This paper proposes Attention-Seeker, an unsupervised keyphrase extraction method that leverages self-attention maps from a Large Language Model to estimate the importance of candidate phrases. Our approach identifies specific components - such as layers, heads, and attention vectors - where the model pays significant attention to the key topics of the text. The attention weights provided by these components are then used to score the candidate phrases. Unlike previous models that require manual tuning of parameters (e.g., selection of heads, prompts, hyperparameters), Attention-Seeker dynamically adapts to the input text without any manual adjustments, enhancing its practical applicability. We evaluate Attention-Seeker on four publicly available datasets: Inspec, SemEval2010, SemEval2017, and Krapivin. Our results demonstrate that, even without parameter tuning, Attention-Seeker outperforms most baseline models, achieving state-of-the-art performance on three out of four datasets, particularly excelling in extracting keyphrases from long documents.

We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training. In terms of model design, we perform a comprehensive comparison between decoder-only multimodal LLMs (e.g., LLaVA) and cross-attention-based models (e.g., Flamingo). Based on the strengths and weaknesses of both approaches, we propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. Furthermore, we introduce a 1-D tile-tagging design for tile-based dynamic high-resolution images, which significantly boosts performance on multimodal reasoning and OCR-related tasks. Regarding training data, we meticulously curate and provide detailed information on our multimodal pretraining and supervised fine-tuning datasets. Our findings indicate that dataset quality and task diversity are more important than scale, even during the pretraining phase, across all architectures. Notably, we develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks while maintaining and even improving text-only performance compared to their LLM backbones. To achieve this, we craft and integrate a high-quality text-only dataset into multimodal training, alongside a substantial amount of multimodal math and reasoning data, leading to enhanced math and coding capabilities across modalities. To advance research in the field, we are releasing the model weights and will open-source the code for the community: https://nvlm-project.github.io/.

Focalization, the perspective through which narrative is presented, is encoded via a wide range of lexico-grammatical features and is subject to reader interpretation. Moreover, trained readers regularly disagree on interpretations, suggesting that this problem may be computationally intractable. In this paper, we provide experiments to test how well contemporary Large Language Models (LLMs) perform when annotating literary texts for focalization mode. Despite the challenging nature of the task, LLMs show comparable performance to trained human annotators in our experiments. We provide a case study working with the novels of Stephen King to demonstrate the usefulness of this approach for computational literary studies, illustrating how focalization can be studied at scale.

Written texts reflect an author's perspective, making the thorough analysis of literature a key research method in fields such as the humanities and social sciences. However, conventional text mining techniques like sentiment analysis and topic modeling are limited in their ability to capture the hierarchical narrative structures that reveal deeper argumentative patterns. To address this gap, we propose a method that leverages large language models (LLMs) to extract and organize these structures into a hierarchical framework. We validate this approach by analyzing public opinions on generative AI collected by Japan's Agency for Cultural Affairs, comparing the narratives of supporters and critics. Our analysis provides clearer visualization of the factors influencing divergent opinions on generative AI, offering deeper insights into the structures of agreement and disagreement.

Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning. While transformer-based architectures have been the de facto in vision-language training, they face challenges like quadratic computational complexity, high GPU memory usage, and difficulty with long-term dependencies. To address these limitations, we introduce MambaVL, a novel model that leverages recent advancements in selective state space modality fusion to efficiently capture long-range dependencies and learn joint representations for vision and language data. MambaVL utilizes a shared state transition matrix across both modalities, allowing the model to capture information about actions from multiple perspectives within the scene. Furthermore, we propose a question-answering task that helps guide the model toward relevant cues. These questions provide critical information about actions, objects, and environmental context, leading to enhanced performance. As a result, MambaVL achieves state-of-the-art performance in action recognition on the Epic-Kitchens-100 dataset and outperforms baseline methods in action anticipation.

AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly correspond to real-world tasks of interest. This paper introduces such a benchmark, designed to measure the accuracy of AI agents in tackling a crucial yet surprisingly challenging aspect of scientific research: computational reproducibility. This task, fundamental to the scientific process, involves reproducing the results of a study using the provided code and data. We introduce CORE-Bench (Computational Reproducibility Agent Benchmark), a benchmark consisting of 270 tasks based on 90 scientific papers across three disciplines (computer science, social science, and medicine). Tasks in CORE-Bench consist of three difficulty levels and include both language-only and vision-language tasks. We provide an evaluation system to measure the accuracy of agents in a fast and parallelizable way, saving days of evaluation time for each run compared to a sequential implementation. We evaluated two baseline agents: the general-purpose AutoGPT and a task-specific agent called CORE-Agent. We tested both variants using two underlying language models: GPT-4o and GPT-4o-mini. The best agent achieved an accuracy of 21% on the hardest task, showing the vast scope for improvement in automating routine scientific tasks. Having agents that can reproduce existing work is a necessary step towards building agents that can conduct novel research and could verify and improve the performance of other research agents. We hope that CORE-Bench can improve the state of reproducibility and spur the development of future research agents.

The development of LLMs has greatly enhanced the intelligence and fluency of question answering, while the emergence of retrieval enhancement has enabled models to better utilize external information. However, the presence of noise and errors in retrieved information poses challenges to the robustness of LLMs. In this work, to evaluate the model's performance under multiple interferences, we first construct a dataset based on machine reading comprehension datasets simulating various scenarios, including critical information absence, noise, and conflicts. To address the issue of model accuracy decline caused by noisy external information, we propose a data augmentation-based fine-tuning method to enhance LLM's robustness against noise. Additionally, contrastive learning approach is utilized to preserve the model's discrimination capability of external information. We have conducted experiments on both existing LLMs and our approach, the results are evaluated by GPT-4, which indicates that our proposed methods improve model robustness while strengthening the model's discrimination capability.

Expressing stressful experiences in words is proven to improve mental and physical health, but individuals often disengage with writing interventions as they struggle to organize their thoughts and emotions. Reflective prompts have been used to provide direction, and large language models (LLMs) have demonstrated the potential to provide tailored guidance. Current systems often limit users' flexibility to direct their reflections. We thus present ExploreSelf, an LLM-driven application designed to empower users to control their reflective journey. ExploreSelf allows users to receive adaptive support through dynamically generated questions. Through an exploratory study with 19 participants, we examine how participants explore and reflect on personal challenges using ExploreSelf. Our findings demonstrate that participants valued the balance between guided support and freedom to control their reflective journey, leading to deeper engagement and insight. Building on our findings, we discuss implications for designing LLM-driven tools that promote user empowerment through effective reflective practices.

Timeline Analysis (TA) plays a crucial role in Timeline Forensics (TF) within the field of Digital Forensics (DF). It focuses on examining and analyzing time-based digital artefacts, such as timestamps derived from event logs, file metadata, and other relevant data, to correlate events linked to cyber incidents and reconstruct their chronological sequence. Traditional tools often struggle to efficiently handle the large volume and variety of data generated during DF investigations and Incident Response (IR) processes. This paper introduces a novel framework, GenDFIR, which combines Rule-Based Artificial Intelligence (R-BAI) algorithms with Large Language Models (LLMs) to enhance and automate the TA process. The proposed approach consists of two key stages: (1) R-BAI is used to identify and select anomalous digital artefacts based on predefined rules. (2) The selected artefacts are then transformed into embeddings for processing by an LLM with the assistance of a Retrieval-Augmented Generation (RAG) agent. The LLM uses its capabilities to perform automated TA on the artefacts and predict potential incident outcomes. To validate the framework, we evaluated its performance, efficiency, and reliability. Several metrics were applied to simulated cyber incident scenarios, which were presented as forensic case documents. Our findings demonstrate the significant potential of integrating R-BAI and LLMs for TA. This innovative approach underscores the power of Generative AI (GenAI), particularly LLMs, and opens up new possibilities for advanced threat detection and incident reconstruction, marking a significant advancement in the field.

Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks. Conditioned on a question and answer-key, does the most likely token match the ground truth? Such benchmarks necessarily fail to evaluate language models' ability to quantify outcome uncertainty. In this work, we focus on the use of language models as risk scores for unrealizable prediction tasks. We introduce folktexts, a software package to systematically generate risk scores using language models, and evaluate them against US Census data products. A flexible API enables the use of different prompting schemes, local or web-hosted models, and diverse census columns that can be used to compose custom prediction tasks. We demonstrate the utility of folktexts through a sweep of empirical insights into the statistical properties of 17 recent large language models across five natural text benchmark tasks. We find that zero-shot risk scores produced by multiple-choice question-answering have high predictive signal but are widely miscalibrated. Base models consistently overestimate outcome uncertainty, while instruction-tuned models underestimate uncertainty and produce over-confident risk scores. In fact, instruction-tuning polarizes answer distribution regardless of true underlying data uncertainty. Conversely, verbally querying models for probability estimates results in substantially improved calibration across all instruction-tuned models. These differences in ability to quantify data uncertainty cannot be revealed in realizable settings, and highlight a blind-spot in the current evaluation ecosystem that \folktexts covers.