an efficient and low-complexity approach has great potential for future wireless network optimization.
As content generated by Large Language Model (LLM) has grown exponentially, the ability to accurately identify and fingerprint such text has become increasingly crucial. In this work, we introduce a novel black-box approach for fingerprinting LLMs, achieving an impressive 72% accuracy in identifying the correct family of models (Such as Llama, Mistral, Gemma, etc) among a lineup of LLMs. We present an evolutionary strategy that leverages the capabilities of one LLM to discover the most salient features for identifying other LLMs. Our method employs a unique "Hide and Seek" algorithm, where an Auditor LLM generates discriminative prompts, and a Detective LLM analyzes the responses to fingerprint the target models. This approach not only demonstrates the feasibility of LLM-driven model identification but also reveals insights into the semantic manifolds of different LLM families. By iteratively refining prompts through in-context learning, our system uncovers subtle distinctions between model outputs, providing a powerful tool for LLM analysis and verification. This research opens new avenues for understanding LLM behavior and has significant implications for model attribution, security, and the broader field of AI transparency.
Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed beliefs and sharpening them as it gathers more information. A sequence model learns the relationship between observations, which differs from typical Bayesian models that quantify uncertainty over latent parameters through priors and likelihoods (e.g., topic models). Despite the apparent difference, we illustrate how exchangeable sequence modeling provides a valid Bayesian model by going back to De Finetti's classical predictive view of probabilistic reasoning: uncertainty comes from data that has not been observed yet, rather than latent parameters. From this perspective, pre-training autoregressive models is equivalent to formulating informed beliefs based on prior observations ("empirical Bayes"), and forward generation is equivalent to simulating instantiations of an environment ("posterior inference"). In particular, exchangeable sequence models can explicitly perform statistical inference; epistemic uncertainty over latent environments is captured by variation in predicted future observations. Formally, we show the sequence prediction loss controls the quality of uncertainty quantification, and propose several approaches for encoding exchangeability in sequence model architectures: data augmentation, regularization, and causal masking.
Event Causality Extraction (ECE) aims at extracting causal event pairs from texts. Despite ChatGPT's recent success, fine-tuning small models remains the best approach for the ECE task. However, existing fine-tuning based ECE methods cannot address all three key challenges in ECE simultaneously: 1) Complex Causality Extraction, where multiple causal-effect pairs occur within a single sentence; 2) Subtask~ Interaction, which involves modeling the mutual dependence between the two subtasks of ECE, i.e., extracting events and identifying the causal relationship between extracted events; and 3) Knowledge Fusion, which requires effectively fusing the knowledge in two modalities, i.e., the expressive pretrained language models and the structured knowledge graphs. In this paper, we propose a unified ECE framework (UniCE to address all three issues in ECE simultaneously. Specifically, we design a subtask interaction mechanism to enable mutual interaction between the two ECE subtasks. Besides, we design a knowledge fusion mechanism to fuse knowledge in the two modalities. Furthermore, we employ separate decoders for each subtask to facilitate complex causality extraction. Experiments on three benchmark datasets demonstrate that our method achieves state-of-the-art performance and outperforms ChatGPT with a margin of at least 30% F1-score. More importantly, our model can also be used to effectively improve the ECE performance of ChatGPT via in-context learning.
Log parsing is a critical step that transforms unstructured log data into structured formats, facilitating subsequent log-based analysis. Traditional syntax-based log parsers are efficient and effective, but they often experience decreased accuracy when processing logs that deviate from the predefined rules. Recently, large language models (LLM) based log parsers have shown superior parsing accuracy. However, existing LLM-based parsers face three main challenges: 1)time-consuming and labor-intensive manual labeling for fine-tuning or in-context learning, 2)increased parsing costs due to the vast volume of log data and limited context size of LLMs, and 3)privacy risks from using commercial models like ChatGPT with sensitive log information. To overcome these limitations, this paper introduces LibreLog, an unsupervised log parsing approach that leverages open-source LLMs (i.e., Llama3-8B) to enhance privacy and reduce operational costs while achieving state-of-the-art parsing accuracy. LibreLog first groups logs with similar static text but varying dynamic variables using a fixed-depth grouping tree. It then parses logs within these groups using three components: i)similarity scoring-based retrieval augmented generation: selects diverse logs within each group based on Jaccard similarity, helping the LLM distinguish between static text and dynamic variables; ii)self-reflection: iteratively query LLMs to refine log templates to improve parsing accuracy; and iii) log template memory: stores parsed templates to reduce LLM queries for improved parsing efficiency. Our evaluation on LogHub-2.0 shows that LibreLog achieves 25% higher parsing accuracy and processes logs 2.7 times faster compared to state-of-the-art LLM-based parsers. In short, LibreLog addresses privacy and cost concerns of using commercial LLMs while achieving state-of-the-arts parsing efficiency and accuracy.
Large language models show a surprising in-context learning ability -- being able to use a prompt to form a prediction for a query, yet without additional training, in stark contrast to old-fashioned supervised learning. Providing a mechanistic interpretation and linking the empirical phenomenon to physics are thus challenging and remain unsolved. We study a simple yet expressive transformer with linear attention and map this structure to a spin glass model with real-valued spins, where the couplings and fields explain the intrinsic disorder in data. The spin glass model explains how the weight parameters interact with each other during pre-training, and further clarifies why an unseen function can be predicted by providing only a prompt yet without further training. Our theory reveals that for single-instance learning, increasing the task diversity leads to the emergence of in-context learning, by allowing the Boltzmann distribution to converge to a unique correct solution of weight parameters. Therefore the pre-trained transformer displays a prediction power in a novel prompt setting. The proposed analytically tractable model thus offers a promising avenue for thinking about how to interpret many intriguing but puzzling properties of large language models.
The FIFA World Cup in Qatar was discussed extensively in the news and on social media. Due to news reports with allegations of human rights violations, there were calls to boycott it. Wearing a OneLove armband was part of a planned protest activity. Controversy around the armband arose when FIFA threatened to sanction captains who wear it. To understand what topics Twitter users Tweeted about and what the opinion of German Twitter users was towards the OneLove armband, we performed an analysis of German Tweets published during the World Cup using in-context learning with LLMs. We validated the labels on human annotations. We found that Twitter users initially discussed the armband's impact, LGBT rights, and politics; after the ban, the conversation shifted towards politics in sports in general, accompanied by a subtle shift in sentiment towards neutrality. Our evaluation serves as a framework for future research to explore the impact of sports activism and evolving public sentiment. This is especially useful in settings where labeling datasets for specific opinions is unfeasible, such as when events are unfolding.
In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrated by Large Language Models (LLMs), existing works are highly dependent on large-scale labeled support sets, not always feasible in practical scenarios. To refine this approach, we focus primarily on an innovative selective annotation mechanism, which precedes the standard demonstration retrieval. We introduce the Language Model-based Determinant Point Process (LM-DPP) that simultaneously considers the uncertainty and diversity of unlabeled instances for optimal selection. Consequently, this yields a subset for annotation that strikes a trade-off between the two factors. We apply LM-DPP to various language models, including GPT-J, LlaMA, and GPT-3. Experimental results on 9 NLU and 2 Generation datasets demonstrate that LM-DPP can effectively select canonical examples. Further analysis reveals that LLMs benefit most significantly from subsets that are both low uncertainty and high diversity.
The aspect-based sentiment analysis (ABSA) is a standard NLP task with numerous approaches and benchmarks, where large language models (LLM) represent the current state-of-the-art. We focus on ABSA subtasks based on Twitter/X data in underrepresented languages. On such narrow tasks, small tuned language models can often outperform universal large ones, providing available and cheap solutions. We fine-tune several LLMs (BERT, BERTweet, Llama2, Llama3, Mistral) for classification of sentiment towards Russia and Ukraine in the context of the ongoing military conflict. The training/testing dataset was obtained from the academic API from Twitter/X during 2023, narrowed to the languages of the V4 countries (Czech Republic, Slovakia, Poland, Hungary). Then we measure their performance under a variety of settings including translations, sentiment targets, in-context learning and more, using GPT4 as a reference model. We document several interesting phenomena demonstrating, among others, that some models are much better fine-tunable on multilingual Twitter tasks than others, and that they can reach the SOTA level with a very small training set. Finally we identify combinations of settings providing the best results.
Knowledge models are fundamental to dialogue systems for enabling conversational interactions, which require handling domain-specific knowledge. Ensuring effective communication in information-providing conversations entails aligning user understanding with the knowledge available to the system. However, dialogue systems often face challenges arising from semantic inconsistencies in how information is expressed in natural language compared to how it is represented within the system's internal knowledge. To address this problem, we study the potential of large language models for conversational grounding, a mechanism to bridge information gaps by establishing shared knowledge between dialogue participants. Our approach involves annotating human conversations across five knowledge domains to create a new dialogue corpus called BridgeKG. Through a series of experiments on this dataset, we empirically evaluate the capabilities of large language models in classifying grounding acts and identifying grounded information items within a knowledge graph structure. Our findings offer insights into how these models use in-context learning for conversational grounding tasks and common prediction errors, which we illustrate with examples from challenging dialogues. We discuss how the models handle knowledge graphs as a semantic layer between unstructured dialogue utterances and structured information items.
This paper aims to extend the code generation capability of large language models (LLMs) to automatically manage comprehensive software requirements from given textual descriptions. Such requirements include both functional (i.e. achieving expected behavior for inputs) and non-functional (e.g., time/space performance, robustness, maintainability) requirements. However, textual descriptions can either express requirements verbosely or may even omit some of them. We introduce ARCHCODE, a novel framework that leverages in-context learning to organize requirements observed in descriptions and to extrapolate unexpressed requirements from them. ARCHCODE generates requirements from given descriptions, conditioning them to produce code snippets and test cases. Each test case is tailored to one of the requirements, allowing for the ranking of code snippets based on the compliance of their execution results with the requirements. Public benchmarks show that ARCHCODE enhances to satisfy functional requirements, significantly improving Pass@k scores. Furthermore, we introduce HumanEval-NFR, the first evaluation of LLMs' non-functional requirements in code generation, demonstrating ARCHCODE's superiority over baseline methods. The implementation of ARCHCODE and the HumanEval-NFR benchmark are both publicly accessible.
The in-context learning ability of Transformer models has brought new possibilities to visual navigation. In this paper, we focus on the video navigation setting, where an in-context navigation policy needs to be learned purely from videos in an offline manner, without access to the actual environment. For this setting, we propose Navigate Only Look Once (NOLO), a method for learning a navigation policy that possesses the in-context ability and adapts to new scenes by taking corresponding context videos as input without finetuning or re-training. To enable learning from videos, we first propose a pseudo action labeling procedure using optical flow to recover the action label from egocentric videos. Then, offline reinforcement learning is applied to learn the navigation policy. Through extensive experiments on different scenes both in simulation and the real world, we show that our algorithm outperforms baselines by a large margin, which demonstrates the in-context learning ability of the learned policy. For videos and more information, visit https://sites.google.com/view/nol0.
Multi-turn dialogues are a key interaction method between humans and Large Language Models (LLMs), as conversations extend over multiple rounds, keeping LLMs' high generation quality and low latency is a challenge. Mainstream LLMs can be grouped into two categories based on masking strategy: causal LLM and prefix LLM. Several works have demonstrated that prefix LLMs tend to outperform causal ones in scenarios that heavily depend on historical context such as multi-turn dialogues or in-context learning, thanks to their bidirectional attention on prefix sequences. However, prefix LLMs have an inherent inefficient training problem in multi-turn dialogue datasets. In addition, the attention mechanism of prefix LLM makes it unable to reuse Key-Value Cache (KV Cache) across dialogue rounds to reduce generation latency. In this paper, we propose a novel masking scheme called Intermittent Semi-working Mask (ISM) to address these problems. Specifically, we apply alternate bidirectional and unidirectional attention on queries and answers in the dialogue history. In this way, ISM is able to maintain the high quality of prefix LLM and low generation latency of causal LLM, simultaneously. Extensive experiments illustrate that our ISM achieves significant performance.
The ability of generative large language models (LLMs) to perform in-context learning has given rise to a large body of research into how best to prompt models for various natural language processing tasks. In this paper, we focus on machine translation (MT), a task that has been shown to benefit from in-context translation examples. However no systematic studies have been published on how best to select examples, and mixed results have been reported on the usefulness of similarity-based selection over random selection. We provide a study covering multiple LLMs and multiple in-context example retrieval strategies, comparing multilingual sentence embeddings. We cover several language directions, representing different levels of language resourcedness (English into French, German, Swahili and Wolof). Contrarily to previously published results, we find that sentence embedding similarity can improve MT, especially for low-resource language directions, and discuss the balance between selection pool diversity and quality. We also highlight potential problems with the evaluation of LLM-based MT and suggest a more appropriate evaluation protocol, adapting the COMET metric to the evaluation of LLMs. Code and outputs are freely available at https://github.com/ArmelRandy/ICL-MT.
Text-to-image (T2I) generative models have revolutionized content creation by transforming textual descriptions into high-quality images. However, these models are vulnerable to jailbreaking attacks, where carefully crafted prompts bypass safety mechanisms to produce unsafe content. While researchers have developed various jailbreak attacks to expose this risk, these methods face significant limitations, including impractical access requirements, easily detectable unnatural prompts, restricted search spaces, and high query demands on the target system. In this paper, we propose JailFuzzer, a novel fuzzing framework driven by large language model (LLM) agents, designed to efficiently generate natural and semantically meaningful jailbreak prompts in a black-box setting. Specifically, JailFuzzer employs fuzz-testing principles with three components: a seed pool for initial and jailbreak prompts, a guided mutation engine for generating meaningful variations, and an oracle function to evaluate jailbreak success. Furthermore, we construct the guided mutation engine and oracle function by LLM-based agents, which further ensures efficiency and adaptability in black-box settings. Extensive experiments demonstrate that JailFuzzer has significant advantages in jailbreaking T2I models. It generates natural and semantically coherent prompts, reducing the likelihood of detection by traditional defenses. Additionally, it achieves a high success rate in jailbreak attacks with minimal query overhead, outperforming existing methods across all key metrics. This study underscores the need for stronger safety mechanisms in generative models and provides a foundation for future research on defending against sophisticated jailbreaking attacks. JailFuzzer is open-source and available at this repository: https://github.com/YingkaiD/JailFuzzer.
Text-aware recommender systems incorporate rich textual features, such as titles and descriptions, to generate item recommendations for users. The use of textual features helps mitigate cold-start problems, and thus, such recommender systems have attracted increased attention. However, we argue that the dependency on item descriptions makes the recommender system vulnerable to manipulation by adversarial sellers on e-commerce platforms. In this paper, we explore the possibility of such manipulation by proposing a new text rewriting framework to attack text-aware recommender systems. We show that the rewriting attack can be exploited by sellers to unfairly uprank their products, even though the adversarially rewritten descriptions are perceived as realistic by human evaluators. Methodologically, we investigate two different variations to carry out text rewriting attacks: (1) two-phase fine-tuning for greater attack performance, and (2) in-context learning for higher text rewriting quality. Experiments spanning 3 different datasets and 4 existing approaches demonstrate that recommender systems exhibit vulnerability against the proposed text rewriting attack. Our work adds to the existing literature around the robustness of recommender systems, while highlighting a new dimension of vulnerability in the age of large-scale automated text generation.
In-context learning (ICL) capabilities are foundational to the success of large language models (LLMs). Recently, context compression has attracted growing interest since it can largely reduce reasoning complexities and computation costs of LLMs. In this paper, we introduce a novel Query-gUIded aTtention cOmpression (QUITO) method, which leverages attention of the question over the contexts to filter useless information. Specifically, we take a trigger token to calculate the attention distribution of the context in response to the question. Based on the distribution, we propose three different filtering methods to satisfy the budget constraints of the context length. We evaluate the QUITO using two widely-used datasets, namely, NaturalQuestions and ASQA. Experimental results demonstrate that QUITO significantly outperforms established baselines across various datasets and downstream LLMs, underscoring its effectiveness. Our code is available at https://github.com/Wenshansilvia/attention_compressor.