Pre-trained Large Language Models (LLMs) have shown success in a diverse set of language inference and understanding tasks. The pre-training stage of LLMs looks at a large corpus of raw textual data. The BabyLM shared task compares LLM pre-training to human language acquisition, where the number of tokens seen by 13-year-old kids is magnitudes smaller than the number of tokens seen by LLMs. In this work, we pre-train and evaluate LLMs on their ability to learn contextual word representations using roughly the same number of tokens as seen by children. We provide a strong set of baselines; with different architectures, evaluation of changes in performance across epochs, and reported pre-training metrics for the strict small and strict tracks of the task. We also try to loosely replicate the RoBERTa baseline given by the task organizers to observe the training robustness to hyperparameter selection and replicability. We provide the submission details to the strict and strict-small tracks in this report.

Evaluating the significance of a paper is pivotal yet challenging for the scientific community. While the citation count is the most commonly used proxy for this purpose, they are widely criticized for failing to accurately reflect a paper's true impact. In this work, we propose a causal inference method, TextMatch, which adapts the traditional matching framework to high-dimensional text embeddings. Specifically, we encode each paper using the text embeddings by large language models (LLMs), extract similar samples by cosine similarity, and synthesize a counterfactual sample by the weighted average of similar papers according to their similarity values. We apply the resulting metric, called CausalCite, as a causal formulation of paper citations. We show its effectiveness on various criteria, such as high correlation with paper impact as reported by scientific experts on a previous dataset of 1K papers, (test-of-time) awards for past papers, and its stability across various sub-fields of AI. We also provide a set of findings that can serve as suggested ways for future researchers to use our metric for a better understanding of a paper's quality. Our code and data are at https://github.com/causalNLP/causal-cite.

The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity and require a retraining process. As humans step into the era of large language models, these issues become increasingly prominent. This paper proposes that the robustness of language models is proportional to the extent of pre-trained knowledge they encompass. Accordingly, we introduce a post-training pruning strategy designed to faithfully replicate the embedding space and feature space of dense language models, aiming to conserve more pre-trained knowledge during the pruning process. In this setup, each layer's reconstruction error not only originates from itself but also includes cumulative error from preceding layers, followed by an adaptive rectification. Compared to other state-of-art baselines, our approach demonstrates a superior balance between accuracy, sparsity, robustness, and pruning cost with BERT on datasets SST2, IMDB, and AGNews, marking a significant stride towards robust pruning in language models.

8 years after the visual question answering (VQA) task was proposed, accuracy remains the primary metric for automatic evaluation. VQA Accuracy has been effective so far in the IID evaluation setting. However, our community is undergoing a shift towards open-ended generative models and OOD evaluation. In this new paradigm, the existing VQA Accuracy metric is overly stringent and underestimates the performance of VQA systems. Thus, there is a need to develop more robust automatic VQA metrics that serve as a proxy for human judgment. In this work, we propose to leverage the in-context learning capabilities of instruction-tuned large language models (LLMs) to build a better VQA metric. We formulate VQA evaluation as an answer-rating task where the LLM is instructed to score the accuracy of a candidate answer given a set of reference answers. We demonstrate the proposed metric better correlates with human judgment compared to existing metrics across several VQA models and benchmarks. We hope wide adoption of our metric will contribute to better estimating the research progress on the VQA task. We plan to release the evaluation code and collected human judgments.

Metaphors and sarcasm are precious fruits of our highly-evolved social communication skills. However, children with Asperger syndrome are known to have difficulties in comprehending sarcasm, even if they possess a certain level of verbal IQ sufficient for understanding metaphors. Given that, a screening test that scores the ability to understand metaphor and sarcasm has been used to differentiate Asperger syndrome from other symptoms exhibiting akin external behaviors (e.g., attention-deficit/hyperactivity disorder). This study uses the standardized test to examine the capability of recent large language models (LLMs) in understanding human nuanced communication. The results divulged that, whereas their ability to comprehend metaphors has been improved with the increase of the number of model parameters, the improvement in sarcasm understanding was not observed. This implies that an alternative approach is imperative to imbue LLMs with the capacity to grasp sarcasm, which has been associated with the amygdala, a pivotal cerebral region for emotional learning, in the case of humans.

Recent advances in metric, semantic, and topological mapping have equipped autonomous robots with semantic concept grounding capabilities to interpret natural language tasks. This work aims to leverage these new capabilities with an efficient task planning algorithm for hierarchical metric-semantic models. We consider a scene graph representation of the environment and utilize a large language model (LLM) to convert a natural language task into a linear temporal logic (LTL) automaton. Our main contribution is to enable optimal hierarchical LTL planning with LLM guidance over scene graphs. To achieve efficiency, we construct a hierarchical planning domain that captures the attributes and connectivity of the scene graph and the task automaton, and provide semantic guidance via an LLM heuristic function. To guarantee optimality, we design an LTL heuristic function that is provably consistent and supplements the potentially inadmissible LLM guidance in multi-heuristic planning. We demonstrate efficient planning of complex natural language tasks in scene graphs of virtualized real environments.

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this information is unavailable in the real world. Therefore, we focus on a more realistic and challenging setting, named hard-label attack, in which the attacker can only query the model and obtain a discrete prediction label. Existing hard-label attack algorithms tend to initialize adversarial examples by random substitution and then utilize complex heuristic algorithms to optimize the adversarial perturbation. These methods require a lot of model queries and the attack success rate is restricted by adversary initialization. In this paper, we propose a novel hard-label attack algorithm named LimeAttack, which leverages a local explainable method to approximate word importance ranking, and then adopts beam search to find the optimal solution. Extensive experiments show that LimeAttack achieves the better attacking performance compared with existing hard-label attack under the same query budget. In addition, we evaluate the effectiveness of LimeAttack on large language models, and results indicate that adversarial examples remain a significant threat to large language models. The adversarial examples crafted by LimeAttack are highly transferable and effectively improve model robustness in adversarial training.

Vehicle-based voice assistants are the next great frontier, incorporating artificial intelligence into the driving experience. At CES 2024, Amazon and BMW announced a partnership to significantly improve the pre-existing experience, marrying a large language model (LLM) with Alexa and the actual driver's manual. You can ask the Alexa-powered chatbot anything about your car and receive accurate real-time information. That thick and unwieldy manual can stay in the glovebox, for good. Amazon says this tool offers a "more natural way of getting to know your new car."

The European Union is considering whether to launch a review of Microsoft's investment in ChatGPT maker OpenAI under the bloc's merger regulations, a month after the U.K. said it was also weighing whether the tech partnership could have an impact on competition. The European Commission, the EU's executive arm, made the disclosure on Tuesday as it sought input from interested parties on the level of competition in virtual worlds and generative artificial intelligence, and feedback on what competition law can do to keep these new markets competitive.

Microsoft's multibillion-dollar investment in the ChatGPT developer OpenAI could face a merger investigation in the European Union, officials have said. Microsoft is the largest minority investor in OpenAI Global LLC, a "capped profit" subsidiary company that is controlled by OpenAI Inc, the non-profit majority owner of the organisation. Its investment, given in the form of cloud-computing credits as well as cash, officially gives it no control of the company itself, but the possibility of a maximum of a 100-times return on its capital. The European Commission said on Tuesday it was "checking whether Microsoft's investment in OpenAI might be reviewable under the EU merger regulation". OpenAI's unusual corporate structure was thrust into the limelight last year, when its chief executive, Sam Altman, was ousted and then reappointed in a bitter struggle with the non-profit's board.