Training large language models is a computationally intensive process that often requires substantial resources to achieve state-of-the-art results. Incremental layer-wise training has been proposed as a potential strategy to optimize the training process by progressively introducing layers, with the expectation that this approach would lead to faster convergence and more efficient use of computational resources. In this paper, we investigate the effectiveness of incremental training for LLMs, dividing the training process into multiple stages where layers are added progressively. Our experimental results indicate that while the incremental approach initially demonstrates some computational efficiency, it ultimately requires greater overall computational costs to reach comparable performance to traditional full-scale training. Although the incremental training process can eventually close the performance gap with the baseline, it does so only after significantly extended continual training. These findings suggest that incremental layer-wise training may not be a viable alternative for training large language models, highlighting its limitations and providing valuable insights into the inefficiencies of this approach.

How to efficiently serve LLMs in practice has become exceptionally challenging due to their prohibitive memory and computation requirements. In this study, we investigate optimizing the KV cache, whose memory footprint poses a critical bottleneck in LLM inference, especially when dealing with long context tasks. To tackle the challenge, we introduce MiniKV, a KV cache optimization method that simultaneously preserves long context task accuracy while significantly reducing KV cache size via a novel 2-bit layer-discriminative KV cache. More importantly, we develop specialized CUDA kernels to make MiniKV compatible with FlashAttention. Experiments on a wide range of long context tasks show that MiniKV effectively achieves 86% KV cache compression ratio while recovering over 98.5% of accuracy, outperforming state-of-the-art methods while achieving excellent measured system performance improvements. On a separate line of research, researchers have studied selective KV methods, where the LLM model selects a small Large language models (LLMs) have exhibited unique capabilities subset of KV states based on their importance (Zhang et al., such as instruction following, commonsense reasoning, 2023; Xiao et al., 2023b; Ge et al., 2023; Liu et al., 2023b). O proposes to dynamically keep a subset OpenAI, 2023).

The impressive essay writing and problem-solving capabilities of large language models (LLMs) like OpenAI's ChatGPT have opened up new avenues in education. Our goal is to gain insights into the widespread use of LLMs among secondary students to inform their future development. Despite school restrictions, our survey of over 300 middle and high school students revealed that a remarkable 70% of students have utilized LLMs, higher than the usage percentage among young adults, and this percentage remains consistent across 7th to 12th grade. Students also reported using LLMs for multiple subjects, including language arts, history, and math assignments, but expressed mixed thoughts on their effectiveness due to occasional hallucinations in historical contexts and incorrect answers for lack of rigorous reasoning. The survey feedback called for LLMs better adapted for students, and also raised questions to developers and educators on how to help students from underserved communities leverage LLMs' capabilities for equal access to advanced education resources. We propose a few ideas to address such issues, including subject-specific models, personalized learning, and AI classrooms.

Systems that answer questions by reviewing the scientific literature are becoming increasingly feasible. To draw reliable conclusions, these systems should take into account the quality of available evidence, placing more weight on studies that use a valid methodology. We present a benchmark for measuring the methodological strength of biomedical papers, drawing on the risk-of-bias framework used for systematic reviews. The four benchmark tasks, drawn from more than 500 papers, cover the analysis of research study methodology, followed by evaluation of risk of bias in these studies. The benchmark contains 2000 expert-generated bias annotations, and a human-validated pipeline for fine-grained alignment with research paper content. We evaluate a range of large language models on the benchmark, and find that these models fall significantly short of expert-level performance. By providing a standardized tool for measuring judgments of study quality, the benchmark can help to guide systems that perform large-scale aggregation of scientific data.

Given the advancements in conversational artificial intelligence, the evaluation and assessment of Large Language Models (LLMs) play a crucial role in ensuring optimal performance across various conversational tasks. In this paper, we present a comprehensive study that thoroughly evaluates the capabilities and limitations of five prevalent LLMs: Llama, OPT, Falcon, Alpaca, and MPT. The study encompasses various conversational tasks, including reservation, empathetic response generation, mental health and legal counseling, persuasion, and negotiation. To conduct the evaluation, an extensive test setup is employed, utilizing multiple evaluation criteria that span from automatic to human evaluation. This includes using generic and task-specific metrics to gauge the LMs' performance accurately. From our evaluation, no single model emerges as universally optimal for all tasks. Instead, their performance varies significantly depending on the specific requirements of each task. While some models excel in certain tasks, they may demonstrate comparatively poorer performance in others. These findings emphasize the importance of considering task-specific requirements and characteristics when selecting the most suitable LM for conversational applications.

Language-conditioned robot models (i.e., robotic foundation models) enable robots to perform a wide range of tasks based on natural language instructions. Despite strong performance on existing benchmarks, evaluating the safety and effectiveness of these models is challenging due to the complexity of testing all possible language variations. Current benchmarks have two key limitations: they rely on a limited set of human-generated instructions, missing many challenging cases, and they focus only on task performance without assessing safety, such as avoiding damage. To address these gaps, we introduce Embodied Red Teaming (ERT), a new evaluation method that generates diverse and challenging instructions to test these models. ERT uses automated red teaming techniques with Vision Language Models (VLMs) to create contextually grounded, difficult instructions. Experimental results show that state-of-the-art models frequently fail or behave unsafely on ERT tests, underscoring the shortcomings of current benchmarks in evaluating real-world performance and safety. Code and videos are available at: https://sites.google.com/view/embodiedredteam.

As events progress, news articles often update with new information: if we are not cautious, we risk propagating outdated facts. In this work, we hypothesize that linguistic features indicate factual fluidity, and that we can predict which facts in a news article will update using solely the text of a news article (i.e. not external resources like search engines). We test this hypothesis, first, by isolating fact-updates in large news revisions corpora. News articles may update for many reasons (e.g. factual, stylistic, narrative). We introduce the NewsEdits 2.0 taxonomy, an edit-intentions schema that separates fact updates from stylistic and narrative updates in news writing. We annotate over 9,200 pairs of sentence revisions and train high-scoring ensemble models to apply this schema. Then, taking a large dataset of silver-labeled pairs, we show that we can predict when facts will update in older article drafts with high precision. Finally, to demonstrate the usefulness of these findings, we construct a language model question asking (LLM-QA) abstention task. We wish the LLM to abstain from answering questions when information is likely to become outdated. Using our predictions, we show, LLM absention reaches near oracle levels of accuracy.

Despite their promise to perform complex reasoning, large language models (LLMs) have been shown to have limited effectiveness in end-to-end planning. This has inspired an intriguing question: if these models cannot plan well, can they still contribute to the planning framework as a helpful plan evaluator? In this work, we generalize this question to consider LLMs augmented with visual understanding, i.e., Vision-Language Models (VLMs). We introduce PathEval, a novel benchmark evaluating VLMs as plan evaluators in complex path-planning scenarios. Succeeding in the benchmark requires a VLM to be able to abstract traits of optimal paths from the scenario description, demonstrate precise low-level perception on each path, and integrate this information to decide the better path. Our analysis of state-of-the-art VLMs reveals that these models face significant challenges on the benchmark. We observe that the VLMs can precisely abstract given scenarios to identify the desired traits and exhibit mixed performance in integrating the provided information. Yet, their vision component presents a critical bottleneck, with models struggling to perceive low-level details about a path. Our experimental results show that this issue cannot be trivially addressed via end-to-end fine-tuning; rather, task-specific discriminative adaptation of these vision encoders is needed for these VLMs to become effective path evaluators.

Recent advances in artificial intelligence have witnessed the emergence of large-scale deep learning models capable of interpreting and generating both textual and imaging data. Such models, typically referred to as foundation models, are trained on extensive corpora of unlabeled data and demonstrate high performance across various tasks. Foundation models have recently received extensive attention from academic, industry, and regulatory bodies. Given the potentially transformative impact that foundation models can have on the field of radiology, this review aims to establish a standardized terminology concerning foundation models, with a specific focus on the requirements of training data, model training paradigms, model capabilities, and evaluation strategies. We further outline potential pathways to facilitate the training of radiology-specific foundation models, with a critical emphasis on elucidating both the benefits and challenges associated with such models. Overall, we envision that this review can unify technical advances and clinical needs in the training of foundation models for radiology in a safe and responsible manner, for ultimately benefiting patients, providers, and radiologists.

Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Logits Evolution Decoding (SLED), a novel decoding framework that enhances the truthfulness of LLMs without relying on external knowledge bases or requiring further fine-tuning. From an optimization perspective, our SLED framework leverages the latent knowledge embedded within the LLM by contrasting the output logits from the final layer with those from early layers. It then utilizes an approximate gradient approach to enable latent knowledge to guide the self-refinement of outputs, thereby effectively improving factual accuracy. Extensive experiments have been conducted on established benchmarks across a diverse range of model families (LLaMA 2, LLaMA 3, Gemma) and scales (from 2B to 70B), including more advanced architectural configurations such as the mixture of experts (MoE). Our evaluation spans a wide variety of tasks, including multi-choice, open-generation, and adaptations to chain-of-thought reasoning tasks. The results demonstrate that SLED consistently improves factual accuracy by up to 20\% compared to existing decoding methods while maintaining natural language fluency and negligible latency overhead. Furthermore, it can be flexibly combined with other decoding methods to further enhance their performance.