arXiv subjects

Feiyu Qu

Publications and source records attributed to Feiyu Qu.

3 recordsLinked to original sources

arXiv2026

RankGLU: Residual Gated Score Formation for Cross-Sectional Stock Prediction

Cross-sectional stock prediction is closer to a ranking problem than to ordinary return-magnitude regression, since portfolio decisions depend on the relative ordering of assets within each trading date. Existing temporal, graph-based, and market-conditioned attention models have improved stock representation learning, yet the final prediction head is often treated as a minor implementation detail. This paper argues that, under information-coefficient-oriented evaluation, score formation is a critical bottleneck: an over-flexible head can fit unstable return magnitude, whereas an overly linear head may underuse cross-feature interactions. We therefore develop RankGLU, a residual bottleneck gated linear unit for cross-sectional stock ranking. RankGLU keeps a direct linear scoring path and adds a bounded multiplicative branch, thereby preserving a stable ordering route while allowing controlled nonlinear interactions. The method is evaluated on CSI300 and CSI800 under a unified protocol with cross-sectional score normalization and an IC-augmented objective. Multi-seed experiments show that, on CSI300, RankGLU achieves the strongest mean IC among the internally controlled variants, improving from 0.0654+/-0.0052 for the original backbone and 0.0697+/-0.0030 for the ranking-aware backbone to 0.0727+/-0.0037, a gain that is consistent across all five seeds. Its best-seed result also exceeds the corresponding baselines. Ablation results further indicate that removing the GLU prediction head causes the clearest degradation among the tested component changes. Additional relation-path calibrations can produce high single-seed peaks, but their multi-seed behavior is less stable. The evidence suggests that ranking-aware stock models benefit most reliably from bounded residual score formation rather than from indiscriminate architectural expansion.

cs.CE↗

arXiv2025

From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis

Hallucinations in Large Language Models (LLMs), defined as the generation of content inconsistent with facts or context, represent a core obstacle to their reliable deployment in critical domains. Current research primarily focuses on binary "detection" approaches that, while capable of identifying hallucinations, fail to provide interpretable and actionable feedback for model improvement, thus limiting practical utility. To address this limitation, a new research paradigm is proposed, shifting from "detection" to "diagnosis". The Hallucination Diagnosis Task is introduced, a task which requires models to not only detect hallucinations, but also perform error localization, causal explanation, and content correction. We develop the Hallucination Diagnosis Generator (HDG), an automated pipeline that systematically generates high-quality training samples with rich diagnostic metadata from raw corpora through multi-dimensional augmentation strategies including controlled fact fabrication and reasoning chain perturbation. Using HDG-generated data, we train HDM-4B-RL, a 4-billion-parameter hallucination diagnosis model, employing Group Relative Policy Optimization (GRPO) with a comprehensive reward function incorporating structural, accuracy, and localization signals. Experimental results demonstrate that our model surpasses previous state-of-the-art detection models on the HaluEval benchmark while achieving comparable performance to advanced general-purpose models. In comprehensive diagnosis tasks, HDM-4B-RL matches the capabilities of larger general models while maintaining a smaller size. This work validates the feasibility and value of hallucination diagnosis, providing an effective methodology for building more trustworthy and reliable generative AI systems.

cs.CL↗

arXiv2025

Augmented Runtime Collaboration for Self-Organizing Multi-Agent Systems: A Hybrid Bi-Criteria Routing Approach

LLM-based multi-agent systems have demonstrated significant capabilities across diverse domains. However, the task performance and efficiency are fundamentally constrained by their collaboration strategies. Prevailing approaches rely on static topologies and centralized global planning, a paradigm that limits their scalability and adaptability in open, decentralized networks. Effective collaboration planning in distributed systems using only local information thus remains a formidable challenge. To address this, we propose BiRouter, a novel dual-criteria routing method for Self-Organizing Multi-Agent Systems (SO-MAS). This method enables each agent to autonomously execute ``next-hop'' task routing at runtime, relying solely on local information. Its core decision-making mechanism is predicated on balancing two metrics: (1) the ImpScore, which evaluates a candidate agent's long-term importance to the overall goal, and (2) the GapScore, which assesses its contextual continuity for the current task state. Furthermore, we introduce a dynamically updated reputation mechanism to bolster system robustness in untrustworthy environments and have developed a large-scale, cross-domain dataset, comprising thousands of annotated task-routing paths, to enhance the model's generalization. Extensive experiments demonstrate that BiRouter achieves superior performance and token efficiency over existing baselines, while maintaining strong robustness and effectiveness in information-limited, decentralized, and untrustworthy settings.

cs.MA↗