In the construction industry, where work environments are complex, unstructured and often dangerous, the implementation of Human-Robot Collaboration (HRC) is emerging as a promising advancement. This underlines the critical need for intuitive communication interfaces that enable construction workers to collaborate seamlessly with robotic assistants. This study introduces a conversational Virtual Reality (VR) interface integrating multimodal interaction to enhance intuitive communication between construction workers and robots. By integrating voice and controller inputs with the Robot Operating System (ROS), Building Information Modeling (BIM), and a game engine featuring a chat interface powered by a Large Language Model (LLM), the proposed system enables intuitive and precise interaction within a VR setting. Evaluated by twelve construction workers through a drywall installation case study, the proposed system demonstrated its low workload and high usability with succinct command inputs. The proposed multimodal interaction system suggests that such technological integration can substantially advance the integration of robotic assistants in the construction industry.

By leveraging the retrieval of information from external knowledge databases, Large Language Models (LLMs) exhibit enhanced capabilities for accomplishing many knowledge-intensive tasks. However, due to the inherent flaws of current retrieval systems, there might exist irrelevant information within those retrieving top-ranked passages. In this work, we present a comprehensive investigation into the robustness of LLMs to different types of irrelevant information under various conditions. We initially introduce a framework to construct high-quality irrelevant information that ranges from semantically unrelated, partially related, and related to questions. Furthermore, our analysis demonstrates that the constructed irrelevant information not only scores highly on similarity metrics, being highly retrieved by existing systems, but also bears semantic connections to the context. Our investigation reveals that current LLMs still face challenges in discriminating highly semantically related information and can be easily distracted by these irrelevant yet misleading contents. Besides, we also find that current solutions for handling irrelevant information have limitations in improving the robustness of LLMs to such distractions.

Summary: The vast generation of genetic data poses a significant challenge in efficiently uncovering valuable knowledge. Introducing GENEVIC, an AI-driven chat framework that tackles this challenge by bridging the gap between genetic data generation and biomedical knowledge discovery. Leveraging generative AI, notably ChatGPT, it serves as a biologist's 'copilot'. It automates the analysis, retrieval, and visualization of customized domain-specific genetic information, and integrates functionalities to generate protein interaction networks, enrich gene sets, and search scientific literature from PubMed, Google Scholar, and arXiv, making it a comprehensive tool for biomedical research. In its pilot phase, GENEVIC is assessed using a curated database that ranks genetic variants associated with Alzheimer's disease, schizophrenia, and cognition, based on their effect weights from the Polygenic Score Catalog, thus enabling researchers to prioritize genetic variants in complex diseases. GENEVIC's operation is user-friendly, accessible without any specialized training, secured by Azure OpenAI's HIPAA-compliant infrastructure, and evaluated for its efficacy through real-time query testing. As a prototype, GENEVIC is set to advance genetic research, enabling informed biomedical decisions. Availability and implementation: GENEVIC is publicly accessible at https://genevic-anath2024.streamlit.app. The underlying code is open-source and available via GitHub at https://github.com/anath2110/GENEVIC.git.

Query Reformulation(QR) is a set of techniques used to transform a user's original search query to a text that better aligns with the user's intent and improves their search experience. Recently, zero-shot QR has been shown to be a promising approach due to its ability to exploit knowledge inherent in large language models. By taking inspiration from the success of ensemble prompting strategies which have benefited many tasks, we investigate if they can help improve query reformulation. In this context, we propose an ensemble based prompting technique, GenQREnsemble which leverages paraphrases of a zero-shot instruction to generate multiple sets of keywords ultimately improving retrieval performance. We further introduce its post-retrieval variant, GenQREnsembleRF to incorporate pseudo relevant feedback. On evaluations over four IR benchmarks, we find that GenQREnsemble generates better reformulations with relative nDCG@10 improvements up to 18% and MAP improvements upto 24% over the previous zero-shot state-of-art. On the MSMarco Passage Ranking task, GenQREnsembleRF shows relative gains of 5% MRR using pseudo-relevance feedback, and 9% nDCG@10 using relevant feedback documents.

Modern Large Language Models (LLMs) have showcased remarkable prowess in various tasks necessitating sophisticated cognitive behaviors. Nevertheless, a paradoxical performance discrepancy is observed, where these models underperform in seemingly elementary tasks like relation extraction and event extraction due to two issues in conventional evaluation. (1) The imprecision of existing evaluation metrics that struggle to effectively gauge semantic consistency between model outputs and ground truth, and (2) The inherent incompleteness of evaluation benchmarks, primarily due to restrictive human annotation schemas, resulting in underestimated LLM performances. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. This method innovatively utilizes LLMs, fine-tuned through subjective question correction data, to refine matching between model outputs and golden labels. Additionally, by incorporating a Natural Language Inference (NLI) model, SQC-Score enriches golden labels, addressing benchmark incompleteness by acknowledging correct yet previously omitted answers. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics. Utilizing SQC-Score, we conduct a comprehensive evaluation of the state-of-the-art LLMs and provide insights for future research for information extraction. Dataset and associated codes can be accessed at https://github.com/THU-KEG/SQC-Score.

Recent advances in AI, machine learning, and NLP have led to the development of a new generation of Large Language Models (LLMs) that are trained on massive amounts of data and often have trillions of parameters. Commercial applications (e.g., ChatGPT) have made this technology available to the general public, thus making it possible to use LLMs to produce high-quality texts for academic and professional purposes. Schools and universities are aware of the increasing use of AI-generated content by students and they have been researching the impact of this new technology and its potential misuse. Educational programs in Computer Science (CS) and related fields are particularly affected because LLMs are also capable of generating programming code in various programming languages. To help understand the potential impact of publicly available LLMs in CS education, we introduce CSEPrompts, a framework with hundreds of programming exercise prompts and multiple-choice questions retrieved from introductory CS and programming courses. We also provide experimental results on CSEPrompts to evaluate the performance of several LLMs with respect to generating Python code and answering basic computer science and programming questions.

Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of common factual knowledge information. However, unravelling the underlying reasoning of LLMs and explaining their internal mechanisms of exploiting this factual knowledge remain active areas of investigation. Our work analyzes the factual knowledge encoded in the latent representation of LLMs when prompted to assess the truthfulness of factual claims. We propose an end-to-end framework that jointly decodes the factual knowledge embedded in the latent space of LLMs from a vector space to a set of ground predicates and represents its evolution across the layers using a temporal knowledge graph. Our framework relies on the technique of activation patching which intervenes in the inference computation of a model by dynamically altering its latent representations. Consequently, we neither rely on external models nor training processes. We showcase our framework with local and global interpretability analyses using two claim verification datasets: FEVER and CLIMATE-FEVER. The local interpretability analysis exposes different latent errors from representation to multi-hop reasoning errors. On the other hand, the global analysis uncovered patterns in the underlying evolution of the model's factual knowledge (e.g., store-and-seek factual information). By enabling graph-based analyses of the latent representations, this work represents a step towards the mechanistic interpretability of LLMs.

In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra in solving undergraduate-level control problems. Controls provides an interesting case study for LLM reasoning due to its combination of mathematical theory and engineering design. We introduce ControlBench, a benchmark dataset tailored to reflect the breadth, depth, and complexity of classical control design. We use this dataset to study and evaluate the problem-solving abilities of these LLMs in the context of control engineering. We present evaluations conducted by a panel of human experts, providing insights into the accuracy, reasoning, and explanatory prowess of LLMs in control engineering. Our analysis reveals the strengths and limitations of each LLM in the context of classical control, and our results imply that Claude 3 Opus has become the state-of-the-art LLM for solving undergraduate control problems. Our study serves as an initial step towards the broader goal of employing artificial general intelligence in control engineering.

We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) language model (LM) for guiding a black-box large (i.e., >10B) LM in reasoning tasks. Specifically, the lightweight LM first generates a rationale for each input instance. The Frozen large LM is then prompted to predict a task output based on the rationale generated by the lightweight LM. Our approach is resource-efficient in the sense that it only requires training the lightweight LM. We optimize the model through 1) knowledge distillation and 2) reinforcement learning from rationale-oriented and task-oriented reward signals. We assess our method with multi-hop extractive question answering (QA) benchmarks, HotpotQA, and 2WikiMultiHopQA. Experimental results show that our approach outperforms all baselines regarding answer prediction accuracy. We also find that reinforcement learning helps the model to produce higher-quality rationales with improved QA performance.

This paper introduces PRobELM (Plausibility Ranking Evaluation for Language Models), a benchmark designed to assess language models' ability to discern more plausible from less plausible scenarios through their parametric knowledge. While benchmarks such as TruthfulQA emphasise factual accuracy or truthfulness, and others such as COPA explore plausible scenarios without explicitly incorporating world knowledge, PRobELM seeks to bridge this gap by evaluating models' capabilities to prioritise plausible scenarios that leverage world knowledge over less plausible alternatives. This design allows us to assess the potential of language models for downstream use cases such as literature-based discovery where the focus is on identifying information that is likely but not yet known. Our benchmark is constructed from a dataset curated from Wikidata edit histories, tailored to align the temporal bounds of the training data for the evaluated models. PRobELM facilitates the evaluation of language models across multiple prompting types, including statement, text completion, and question-answering. Experiments with 10 models of various sizes and architectures on the relationship between model scales, training recency, and plausibility performance, reveal that factual accuracy does not directly correlate with plausibility performance and that up-to-date training data enhances plausibility assessment across different model architectures.