Large Language Models (LLMs) have recently showcased remarkable generalizability in various domains. Despite their extensive knowledge, LLMs still face challenges in efficiently utilizing encoded knowledge to develop accurate and logical reasoning processes. To mitigate this problem, we introduced Hint-before-Solving Prompting (HSP), which guides the model to generate hints (e.g., specific knowledge or key ideas) for solving the problem and then generate solutions containing intermediate reasoning steps. Since HSP is orthogonal to prompting methods (e.g., Chain-of-Thought (CoT)), we applied HSP to CoT, Least-to-Most, Plan-and-Solve, and Standard promptings. The results of extensive experiments on 6 reasoning benchmarks and 4 open-source LLMs demonstrate that HSP can effectively improve the accuracy of reasoning tasks: (1) By applying high-quality hint-enhanced HSP to CoT prompting, Llama2-70B-Chat shows an improvement of 9.7. (2) Beyond exploring training-free LLM capabilities, we built the HSPMATH dataset based on HSP and fine-tuned Llemma-7B, reaching 64.3 accuracy, surpassing GPT-3.5 and WizardMath-13B. We make our code and dataset publicly available at \url{https://github.com/jinlanfu/HSP}.

The present study introduces the knowledge-augmented generator, which is specifically designed to produce information that remains grounded in contextual knowledge, regardless of alterations in the context. Previous research has predominantly focused on examining hallucinations stemming from static input, such as in the domains of summarization or machine translation. However, our investigation delves into the faithfulness of generative question answering in the presence of dynamic knowledge. Our objective is to explore the existence of hallucinations arising from parametric memory when contextual knowledge undergoes changes, while also analyzing the underlying causes for their occurrence. In order to efficiently address this issue, we propose a straightforward yet effective measure for detecting such hallucinations. Intriguingly, our investigation uncovers that all models exhibit a tendency to generate previous answers as hallucinations. To gain deeper insights into the underlying causes of this phenomenon, we conduct a series of experiments that verify the critical role played by context in hallucination, both during training and testing, from various perspectives.

The applications of large language models (LLMs) have expanded well beyond the confines of text processing, signaling a new era where LLMs are envisioned as generalist language agents capable of operating within complex real-world environments. These environments are often highly expansive, making it impossible for the LLM to process them within its short-term memory. Motivated by recent research on extending the capabilities of LLMs with tools, this paper investigates the intriguing potential of tools to augment LLMs in handling such complexity. To this end, we design customized tools to aid in the proactive exploration within these massive environments. Such tools can serve as a middleware layer shielding the LLM from environmental complexity. In two representative complex environments -- knowledge bases (KBs) and databases -- we demonstrate the significant potential of augmenting language agents with tools in complex environments. Notably, equipped with these tools, GPT-4 achieves 2.8X the performance of the best baseline in tasks requiring access to database content and 2.2X in KB tasks. Our findings illuminate the path for advancing language agents in complex real-world applications.

This short paper highlights the growing importance of information retrieval (IR) engines in the scientific community, addressing the inefficiency of traditional keyword-based search engines due to the rising volume of publications. The proposed solution involves structured records, underpinning advanced information technology (IT) tools, including visualization dashboards, to revolutionize how researchers access and filter articles, replacing the traditional text-heavy approach. This vision is exemplified through a proof of concept centered on the ``reproductive number estimate of infectious diseases'' research theme, using a fine-tuned large language model (LLM) to automate the creation of structured records to populate a backend database that now goes beyond keywords. The result is a next-generation IR method accessible at https://orkg.org/usecases/r0-estimates.

The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this amplified context can inadvertently increase inference latency, potentially undermining the developer experience and deterring tool adoption - a challenge we termed the Context-Latency Conundrum. This paper introduces REPOFUSE, a pioneering solution designed to enhance repository-level code completion without the latency trade-off. REPOFUSE uniquely fuses two types of context: the analogy context, rooted in code analogies, and the rationale context, which encompasses in-depth semantic relationships. We propose a novel rank truncated generation (RTG) technique that efficiently condenses these contexts into prompts with restricted size. This enables REPOFUSE to deliver precise code completions while maintaining inference efficiency. Through testing with the CrossCodeEval suite, REPOFUSE has demonstrated a significant leap over existing models, achieving a 40.90% to 59.75% increase in exact match (EM) accuracy for code completions and a 26.8% enhancement in inference speed. Beyond experimental validation, REPOFUSE has been integrated into the workflow of a large enterprise, where it actively supports various coding tasks.

Recent developments in natural language processing (NLP) have highlighted the need for substantial amounts of data for models to capture textual information accurately. This raises concerns regarding the computational resources and time required for training such models. This paper introduces Semantics for data SAliency in Model performance Estimation (SeSaME). It is an efficient data sampling mechanism solely based on textual information without passing the data through a compute-heavy model or other intensive pre-processing transformations. The application of this approach is demonstrated in the use case of low-resource automated speech recognition (ASR) models, which excessively rely on text-to-speech (TTS) calls when using augmented data. SeSaME learns to categorize new incoming data points into speech recognition difficulty buckets by employing semantic similarity-based graph structures and discrete ASR information from homophilous neighbourhoods through message passing. The results indicate reliable projections of ASR performance, with a 93% accuracy increase when using the proposed method compared to random predictions, bringing non-trivial information on the impact of textual representations in speech models. Furthermore, a series of experiments show both the benefits and challenges of using the ASR information on incoming data to fine-tune the model. We report a 7% drop in validation loss compared to random sampling, 7% WER drop with non-local aggregation when evaluating against a highly difficult dataset, and 1.8% WER drop with local aggregation and high semantic similarity between datasets.

Rationales behind answers not only explain model decisions but boost language models to reason well on complex reasoning tasks. However, obtaining impeccable rationales is often impossible. Besides, it is non-trivial to estimate the degree to which the rationales are faithful enough to encourage model performance. Thus, such reasoning tasks often compel models to output correct answers under undesirable rationales and are sub-optimal compared to what the models are fully capable of. In this work, we propose how to deal with imperfect rationales causing aleatoric uncertainty. We first define the ambiguous rationales with entropy scores of given rationales, using model prior beliefs as informativeness. We then guide models to select one of two different reasoning models according to the ambiguity of rationales. We empirically argue that our proposed method produces robust performance superiority against the adversarial quality of rationales and low-resource settings.

Posidonia oceanica is a protected endemic seagrass of Mediterranean sea that fosters biodiversity, stores carbon, releases oxygen, and provides habitat to numerous sea organisms. Leveraging augmented research, we collected a comprehensive dataset of 174 features compiled from diverse data sources. Through machine learning analysis, we discovered the existence of a robust correlation between the exact location of P. oceanica and water biogeochemical properties. The model's feature importance, showed that carbon-related variables as net biomass production and downward surface mass flux of carbon dioxide have their values altered in the areas with P. oceanica, which in turn can be used for indirect location of P. oceanica meadows. The study provides the evidence of the plant's ability to exert a global impact on the environment and underscores the crucial role of this plant in sea ecosystems, emphasizing the need for its conservation and management.

The use of machine learning algorithms in healthcare can amplify social injustices and health inequities. While the exacerbation of biases can occur and compound during the problem selection, data collection, and outcome definition, this research pertains to some generalizability impediments that occur during the development and the post-deployment of machine learning classification algorithms. Using the Framingham coronary heart disease data as a case study, we show how to effectively select a probability cutoff to convert a regression model for a dichotomous variable into a classifier. We then compare the sampling distribution of the predictive performance of eight machine learning classification algorithms under four training/testing scenarios to test their generalizability and their potential to perpetuate biases. We show that both the Extreme Gradient Boosting, and Support Vector Machine are flawed when trained on an unbalanced dataset. We introduced and show that the double discriminant scoring of type I is the most generalizable as it consistently outperforms the other classification algorithms regardless of the training/testing scenario. Finally, we introduce a methodology to extract an optimal variable hierarchy for a classification algorithm, and illustrate it on the overall, male and female Framingham coronary heart disease data.

Large language models (LLMs) have revolutionized natural language processing. However, effectively incorporating complex and potentially noisy user interaction data remains a challenge. To address this, we propose User-LLM, a novel framework that leverages user embeddings to contextualize LLMs. These embeddings, distilled from diverse user interactions using self-supervised pretraining, capture latent user preferences and their evolution over time. We integrate these user embeddings with LLMs through cross-attention and soft-prompting, enabling LLMs to dynamically adapt to user context. Our comprehensive experiments on MovieLens, Amazon Review, and Google Local Review datasets demonstrate significant performance gains across various tasks. Notably, our approach outperforms text-prompt-based contextualization on long sequence tasks and tasks that require deep user understanding while being computationally efficient. We further incorporate Perceiver layers to streamline the integration between user encoders and LLMs, reducing computational demands.