Detecting salient parts in text using natural language processing has been widely used to mitigate the effects of information overflow. Nevertheless, most of the datasets available for this task are derived mainly from academic publications. We introduce SPACE-IDEAS, a dataset for salient information detection from innovation ideas related to the Space domain. The text in SPACE-IDEAS varies greatly and includes informal, technical, academic and business-oriented writing styles. In addition to a manually annotated dataset we release an extended version that is annotated using a large generative language model. We train different sentence and sequential sentence classifiers, and show that the automatically annotated dataset can be leveraged using multitask learning to train better classifiers.

MILA, Quebec AI Institute Abstract We test whether a leading AI system GPT-4 understands discourse as well as humans do, using a standardized test of discourse comprehension. Participants are presented with brief stories and then answer eight yes/no questions probing their comprehension of the story. The questions are formatted to assess the separate impacts of directness (stated vs. implied) and salience (main idea vs. details). GPT-4 performs slightly, but not statistically significantly, better than humans given the very high level of human performance. Both GPT-4 and humans exhibit a strong ability to make inferences about information that is not explicitly stated in a story, a critical test of understanding.

In AI-assisted decision-making, humans often passively review AI's suggestion and decide whether to accept or reject it as a whole. In such a paradigm, humans are found to rarely trigger analytical thinking and face difficulties in communicating the nuances of conflicting opinions to the AI when disagreements occur. To tackle this challenge, we propose Human-AI Deliberation, a novel framework to promote human reflection and discussion on conflicting human-AI opinions in decision-making. Based on theories in human deliberation, this framework engages humans and AI in dimension-level opinion elicitation, deliberative discussion, and decision updates. To empower AI with deliberative capabilities, we designed Deliberative AI, which leverages large language models (LLMs) as a bridge between humans and domain-specific models to enable flexible conversational interactions and faithful information provision. An exploratory evaluation on a graduate admissions task shows that Deliberative AI outperforms conventional explainable AI (XAI) assistants in improving humans' appropriate reliance and task performance. Based on a mixed-methods analysis of participant behavior, perception, user experience, and open-ended feedback, we draw implications for future AI-assisted decision tool design.

Large language models (LLMs) are gaining increasing interests to improve clinical efficiency for medical diagnosis, owing to their unprecedented performance in modelling natural language. Ensuring the safe and reliable clinical applications, the evaluation of LLMs indeed becomes critical for better mitigating the potential risks, e.g., hallucinations. However, current evaluation methods heavily rely on labor-intensive human participation to achieve human-preferred judgements. To overcome this challenge, we propose an automatic evaluation paradigm tailored to assess the LLMs' capabilities in delivering clinical services, e.g., disease diagnosis and treatment. The evaluation paradigm contains three basic elements: metric, data, and algorithm. Specifically, inspired by professional clinical practice pathways, we formulate a LLM-specific clinical pathway (LCP) to define the clinical capabilities that a doctor agent should possess. Then, Standardized Patients (SPs) from the medical education are introduced as the guideline for collecting medical data for evaluation, which can well ensure the completeness of the evaluation procedure. Leveraging these steps, we develop a multi-agent framework to simulate the interactive environment between SPs and a doctor agent, which is equipped with a Retrieval-Augmented Evaluation (RAE) to determine whether the behaviors of a doctor agent are in accordance with LCP. The above paradigm can be extended to any similar clinical scenarios to automatically evaluate the LLMs' medical capabilities. Applying such paradigm, we construct an evaluation benchmark in the field of urology, including a LCP, a SPs dataset, and an automated RAE. Extensive experiments are conducted to demonstrate the effectiveness of the proposed approach, providing more insights for LLMs' safe and reliable deployments in clinical practice.

Recent works in Task and Motion Planning (TAMP) show that training control policies on language-supervised robot trajectories with quality labeled data markedly improves agent task success rates. However, the scarcity of such data presents a significant hurdle to extending these methods to general use cases. To address this concern, we present an automated framework to decompose trajectory data into temporally bounded and natural language-based descriptive sub-tasks by leveraging recent prompting strategies for Foundation Models (FMs) including both Large Language Models (LLMs) and Vision Language Models (VLMs). Our framework provides both time-based and language-based descriptions for lower-level sub-tasks that comprise full trajectories. To rigorously evaluate the quality of our automatic labeling framework, we contribute an algorithm SIMILARITY to produce two novel metrics, temporal similarity and semantic similarity. The metrics measure the temporal alignment and semantic fidelity of language descriptions between two sub-task decompositions, namely an FM sub-task decomposition prediction and a ground-truth sub-task decomposition. We present scores for temporal similarity and semantic similarity above 90%, compared to 30% of a randomized baseline, for multiple robotic environments, demonstrating the effectiveness of our proposed framework. Our results enable building diverse, large-scale, language-supervised datasets for improved robotic TAMP.

Conversational Recommender System (CRS) interacts with users through natural language to understand their preferences and provide personalized recommendations in real-time. CRS has demonstrated significant potential, prompting researchers to address the development of more realistic and reliable user simulators as a key focus. Recently, the capabilities of Large Language Models (LLMs) have attracted a lot of attention in various fields. Simultaneously, efforts are underway to construct user simulators based on LLMs. While these works showcase innovation, they also come with certain limitations that require attention. In this work, we aim to analyze the limitations of using LLMs in constructing user simulators for CRS, to guide future research. To achieve this goal, we conduct analytical validation on the notable work, iEvaLM. Through multiple experiments on two widely-used datasets in the field of conversational recommendation, we highlight several issues with the current evaluation methods for user simulators based on LLMs: (1) Data leakage, which occurs in conversational history and the user simulator's replies, results in inflated evaluation results. (2) The success of CRS recommendations depends more on the availability and quality of conversational history than on the responses from user simulators. (3) Controlling the output of the user simulator through a single prompt template proves challenging. To overcome these limitations, we propose SimpleUserSim, employing a straightforward strategy to guide the topic toward the target items. Our study validates the ability of CRS models to utilize the interaction information, significantly improving the recommendation results.

Inspired by cognitive neuroscience studies, we introduce a novel `decoding probing' method that uses minimal pairs benchmark (BLiMP) to probe internal linguistic characteristics in neural language models layer by layer. By treating the language model as the `brain' and its representations as `neural activations', we decode grammaticality labels of minimal pairs from the intermediate layers' representations. This approach reveals: 1) Self-supervised language models capture abstract linguistic structures in intermediate layers that GloVe and RNN language models cannot learn. 2) Information about syntactic grammaticality is robustly captured through the first third layers of GPT-2 and also distributed in later layers. As sentence complexity increases, more layers are required for learning grammatical capabilities. 3) Morphological and semantics/syntax interface-related features are harder to capture than syntax. 4) For Transformer-based models, both embeddings and attentions capture grammatical features but show distinct patterns. Different attention heads exhibit similar tendencies toward various linguistic phenomena, but with varied contributions.

Text-to-SQL, which involves translating natural language into Structured Query Language (SQL), is crucial for enabling broad access to structured databases without expert knowledge. However, designing models for such tasks is challenging due to numerous factors, including the presence of 'noise,' such as ambiguous questions and syntactical errors. This study provides an in-depth analysis of the distribution and types of noise in the widely used BIRD-Bench benchmark and the impact of noise on models. While BIRD-Bench was created to model dirty and noisy database values, it was not created to contain noise and errors in the questions and gold queries. We found that noise in questions and gold queries are prevalent in the dataset, with varying amounts across domains, and with an uneven distribution between noise types. The presence of incorrect gold SQL queries, which then generate incorrect gold answers, has a significant impact on the benchmark's reliability. Surprisingly, when evaluating models on corrected SQL queries, zero-shot baselines surpassed the performance of state-of-the-art prompting methods. We conclude that informative noise labels and reliable benchmarks are crucial to developing new Text-to-SQL methods that can handle varying types of noise. All datasets, annotations, and code are available at https://github.com/niklaswretblad/the-effects-of-noise-in-text-to-SQL.

The integration and deployment of large language model (LLM)-based intelligent agents have been fraught with challenges that compromise their efficiency and efficacy. Among these issues are sub-optimal scheduling and resource allocation of agent requests over the LLM, the difficulties in maintaining context during interactions between agent and LLM, and the complexities inherent in integrating heterogeneous agents with different capabilities and specializations. The rapid increase of agent quantity and complexity further exacerbates these issues, often leading to bottlenecks and sub-optimal utilization of resources. Inspired by these challenges, this paper presents AIOS, an LLM agent operating system, which embeds large language model into operating systems (OS) as the brain of the OS, enabling an operating system "with soul" -- an important step towards AGI. Specifically, AIOS is designed to optimize resource allocation, facilitate context switch across agents, enable concurrent execution of agents, provide tool service for agents, and maintain access control for agents. We present the architecture of such an operating system, outline the core challenges it aims to resolve, and provide the basic design and implementation of the AIOS. Our experiments on concurrent execution of multiple agents demonstrate the reliability and efficiency of our AIOS modules. Through this, we aim to not only improve the performance and efficiency of LLM agents but also to pioneer for better development and deployment of the AIOS ecosystem in the future. The project is open-source at https://github.com/agiresearch/AIOS.

Users often struggle with decision-making between two options (A vs B), as it usually requires time-consuming research across multiple web pages. We propose STRUM-LLM that addresses this challenge by generating attributed, structured, and helpful contrastive summaries that highlight key differences between the two options. STRUM-LLM identifies helpful contrast: the specific attributes along which the two options differ significantly and which are most likely to influence the user's decision. Our technique is domain-agnostic, and does not require any human-labeled data or fixed attribute list as supervision. STRUM-LLM attributes all extractions back to the input sources along with textual evidence, and it does not have a limit on the length of input sources that it can process. STRUM-LLM Distilled has 100x more throughput than the models with comparable performance while being 10x smaller. In this paper, we provide extensive evaluations for our method and lay out future directions for our currently deployed system.