The rapid development of large language models (LLMs) has necessitated the creation of benchmarks to evaluate their performance. These benchmarks resemble human tests and surveys, as they consist of sets of questions designed to measure emergent properties in the cognitive behavior of these systems. However, unlike the well-defined traits and abilities studied in social sciences, the properties measured by these benchmarks are often vaguer and less rigorously defined. The most prominent benchmarks are often grouped into leaderboards for convenience, aggregating performance metrics and enabling comparisons between models. Unfortunately, these leaderboards typically rely on simplistic aggregation methods, such as taking the average score across benchmarks. In this paper, we demonstrate the advantages of applying contemporary psychometric methodologies - originally developed for human tests and surveys - to improve the ranking of large language models on leaderboards. Using data from the Hugging Face Leaderboard as an example, we compare the results of the conventional naive ranking approach with a psychometrically informed ranking. The findings highlight the benefits of adopting psychometric techniques for more robust and meaningful evaluation of LLM performance.

Retrieval-augmented generation improves various aspects of large language models (LLMs) generation, but suffers from computational overhead caused by long contexts as well as the propagation of irrelevant retrieved information into generated responses. Context pruning deals with both aspects, by removing irrelevant parts of retrieved contexts before LLM generation. Existing context pruning approaches are however limited, and do not provide a universal model that would be both efficient and robust in a wide range of scenarios, e.g., when contexts contain a variable amount of relevant information or vary in length, or when evaluated on various domains. In this work, we close this gap and introduce Provence (Pruning and Reranking Of retrieVEd relevaNt ContExts), an efficient and robust context pruner for Question Answering, which dynamically detects the needed amount of pruning for a given context and can be used out-of-the-box for various domains. The three key ingredients of Provence are formulating the context pruning task as sequence labeling, unifying context pruning capabilities with context reranking, and training on diverse data. Our experimental results show that Provence enables context pruning with negligible to no drop in performance, in various domains and settings, at almost no cost in a standard RAG pipeline. We also conduct a deeper analysis alongside various ablations to provide insights into training context pruners for future work.

Known by more than 1.5 billion people in the Indian subcontinent, Indic languages present unique challenges and opportunities for natural language processing (NLP) research due to their rich cultural heritage, linguistic diversity, and complex structures. IndicMMLU-Pro is a comprehensive benchmark designed to evaluate Large Language Models (LLMs) across Indic languages, building upon the MMLU Pro (Massive Multitask Language Understanding) framework. Covering major languages such as Hindi, Bengali, Gujarati, Marathi, Kannada, Punjabi, Tamil, Telugu, and Urdu, our benchmark addresses the unique challenges and opportunities presented by the linguistic diversity of the Indian subcontinent. This benchmark encompasses a wide range of tasks in language comprehension, reasoning, and generation, meticulously crafted to capture the intricacies of Indian languages. IndicMMLU-Pro provides a standardized evaluation framework to push the research boundaries in Indic language AI, facilitating the development of more accurate, efficient, and culturally sensitive models. This paper outlines the benchmarks' design principles, task taxonomy, and data collection methodology, and presents baseline results from state-of-the-art multilingual models.

Satellite networks are able to collect massive space information with advanced remote sensing technologies, which is essential for real-time applications such as natural disaster monitoring. However, traditional centralized processing by the ground server incurs a severe timeliness issue caused by the transmission bottleneck of raw data. To this end, Space Computing Power Networks (Space-CPN) emerges as a promising architecture to coordinate the computing capability of satellites and enable on board data processing. Nevertheless, due to the natural limitations of solar panels, satellite power system is difficult to meet the energy requirements for ever-increasing intelligent computation tasks of artificial neural networks. To tackle this issue, we propose to employ spiking neural networks (SNNs), which is supported by the neuromorphic computing architecture, for on-board data processing. The extreme sparsity in its computation enables a high energy efficiency. Furthermore, to achieve effective training of these on-board models, we put forward a decentralized neuromorphic learning framework, where a communication-efficient inter-plane model aggregation method is developed with the inspiration from RelaySum. We provide a theoretical analysis to characterize the convergence behavior of the proposed algorithm, which reveals a network diameter related convergence speed. We then formulate a minimum diameter spanning tree problem on the inter-plane connectivity topology and solve it to further improve the learning performance. Extensive experiments are conducted to evaluate the superiority of the proposed method over benchmarks.

Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data duplication on the unlearning process remains largely unexplored. This paper addresses this gap by pioneering a comprehensive investigation into the role of data duplication, not only in standard machine unlearning but also in federated and reinforcement unlearning paradigms. Specifically, we propose an adversary who duplicates a subset of the target model's training set and incorporates it into the training set. After training, the adversary requests the model owner to unlearn this duplicated subset, and analyzes the impact on the unlearned model. For example, the adversary can challenge the model owner by revealing that, despite efforts to unlearn it, the influence of the duplicated subset remains in the model. Moreover, to circumvent detection by de-duplication techniques, we propose three novel near-duplication methods for the adversary, each tailored to a specific unlearning paradigm. We then examine their impacts on the unlearning process when de-duplication techniques are applied. Our findings reveal several crucial insights: 1) the gold standard unlearning method, retraining from scratch, fails to effectively conduct unlearning under certain conditions; 2) unlearning duplicated data can lead to significant model degradation in specific scenarios; and 3) meticulously crafted duplicates can evade detection by de-duplication methods.

The recent proliferation of short form video social media sites such as TikTok has been effectively utilized for increased visibility, communication, and community connection amongst trans/nonbinary creators online. However, these same platforms have also been exploited by right-wing actors targeting trans/nonbinary people, enabling such anti-trans actors to efficiently spread hate speech and propaganda. Given these divergent groups, what are the differences in network structure between anti-trans and pro-trans communities on TikTok, and to what extent do they amplify the effects of anti-trans content? In this paper, we collect a sample of TikTok videos containing pro and anti-trans content, and develop a taxonomy of trans related sentiment to enable the classification of content on TikTok, and ultimately analyze the reply network structures of pro-trans and anti-trans communities. In order to accomplish this, we worked with hired expert data annotators from the trans/nonbinary community in order to generate a sample of highly accurately labeled data. From this subset, we utilized a novel classification pipeline leveraging Retrieval-Augmented Generation (RAG) with annotated examples and taxonomy definitions to classify content into pro-trans, anti-trans, or neutral categories. We find that incorporating our taxonomy and its logics into our classification engine results in improved ability to differentiate trans related content, and that Results from network analysis indicate many interactions between posters of pro-trans and anti-trans content exist, further demonstrating targeting of trans individuals, and demonstrating the need for better content moderation tools

Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater assurance over AI system behavior and shed light on exciting scientific questions about the nature of intelligence. Despite recent progress toward these goals, there are many open problems in the field that require solutions before many scientific and practical benefits can be realized: Our methods require both conceptual and practical improvements to reveal deeper insights; we must figure out how best to apply our methods in pursuit of specific goals; and the field must grapple with socio-technical challenges that influence and are influenced by our work. This forward-facing review discusses the current frontier of mechanistic interpretability and the open problems that the field may benefit from prioritizing. This review collects the perspectives of its various authors and represents a synthesis of their views by Apollo Research on behalf of Schmidt Sciences. The perspectives presented here do not necessarily reflect the views of any individual author or the institutions with which they are affiliated.

Generative AI could enhance scientific discovery by supporting knowledge workers in science organizations. However, the real-world applications and perceived concerns of generative AI use in these organizations are uncertain. In this paper, we report on a collaborative study with a US national laboratory with employees spanning Science and Operations about their use of generative AI tools. We surveyed 66 employees, interviewed a subset (N=22), and measured early adoption of an internal generative AI interface called Argo lab-wide. We have four findings: (1) Argo usage data shows small but increasing use by Science and Operations employees; Common current and envisioned use cases for generative AI in this context conceptually fall into either a (2) copilot or (3) workflow agent modality; and (4) Concerns include sensitive data security, academic publishing, and job impacts. Based on our findings, we make recommendations for generative AI use in science and other organizations.

With the rapid advancement of Artificial Intelligence, particularly in Natural Language Processing, Large Language Models (LLMs) have become pivotal in educational question-answering systems, especially university admission chatbots. Concepts such as Retrieval-Augmented Generation (RAG) and other advanced techniques have been developed to enhance these systems by integrating specific university data, enabling LLMs to provide informed responses on admissions and academic counseling. However, these enhanced RAG techniques often involve high operational costs and require the training of complex, specialized modules, which poses challenges for practical deployment. Additionally, in the educational context, it is crucial to provide accurate answers to prevent misinformation, a task that LLM-based systems find challenging without appropriate strategies and methods. In this paper, we introduce the Unified RAG (URAG) Framework, a hybrid approach that significantly improves the accuracy of responses, particularly for critical queries. Experimental results demonstrate that URAG enhances our in-house, lightweight model to perform comparably to state-of-the-art commercial models. Moreover, to validate its practical applicability, we conducted a case study at our educational institution, which received positive feedback and acclaim. This study not only proves the effectiveness of URAG but also highlights its feasibility for real-world implementation in educational settings.

Retrieval-Augmented Generation (RAG) pipelines enhance Large Language Models (LLMs) by retrieving relevant documents, but they face scalability issues due to high inference costs and limited context size. Document compression is a practical solution, but current soft compression methods suffer from accuracy losses and require extensive pretraining. In this paper, we introduce PISCO, a novel method that achieves a 16x compression rate with minimal accuracy loss (0-3%) across diverse RAG-based question-answering (QA) tasks. Unlike existing approaches, PISCO requires no pretraining or annotated data, relying solely on sequence-level knowledge distillation from document-based questions. With the ability to fine-tune a 7-10B LLM in 48 hours on a single A100 GPU, PISCO offers a highly efficient and scalable solution. We present comprehensive experiments showing that PISCO outperforms existing compression models by 8% in accuracy.