RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning
Mingqi Yuan
Roger Creus Castanyer
Bo Li
Xin Jin
Glen Berseth
Wenjun Zeng
2024-05-29
ArXiv (prépublication)
doi.org
arxiv.org
Stress-Testing Capability Elicitation With Password-Locked Models
Ryan Greenblatt
Fabien Roger
Dmitrii Krasheninnikov
David Scott Krueger
2024-05-29
ArXiv (prépublication)
doi.org
arxiv.org
Stress-Testing Capability Elicitation With Password-Locked Models
Ryan Greenblatt
Fabien Roger
Dmitrii Krasheninnikov
David Scott Krueger
To determine the safety of large language models (LLMs), AI developers must be able to assess their dangerous capabilities. But simple promp… (voir plus)ting strategies often fail to elicit an LLM's full capabilities. One way to elicit capabilities more robustly is to fine-tune the LLM to complete the task. In this paper, we investigate the conditions under which fine-tuning-based elicitation suffices to elicit capabilities. To do this, we introduce password-locked models, LLMs fine-tuned such that some of their capabilities are deliberately hidden. Specifically, these LLMs are trained to exhibit these capabilities only when a password is present in the prompt, and to imitate a much weaker LLM otherwise. Password-locked models enable a novel method of evaluating capabilities elicitation methods, by testing whether these password-locked capabilities can be elicited without using the password. We find that a few high-quality demonstrations are often sufficient to fully elicit password-locked capabilities. More surprisingly, fine-tuning can elicit other capabilities that have been locked using the same password, or even different passwords. Furthermore, when only evaluations, and not demonstrations, are available, approaches like reinforcement learning are still often able to elicit capabilities. Overall, our findings suggest that fine-tuning is an effective method of eliciting hidden capabilities of current models, but may be unreliable when high-quality demonstrations are not available, e.g. as may be the case when models' (hidden) capabilities exceed those of human demonstrators.
2024-05-29
ArXiv (prépublication)
doi.org
arxiv.org
On the Limits of Multi-modal Meta-Learning with Auxiliary Task Modulation Using Conditional Batch Normalization
Jordi Armengol-Estap'e
Vincent Michalski
Ramnath Kumar
Pierre-Luc St-Charles
Doina Precup
Samira Ebrahimi Kahou
Few-shot learning aims to learn representations that can tackle novel tasks given a small number of examples. Recent studies show that cross… (voir plus)-modal learning can improve representations for few-shot classification. More specifically, language is a rich modality that can be used to guide visual learning. In this work, we experiment with a multi-modal architecture for few-shot learning that consists of three components: a classifier, an auxiliary network, and a bridge network. While the classifier performs the main classification task, the auxiliary network learns to predict language representations from the same input, and the bridge network transforms high-level features of the auxiliary network into modulation parameters for layers of the few-shot classifier using conditional batch normalization. The bridge should encourage a form of lightweight semantic alignment between language and vision which could be useful for the classifier. However, after evaluating the proposed approach on two popular few-shot classification benchmarks we find that a) the improvements do not reproduce across benchmarks, and b) when they do, the improvements are due to the additional compute and parameters introduced by the bridge network. We contribute insights and recommendations for future work in multi-modal meta-learning, especially when using language representations.
2024-05-29
ArXiv (prépublication)
doi.org
arxiv.org
Arbuscular and ectomycorrhizal tree seedling growth is inhibited by competition from neighboring roots and associated fungal hyphae
V. Parasquive
Jacques Brisson
Étienne Laliberté
P. L. Chagnon
2024-05-28
Plant and Soil (publié)
doi.org
ERS0: Enhancing Military Cybersecurity with AI-Driven SBOM for Firmware Vulnerability Detection and Asset Management
Max Beninger
Philippe Charland
Steven H. H. Ding
Benjamin Fung
Firmware vulnerability detection and asset management through a software bill of material (SBOM) approach is integral to defensive military … (voir plus)operations. SBOMs provide a comprehensive list of software components, enabling military organizations to identify vulnerabilities within critical systems, including those controlling various functions in military platforms, as well as in operational technologies and Internet of Things devices. This proactive approach is essential for supply chain security, ensuring that software components are sourced from trusted suppliers and have not been tampered with during production, distribution, or through updates. It is a key element of defense strategies, allowing for rapid assessment, response, and mitigation of vulnerabilities, ultimately safeguarding military capabilities and information from cyber threats. In this paper, we propose ERS0, an SBOM system, driven by artificial intelligence (AI), for detecting firmware vulnerabilities and managing firmware assets. We harness the power of pre-trained large-scale language models to effectively address a wide array of string patterns, extending our coverage to thousands of third-party library patterns. Furthermore, we employ AI-powered code clone search models, enabling a more granular and precise search for vulnerabilities at the binary level, reducing our dependence on string analysis only. Additionally, our AI models extract high-level behavioral functionalities in firmware, such as communication and encryption, allowing us to quantitatively define the behavioral scope of firmware. In preliminary comparative assessments against open-source alternatives, our solution has demonstrated better SBOM coverage, accuracy in vulnerability identification, and a wider array of features.
2024-05-28
2024 16th International Conference on Cyber Conflict: Over the Horizon (CyCon) (publié)
doi.org
Structured Learning in Time-dependent Cox Models
Guanbo Wang
Yi Lian
Archer Yang
Robert W. Platt
Rui Wang
Sylvie Perreault
Marc Dorais
Mireille E. Schnitzer
2024-05-28
Statistics in Medicine (publié)
doi.org
arxiv.org
The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity
Prakhar Ganesh
Ihsan Ibrahim Daldaban
Ignacio Cofone
Golnoosh Farnadi
Model multiplicity, the phenomenon where multiple models achieve similar performance despite different underlying learned functions, introdu… (voir plus)ces arbitrariness in model selection. While this arbitrariness may seem inconsequential in expectation, its impact on individuals can be severe. This paper explores various individual concerns stemming from multiplicity, including the effects of arbitrariness beyond final predictions, disparate arbitrariness for individuals belonging to protected groups, and the challenges associated with the arbitrariness of a single algorithmic system creating a monopoly across various contexts. It provides both an empirical examination of these concerns and a comprehensive analysis from the legal standpoint, addressing how these issues are perceived in the anti-discrimination law in Canada. We conclude the discussion with technical challenges in the current landscape of model multiplicity to meet legal requirements and the legal gap between current law and the implications of arbitrariness in model selection, highlighting relevant future research directions for both disciplines.
2024-05-28
ArXiv (prépublication)
doi.org
arxiv.org
Towards a Reliable French Speech Recognition Tool for an Automated Diagnosis of Learning Disabilities
Jihene Rezgui
Félix Jobin
Younes Kechout
Chritine Turgeon
Foutse Khomh
Dyslexia, characterized by severe challenges in reading and spelling acquisition, presents a substantial barrier to proficient literacy, res… (voir plus)ulting in significantly reduced reading speed (2 to 3 times slower) and diminished text comprehension. With a prevalence ranging from 5G to 10% in the population, early intervention by speech and language pathologists (SLPs) can mitigate dyslexia's effects, but the diagnosis bottleneck impedes timely support. To address this, we propose leveraging machine learning tools to expedite the diagnosis process, focusing on automating phonetic transcription, a critical step in dyslexia assessment. We investigated the practicality of two model configurations utilizing Google's speech-to-text API with children speech in evaluation scenarios and compared their results against transcriptions crafted by experts. The first configuration focuses on Google API's speech-to-text while the second integrates Phonemizer, a text-to-phonemes tool based on a dictionary. Results analysis indicate that our Google-Phonemizer model yields reading accuracies comparable to those computed from human-made transcriptions, offering promise for clinical application. These findings underscore the potential of AI-driven solutions to enhance dyslexia diagnosis efficiency, paving the way for improved accessibility to vital SLP services.
2024-05-28
2024 International Conference on Smart Applications, Communications and Networking (SmartNets) (publié)
doi.org
Advancing Cultural Inclusivity: Optimizing Embedding Spaces for Balanced Music Recommendations
Armin Moradi
Nicola Neophytou
Golnoosh Farnadi
2024-05-27
ArXiv (prépublication)
doi.org
arxiv.org
Comparative Study of Large Language Model Architectures on Frontier
Junqi Yin
Joey Bose
Guojing Cong
Isaac Lyngaas
Quentin Gregory Anthony
Large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-traine… (voir plus)d Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However, these variants have undergone pre-training under diverse conditions, including variations in input data, data preprocessing, and training methodologies, resulting in a lack of controlled comparative studies. Here we meticulously examine two prominent open-sourced GPT architectures, GPT-NeoX and LLaMA, leveraging the computational power of Frontier, the world’s first Exascale supercomputer. Employing the same materials science text corpus and a comprehensive end-to-end pipeline, we conduct a comparative analysis of their training and downstream performance. Our efforts culminate in achieving state-of-the-art performance on a challenging materials science benchmark. Furthermore, we investigate the computation and energy efficiency, and propose a computationally efficient method for architecture design. To our knowledge, these pre-trained models represent the largest available for materials science. Our findings provide practical guidance for building LLMs on HPC platforms.
2024-05-27
2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (publié)
doi.org
arxiv.org
Distilling Privileged Multimodal Information for Expression Recognition using Optimal Transport
Muhammad Haseeb Aslam
Muhammad Osama Zeeshan
Soufiane Belharbi
Marco Pedersoli
Alessandro Lameiras Koerich
Simon Bacon
Eric Granger
Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments because… (voir plus) of their ability to learn complementary and redundant semantic information. However, these models struggle in the wild, mainly because of the unavailability and quality of modalities used for training. In practice, only a subset of the training-time modalities may be available at test time. Learning with privileged information enables models to exploit data from additional modalities that are only available during training. State-of-the-art knowledge distillation (KD) methods have been proposed to distill information from multiple teacher models (each trained on a modality) to a common student model. These privileged KD methods typically utilize point-to-point matching, yet have no explicit mechanism to capture the structural information in the teacher representation space formed by introducing the privileged modality. We argue that encoding this same structure in the student space may lead to enhanced student performance. This paper introduces a new structural KD mechanism based on optimal transport (OT), where entropy-regularized OT distills the structural dark knowledge. Our privileged KD with OT (PKDOT) method captures the local structures in the multimodal teacher representation by calculating a cosine similarity matrix and selecting the top-k anchors to allow for sparse OT solutions, resulting in a more stable distillation process. Experiments1 were performed on two challenging problems - pain estimation on the Biovid dataset (ordinal classification) and arousal-valance prediction on the Affwild2 dataset (regression). Results show that our proposed method can outperform state-of-the-art privileged KD methods on these problems. The diversity among modalities and fusion architectures indicates that PKDOT is modality-and model-agnostic.
2024-05-27
2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG) (publié)
doi.org
arxiv.org