People increasingly turn to large language models (LLMs) for everyday advice, making ethically charged interpersonal problems a practical moral-advisory context. Most prior work has studied this context through single-turn judgments or pressure-laden rebuttals, assumptions that poorly match how guidance is sought in real-world contexts. These assumptions leave unclear whether narration alone, without an explicit opposing position, can shift model judgments during multi-turn moral consultation. Yet real-world moral-conflict conversation often elicits one party’s self-justifying account, which can unfold over multiple turns and create information asymmetry. We introduce narrative captivity, a failure mode in which a model treats an unopposed one-sided account as complete and aligns with the narrator’s interpretation without seeking missing perspectives. To measure this phenomenon, we build a benchmark of 5,078 interpersonal-conflict scenarios spanning six moral dimensions. Across 17 LLMs, narrative captivity is widespread: end-state judgments under multi-turn narration shift by 25 percentage points on average beyond the matched single-turn baseline. Stage-level analysis identifies preference optimization as a major contributor, while four inference-time strategies provide only partial mitigation. We hope our project fosters LLM advisors that preserve independent judgment in real-world consultation.

While multi-agent systems based on large language models (LLMs) have shown promise in automating academic research workflows, extending them to economics and business research presents two key challenges, as specialized domain knowledge often spans neighboring disciplines yet remains difficult to access in a structured manner. First, existing methods primarily retrieve information at the paper level, whereas the evidence required for research tasks is often distributed across different sections, creating a granularity mismatch that limits retrieval coverage and precision. Second, these fields demand strict empirical rigor, yet current systems provide limited mechanisms for learning from evaluation feedback. We present BizSage, a multi-agent framework that combines corpus-level fine-grained retrieval with quality-driven self-evolution. We construct a Lateral Knowledge Graph (LKG) by integrating section-level knowledge graphs and apply Personalized PageRank (PPR) to identify sections that are both semantically relevant and structurally important. Seven specialized agents collaborate under a Meta-Review self-evolution mechanism that distills failure modes from evaluation traces into reusable strategies. On a benchmark spanning four domains and three tasks, BizSage ranks first on the majority of metrics, achieves pairwise win rates above 60% against six baselines, and produces zero hallucinated citations. We hope BizSage paves the way for reliable research assistance in economics, business, and the broader social sciences.

Large language models (LLMs) hold great promise for business applications, yet business analysis remains inherently complex, demanding rigorous reasoning and the integration of diverse knowledge sources. Existing benchmarks typically target narrow tasks and thus leave a fundamental question unanswered: how can LLMs be reliably applied in business, and how are these applications grounded in underlying theoretical capabilities? To address this gap, we introduce BizCompass, a benchmark explicitly designed to connect theoretical foundations with practical business knowledge and applications. At the knowledge level, BizCompass covers four core domains—finance, economics, statistics, and operations management. At the application level, it structures tasks around three representative roles: the analyst, the trader, and the consultant. This dual-axis design not only exposes performance differences across realistic scenarios but also diagnoses which foundational capabilities enable or constrain success. We systematically evaluate both open-source and commercial LLMs, revealing how theoretical knowledge translates into practical performance in business. The results provide actionable insights for model selection and training optimization in real-world business contexts. All datasets and evaluation code are publicly released to support reproducibility and future research: https://bizcompass.dev.ypemc.com.

LLM agents are widely used in social simulation, yet fluent social reasoning does not guarantee valid decision mechanisms. We test whether models implement socially embedded utility, where actions depend on peer-weighted references rather than isolated private preference. We introduce a theory-guided benchmark from network utility theory covering utility recovery, social-comparison gating, and structural transfer across two out-of-distribution decision forms. Across open-source and proprietary models, we find a gap between cue recognition and peer aggregation, spurious social activation when comparison should be inactive, and declining accuracy as social dependence rises. We propose theory-supervised mechanism alignment trained on latent utility states. Fine-tuning yields +8.3 and +13.9 utility-recovery points on Llama-3.1-8B and Qwen3-8B, raises gating above 95%, and improves transfer to unseen structures. Multi-agent simulations show that repairing local utility shifts macro outcomes, including stronger financial amplification and more stable labor stratification, which indicates that realistic macro-level simulations require adjustments at the individual level. Data and code are available at https://github.com/saaranLiu/SEDM-alignment.

Data mixing strategy is essential for large language model (LLM) training. Empirical evidence shows that inappropriate strategies can significantly reduce generalization. Although recent methods have improved empirical performance, several fundamental questions remain open: what constitutes a domain, whether human and model perceptions of domains are aligned, and how domain weighting influences generalization. We address these questions by establishing formal connections between gradient dynamics and domain distributions, offering a theoretical framework that clarifies the role of domains in training dynamics. Building on this analysis, we introduce DoGraph, a reweighting framework that formulates data scheduling as a graph-constrained optimization problem. Extensive experiments on GPT-2 models of varying scales demonstrate that DoGraph consistently achieves competitive performance.

As large language models (LLMs) evolve from conversational assistants into agents capable of handling complex tasks, they are increasingly deployed in high-risk domains. However, existing benchmarks largely rely on mixed queries and posterior evaluation, output-level scoring, which quantifies hallucination severity but offers limited insight into where and why hallucinations arise in the generation pipeline. We therefore reformulate hallucination evaluation as a diagnostic problem and propose PRISM, a controlled benchmark that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors, grounded in three stages of generation (memory, instruction, and reasoning). PRISM contains 9,448 instances across 65 tasks and supports fine-grained, stage-aware diagnostic evaluation. Evaluating 24 mainstream open-source and proprietary LLMs, we uncover consistent trade-offs across instruction following, memory retrieval, and logical reasoning, showing that mitigation strategies often improve specific dimensions at the expense of others.We hope PRISM provides a framework for understanding the specific mechanisms behind LLMs hallucinations, ultimately accelerating the development of trustworthy large language models.

Financial markets exhibit complex dynamics where localized events trigger ripple effects across entities. Previous event studies, constrained by static single-companies analyses and simplistic assumptions, fail to capture these ripple effects. While large language models (LLMs) offer emergent reasoning capabilities, their direct application falters due to structural market unawareness and limited capacity to analyze ripple effects. We propose FinRipple, an elegant framework that empowers LLMs with the ability to analyze ripple effects through financial theory-guided large-scale reinforcement learning. We begin by relaxing the assumptions of previous methods, incorporating a time-varying knowledge graph to accurately represent market structure. By seamlessly integrating classical asset pricing theory, we align the LLM with the market, enabling it to predict ripple effects. To the best of our knowledge, we are the first to provide a standardized definition of ripple effect prediction, a task that is extremely important yet unexplored in the financial domain. Extensive experiments demonstrate that FinRipple provides a promising solution to this task.