As AI systems advance, AI evaluations are becoming an important pillar of regulations for ensuring safety. We argue that such regulation should require developers to explicitly identify and justify key underlying assumptions about evaluations as part of their case for safety. We identify core assumptions in AI evaluations (both for evaluating existing models and forecasting future models), such as comprehensive threat modeling, proxy task validity, and adequate capability elicitation. Many of these assumptions cannot currently be well justified. If regulation is to be based on evaluations, it should require that AI development be halted if evaluations demonstrate unacceptable danger or if these assumptions are inadequately justified. Our presented approach aims to enhance transparency in AI development, offering a practical path towards more effective governance of advanced AI systems.

Knowledge editing aims to efficiently and cost-effectively correct inaccuracies and update outdated information. Recently, there has been growing interest in extending knowledge editing from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs), which integrate both textual and visual information, introducing additional editing complexities. Existing multimodal knowledge editing works primarily focus on text-oriented, coarse-grained scenarios, failing to address the unique challenges posed by multimodal contexts. In this paper, we propose a visual-oriented, fine-grained multimodal knowledge editing task that targets precise editing in images with multiple interacting entities. We introduce the Fine-Grained Visual Knowledge Editing (FGVEdit) benchmark to evaluate this task. Moreover, we propose a Multimodal Scope Classifier-based Knowledge Editor (MSCKE) framework. MSCKE leverages a multimodal scope classifier that integrates both visual and textual information to accurately identify and update knowledge related to specific entities within images. This approach ensures precise editing while preserving irrelevant information, overcoming the limitations of traditional text-only editing methods. Extensive experiments on the FGVEdit benchmark demonstrate that MSCKE outperforms existing methods, showcasing its effectiveness in solving the complex challenges of multimodal knowledge editing.

The capabilities and limitations of Large Language Models have been sketched out in great detail in recent years, providing an intriguing yet conflicting picture. On the one hand, LLMs demonstrate a general ability to solve problems. On the other hand, they show surprising reasoning gaps when compared to humans, casting doubt on the robustness of their generalisation strategies. The sheer volume of data used in the design of LLMs has precluded us from applying the method traditionally used to measure generalisation: train-test set separation. To overcome this, we study what kind of generalisation strategies LLMs employ when performing reasoning tasks by investigating the pretraining data they rely on. For two models of different sizes (7B and 35B) and 2.5B of their pretraining tokens, we identify what documents influence the model outputs for three simple mathematical reasoning tasks and contrast this to the data that are influential for answering factual questions. We find that, while the models rely on mostly distinct sets of data for each factual question, a document often has a similar influence across different reasoning questions within the same task, indicating the presence of procedural knowledge. We further find that the answers to factual questions often show up in the most influential data. However, for reasoning questions the answers usually do not show up as highly influential, nor do the answers to the intermediate reasoning steps. When we characterise the top ranked documents for the reasoning questions qualitatively, we confirm that the influential documents often contain procedural knowledge, like demonstrating how to obtain a solution using formulae or code. Our findings indicate that the approach to reasoning the models use is unlike retrieval, and more like a generalisable strategy that synthesises procedural knowledge from documents doing a similar form of reasoning.

Large language models are increasingly becoming a cornerstone technology in artificial intelligence, the sciences, and society as a whole, yet the optimal strategies for dataset composition and filtering remain largely elusive. Many of the top-performing models lack transparency in their dataset curation and model development processes, posing an obstacle to the development of fully open language models. In this paper, we identify three core data-related challenges that must be addressed to advance open-source language models. These include (1) transparency in model development, including the data curation process, (2) access to large quantities of high-quality data, and (3) availability of artifacts and metadata for dataset curation and analysis. To address these challenges, we release RedPajama-V1, an open reproduction of the LLaMA training dataset. In addition, we release RedPajama-V2, a massive web-only dataset consisting of raw, unfiltered text data together with quality signals and metadata. Together, the RedPajama datasets comprise over 100 trillion tokens spanning multiple domains and with their quality signals facilitate the filtering of data, aiming to inspire the development of numerous new datasets. To date, these datasets have already been used in the training of strong language models used in production, such as Snowflake Arctic, Salesforce's XGen and AI2's OLMo. To provide insight into the quality of RedPajama, we present a series of analyses and ablation studies with decoder-only language models with up to 1.6B parameters. Our findings demonstrate how quality signals for web data can be effectively leveraged to curate high-quality subsets of the dataset, underscoring the potential of RedPajama to advance the development of transparent and high-performing language models at scale.

Retrieval and recommendation are two essential tasks in modern search tools. This paper introduces a novel retrieval-reranking framework leveraging Large Language Models (LLMs) to enhance the spatiotemporal and semantic associated mining and recommendation of relevant unusual climate and environmental events described in news articles and web posts. This framework uses advanced natural language processing techniques to address the limitations of traditional manual curation methods in terms of high labor cost and lack of scalability. Specifically, we explore an optimized solution to employ cutting-edge embedding models for semantically analyzing spatiotemporal events (news) and propose a Geo-Time Re-ranking (GT-R) strategy that integrates multi-faceted criteria including spatial proximity, temporal association, semantic similarity, and category-instructed similarity to rank and identify similar spatiotemporal events. We apply the proposed framework to a dataset of four thousand Local Environmental Observer (LEO) Network events, achieving top performance in recommending similar events among multiple cutting-edge dense retrieval models. The search and recommendation pipeline can be applied to a wide range of similar data search tasks dealing with geospatial and temporal data. We hope that by linking relevant events, we can better aid the general public to gain an enhanced understanding of climate change and its impact on different communities.

The fast development of location-based social networks (LBSNs) has led to significant changes in society, resulting in popular studies of using LBSN data for socioeconomic prediction, e.g., regional population and commercial activity estimation. Existing studies design various graphs to model heterogeneous LBSN data, and further apply graph representation learning methods for socioeconomic prediction. However, these approaches heavily rely on heuristic ideas and expertise to extract task-relevant knowledge from diverse data, which may not be optimal for specific tasks. Additionally, they tend to overlook the inherent relationships between different indicators, limiting the prediction accuracy. Motivated by the remarkable abilities of large language models (LLMs) in commonsense reasoning, embedding, and multi-agent collaboration, in this work, we synergize LLM agents and knowledge graph for socioeconomic prediction. We first construct a location-based knowledge graph (LBKG) to integrate multi-sourced LBSN data. Then we leverage the reasoning power of LLM agent to identify relevant meta-paths in the LBKG for each type of socioeconomic prediction task, and design a semantic-guided attention module for knowledge fusion with meta-paths. Moreover, we introduce a cross-task communication mechanism to further enhance performance by enabling knowledge sharing across tasks at both LLM agent and KG levels. On the one hand, the LLM agents for different tasks collaborate to generate more diverse and comprehensive meta-paths. On the other hand, the embeddings from different tasks are adaptively merged for better socioeconomic prediction. Experiments on two datasets demonstrate the effectiveness of the synergistic design between LLM and KG, providing insights for information sharing across socioeconomic prediction tasks.

Dense retrieval, which aims to encode the semantic information of arbitrary text into dense vector representations or embeddings, has emerged as an effective and efficient paradigm for text retrieval, consequently becoming an essential component in various natural language processing systems. These systems typically focus on optimizing the embedding space by attending to the relevance of text pairs, while overlooking the Boolean logic inherent in language, which may not be captured by current training objectives. In this work, we first investigate whether current retrieval systems can comprehend the Boolean logic implied in language. To answer this question, we formulate the task of Boolean Dense Retrieval and collect a benchmark dataset, BoolQuestions, which covers complex queries containing basic Boolean logic and corresponding annotated passages. Through extensive experimental results on the proposed task and benchmark dataset, we draw the conclusion that current dense retrieval systems do not fully understand Boolean logic in language, and there is a long way to go to improve our dense retrieval systems. Furthermore, to promote further research on enhancing the understanding of Boolean logic for language models, we explore Boolean operation on decomposed query and propose a contrastive continual training method that serves as a strong baseline for the research community.

The growing usage of Large Language Models (LLMs) highlights the demands and challenges in scalable LLM inference systems, affecting deployment and development processes. On the deployment side, there is a lack of comprehensive analysis on the conditions under which a particular scheduler performs better or worse, with performance varying substantially across different schedulers, hardware, models, and workloads. Manually testing each configuration on GPUs can be prohibitively expensive. On the development side, unpredictable performance and unknown upper limits can lead to inconclusive trial-and-error processes, consuming resources on ideas that end up ineffective. To address these challenges, we introduce INFERMAX, an analytical framework that uses inference cost models to compare various schedulers, including an optimal scheduler formulated as a constraint satisfaction problem (CSP) to establish an upper bound on performance. Our framework offers in-depth analysis and raises essential questions, challenging assumptions and exploring opportunities for more efficient scheduling. Notably, our findings indicate that preempting requests can reduce GPU costs by 30% compared to avoiding preemptions at all. We believe our methods and insights will facilitate the cost-effective deployment and development of scalable, efficient inference systems and pave the way for cost-based scheduling.

LLM based copilot assistants are useful in everyday tasks. There is a proliferation in the exploration of AI assistant use cases to support radiology workflows in a reliable manner. In this work, we present RadPhi-3, a Small Language Model instruction tuned from Phi-3-mini-4k-instruct with 3.8B parameters to assist with various tasks in radiology workflows. While impression summary generation has been the primary task which has been explored in prior works w.r.t radiology reports of Chest X-rays, we also explore other useful tasks like change summary generation comparing the current radiology report and its prior report, section extraction from radiology reports, tagging the reports with various pathologies and tubes, lines or devices present in them etc. In-addition, instruction tuning RadPhi-3 involved learning from a credible knowledge source used by radiologists, Radiopaedia.org. RadPhi-3 can be used both to give reliable answers for radiology related queries as well as perform useful tasks related to radiology reports. RadPhi-3 achieves SOTA results on the RaLEs radiology report generation benchmark.

Time series foundation models are pre-trained on large datasets and are able to achieve state-of-the-art performance in diverse tasks. However, to date, there has been limited work demonstrating how well these models perform in medical applications, where labeled data can be scarce. Further, we observe that currently, the majority of time series foundation models either are univariate in nature, or assume channel independence, meaning that they handle multivariate time series but do not model how the different variables relate. In this paper, we propose a prompt-tuning-inspired fine-tuning technique, Generalized Prompt Tuning (Gen-P-Tuning), that enables us to adapt an existing univariate time series foundation model (treated as frozen) to handle multivariate time series prediction. Our approach provides a way to combine information across channels (variables) of multivariate time series. We demonstrate the effectiveness of our fine-tuning approach against various baselines on two MIMIC classification tasks, and on influenza-like illness forecasting.