We build a Generative Pre-trained Transformer (GPT) model from scratch to solve sequential decision making tasks arising in contexts of operations research and management science which we call OMGPT. We first propose a general sequence modeling framework to cover several operational decision making tasks as special cases, such as dynamic pricing, inventory management, resource allocation, and queueing control. Under the framework, all these tasks can be viewed as a sequential prediction problem where the goal is to predict the optimal future action given all the historical information. Then we train a transformer-based neural network model (OMGPT) as a natural and powerful architecture for sequential modeling. This marks a paradigm shift compared to the existing methods for these OR/OM tasks in that (i) the OMGPT model can take advantage of the huge amount of pre-trained data; (ii) when tackling these problems, OMGPT does not assume any analytical model structure and enables a direct and rich mapping from the history to the future actions. Either of these two aspects, to the best of our knowledge, is not achieved by any existing method. We establish a Bayesian perspective to theoretically understand the working mechanism of the OMGPT on these tasks, which relates its performance with the pre-training task diversity and the divergence between the testing task and pre-training tasks. Numerically, we observe a surprising performance of the proposed model across all the above tasks.

Daniel Dennett speculated in *Kinds of Minds* 1996: "Perhaps the kind of mind you get when you add language to it is so different from the kind of mind you can have without language that calling them both minds is a mistake." Recent work in AI can be seen as testing Dennett's thesis by exploring the performance of AI systems with and without linguistic training. I argue that the success of Large Language Models at inferential reasoning, limited though it may be, supports Dennett's radical view about the effect of language on thought. I suggest it is the abstractness and efficiency of linguistic encoding that lies behind the capacity of LLMs to perform inferences across a wide range of domains. In a slogan, language makes inference computationally tractable. I assess what these results in AI indicate about the role of language in the workings of our own biological minds.

Code-switching (CS) poses a significant challenge for Large Language Models (LLMs), yet its comprehensibility remains underexplored in LLMs. We introduce CS-Sum, to evaluate the comprehensibility of CS by the LLMs through CS dialogue to English summarization. CS-Sum is the first benchmark for CS dialogue summarization across Mandarin-English (EN-ZH), Tamil-English (EN-TA), and Malay-English (EN-MS), with 900-1300 human-annotated dialogues per language pair. Evaluating ten LLMs, including open and closed-source models, we analyze performance across few-shot, translate-summarize, and fine-tuning (LoRA, QLoRA on synthetic data) approaches. Our findings show that though the scores on automated metrics are high, LLMs make subtle mistakes that alter the complete meaning of the dialogue. To this end, we introduce 3 most common type of errors that LLMs make when handling CS input. Error rates vary across CS pairs and LLMs, with some LLMs showing more frequent errors on certain language pairs, underscoring the need for specialized training on code-switched data.

Retrieval-augmented generation (RAG) systems are widely used in question-answering (QA) tasks, but current benchmarks lack metadata integration, hindering evaluation in scenarios requiring both textual data and external information. To address this, we present AMAQA, a new open-access QA dataset designed to evaluate tasks combining text and metadata. The integration of metadata is especially important in fields that require rapid analysis of large volumes of data, such as cybersecurity and intelligence, where timely access to relevant information is critical. AMAQA includes about 1.1 million English messages collected from 26 public Telegram groups, enriched with metadata such as timestamps, topics, emotional tones, and toxicity indicators, which enable precise and contextualized queries by filtering documents based on specific criteria. It also includes 450 high-quality QA pairs, making it a valuable resource for advancing research on metadata-driven QA and RAG systems. To the best of our knowledge, AMAQA is the first single-hop QA benchmark to incorporate metadata and labels such as topics covered in the messages. We conduct extensive tests on the benchmark, establishing a new standard for future research. We show that leveraging metadata boosts accuracy from 0.12 to 0.61, highlighting the value of structured context. Building on this, we explore several strategies to refine the LLM input by iterating over provided context and enriching it with noisy documents, achieving a further 3-point gain over the best baseline and a 14-point improvement over simple metadata filtering. The dataset is available at https://anonymous.4open.science/r/AMAQA-5D0D/

Large language model (LLM) shows promising performances in a variety of downstream tasks, such as machine translation (MT). However, using LLMs for translation suffers from high computational costs and significant latency. Based on our evaluation, in most cases, translations using LLMs are comparable to that generated by neural machine translation (NMT) systems. Only in particular scenarios, LLM and NMT models show respective advantages. As a result, integrating NMT and LLM for translation and using LLM only when necessary seems to be a sound solution. A scheduling policy that optimizes translation result while ensuring fast speed and as little LLM usage as possible is thereby required. We compare several scheduling policies and propose a novel and straightforward decider that leverages source sentence features. We conduct extensive experiments on multilingual test sets and the result shows that we can achieve optimal translation performance with minimal LLM usage, demonstrating effectiveness of our decider.

Just-in-time Information Recommendation (JIR) is a service designed to deliver the most relevant information precisely when users need it, , addressing their knowledge gaps with minimal effort and boosting decision-making and efficiency in daily life. Advances in device-efficient deployment of foundation models and the growing use of intelligent wearable devices have made always-on JIR assistants feasible. However, there has been no systematic effort to formally define JIR tasks or establish evaluation frameworks. To bridge this gap, we present the first mathematical definition of JIR tasks and associated evaluation metrics. Additionally, we introduce JIR-Arena, a multimodal benchmark dataset featuring diverse, information-request-intensive scenarios to evaluate JIR systems across critical dimensions: i) accurately inferring user information needs, ii) delivering timely and relevant recommendations, and iii) avoiding irrelevant content that may distract users. Developing a JIR benchmark dataset poses challenges due to subjectivity in estimating user information needs and uncontrollable system variables affecting reproducibility. To address these, JIR-Arena: i) combines input from multiple humans and large AI models to approximate information need distributions; ii) assesses JIR quality through information retrieval outcomes using static knowledge base snapshots; and iii) employs a multi-turn, multi-entity validation framework to improve objectivity and generality. Furthermore, we implement a baseline JIR system capable of processing real-time information streams aligned with user inputs. Our evaluation of this baseline system on JIR-Arena indicates that while foundation model-based JIR systems simulate user needs with reasonable precision, they face challenges in recall and effective content retrieval. To support future research in this new area, we fully release our code and data.

Information extraction (IE) from Visually Rich Documents (VRDs) containing layout features along with text is a critical and well-studied task. Specialized non-LLM NLP-based solutions typically involve training models using both textual and geometric information to label sequences/tokens as named entities or answers to specific questions. However, these approaches lack reasoning, are not able to infer values not explicitly present in documents, and do not generalize well to new formats. Generative LLM-based approaches proposed recently are capable of reasoning, but struggle to comprehend clues from document layout especially in previously unseen document formats, and do not show competitive performance in heterogeneous VRD benchmark datasets. In this paper, we propose BLOCKIE, a novel LLM-based approach that organizes VRDs into localized, reusable semantic textual segments called $\textit{semantic blocks}$, which are processed independently. Through focused and more generalizable reasoning,our approach outperforms the state-of-the-art on public VRD benchmarks by 1-3% in F1 scores, is resilient to document formats previously not encountered and shows abilities to correctly extract information not explicitly present in documents.

Recommender systems (RS) are increasingly vulnerable to shilling attacks, where adversaries inject fake user profiles to manipulate system outputs. Traditional attack strategies often rely on simplistic heuristics, require access to internal RS data, and overlook the manipulation potential of textual reviews. In this work, we introduce Agent4SR, a novel framework that leverages Large Language Model (LLM)-based agents to perform low-knowledge, high-impact shilling attacks through both rating and review generation. Agent4SR simulates realistic user behavior by orchestrating adversarial interactions, selecting items, assigning ratings, and crafting reviews, while maintaining behavioral plausibility. Our design includes targeted profile construction, hybrid memory retrieval, and a review attack strategy that propagates target item features across unrelated reviews to amplify manipulation. Extensive experiments on multiple datasets and RS architectures demonstrate that Agent4SR outperforms existing low-knowledge baselines in both effectiveness and stealth. Our findings reveal a new class of emergent threats posed by LLM-driven agents, underscoring the urgent need for enhanced defenses in modern recommender systems.

The next Point-of-Interest (POI) recommendation task aims to predict users' next destinations based on their historical movement data and plays a key role in location-based services and personalized applications. Accurate next POI recommendation depends on effectively modeling geographic information and POI transition relations, which are crucial for capturing spatial dependencies and user movement patterns. While Large Language Models (LLMs) exhibit strong capabilities in semantic understanding and contextual reasoning, applying them to spatial tasks like next POI recommendation remains challenging. First, the infrequent nature of specific GPS coordinates makes it difficult for LLMs to model precise spatial contexts. Second, the lack of knowledge about POI transitions limits their ability to capture potential POI-POI relationships. To address these issues, we propose GA-LLM (Geography-Aware Large Language Model), a novel framework that enhances LLMs with two specialized components. The Geographic Coordinate Injection Module (GCIM) transforms GPS coordinates into spatial representations using hierarchical and Fourier-based positional encoding, enabling the model to understand geographic features from multiple perspectives. The POI Alignment Module (PAM) incorporates POI transition relations into the LLM's semantic space, allowing it to infer global POI relationships and generalize to unseen POIs. Experiments on three real-world datasets demonstrate the state-of-the-art performance of GA-LLM.

This study explores the potential of zero-shot time series forecasting, an innovative approach leveraging pre-trained foundation models, to forecast mortality rates without task-specific fine-tuning. We evaluate two state-of-the-art foundation models, TimesFM and CHRONOS, alongside traditional and machine learning-based methods across three forecasting horizons (5, 10, and 20 years) using data from 50 countries and 111 age groups. In our investigations, zero-shot models showed varying results: while CHRONOS delivered competitive shorter-term forecasts, outperforming traditional methods like ARIMA and the Lee-Carter model, TimesFM consistently underperformed. Fine-tuning CHRONOS on mortality data significantly improved long-term accuracy. A Random Forest model, trained on mortality data, achieved the best overall performance. These findings underscore the potential of zero-shot forecasting while highlighting the need for careful model selection and domain-specific adaptation.