paper-with-me

홈 › Papers

PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering

2026-02-26 · Junkai Lu, Peng Chen, Xingjian Wu, Yang Shu, Chenjuan Guo, Christian S. Jensen, Bin Yang arxiv

Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time series merely as text or images, failing to capture the patterns like trends and seasonalities needed to answer specific questions; and when trained on a mix of simple and complex tasks, simpler objectives often dominate the learning process, hindering the development of deep reasoning capabilities. To address these limitations, we propose the Pattern-Aware Alignment and Balanced Reasoning model (PATRA), introducing a pattern-aware mechanism that extracts trend and seasonality patterns from time series to achieve deep alignment. Furthermore, we design a task-aware balanced reward to harmonize learning across tasks of varying difficulty, incentivizing the generation of coherent Chains of Thought. Extensive experiments show that PATRA outperforms strong baselines across diverse Time Series Question Answering (TSQA) tasks, demonstrating superior cross-modal understanding and reasoning capability.

📄 PDF Abstract BibTeX arXiv:2602.23161

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

HAIR: Hardness-Aware Inverse Reinforcement Learning with Introspective Reasoning for LLM Alignment

2025-03-23 · Ruoxi Cheng, Haoxuan Ma, Weixin Wang

The alignment of large language models (LLMs) with human values remains critical yet hindered by four key challenges: (1) scarcity of balanced safety datasets, (2) alignment tax, (3) vulnerability to jailbreak attacks du…

From Pattern to Interpretation. Using Colibri Core to Detect Translation Patterns in the Peshitta.

2022-06-01 · LREC 2022 6 · Mathias Coeckelbergs

This article presents the first results of the CLARIAH-funded project ‘Patterns in Translation: Using Colibri Core for the Syriac Bible’ (PaTraCoSy). This project seeks to use Colibri Core to detect translation patterns …

Translation

Sitatapatra: Blocking the Transfer of Adversarial Samples

2019-01-23 · Ilia Shumailov, Xitong Gao, Yiren Zhao, Robert Mullins 외

Convolutional Neural Networks (CNNs) are widely used to solve classification tasks in computer vision. However, they can be tricked into misclassifying specially crafted `adversarial' samples -- and samples built to tric…

BlockingGeneral Classification

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

2025-06-04 · Liang Chen, Xueting Han, Li Shen, Jing Bai 외

Harmful fine-tuning (HFT), performed directly on open-source LLMs or through Fine-tuning-as-a-Service, breaks safety alignment and poses significant threats. Existing methods aim to mitigate HFT risks by learning robust …

Safety Alignment

Pattern-Aware Graph Neural Networks for Handling Missing Data

2026-07-09 · Minett Tran, Taehee Jeong arxiv

Missing data is ubiquitous in real-world datasets. Traditional methods either discard incomplete samples or apply imputation techniques that ignore potentially informative missingness patterns, implicitly assuming that m…