22 papers
Not All Information Is Worth Asking For: Decision-Informed Information Seeking with LLMs
Seunghan Lee, Jun Seo, Junhyeok Kang +9
Large language models (LLMs) are increasingly used to support decisions under incomplete information, where deciding what to look up and when to stop matters as much as the final a…
OneShot: Label-Efficient Detector Weighting for Time Series Anomaly Detection
Seunghan Lee, Jun Seo, Jaehoon Lee +9
Time series (TS) anomaly detection (AD) lacks a universal detector, with the best choice determined by the series rather than by the algorithm. Existing methods therefore either se…
XForecast: The KDD 2026 Finance Day Challenge on News-Grounded Financial Forecasting
Jaehoon Lee, Jun Seo, Seunghan Lee +10
Financial forecasting has traditionally relied on numerical time-series (TS) signals, while textual information such as news remains largely underutilized. We introduce XForecast,…
EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting
Seunghan Lee, Sangjun Han, Jun Seo +9
Time series foundation models (TSFMs) are pretrained on series from diverse domains, where demand series make up only a small fraction. Demand data has properties that such corpora…
Explaining Time Series Forecasting with Horizon-Resolved Attribution
Seunghan Lee, Jun Seo, Jaehoon Lee +9
Recent advances in explaining time series (TS) models have produced methods that identify which past values a prediction depends on. However, most existing methods return a single…
EXAONE Finance 1.0: An Attention-free Time Series Foundation Model for Financial Time Series
Seunghan Lee, Jaehoon Lee, Jun Seo +9
This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series foundation model (TSFM) tailored to financial forecasting. While recent TSFMs a…
PALM: Point-in-Time Adaptation for Financial Language Models
Seunghan Lee, Jun Seo, Jaehoon Lee +9
Language models used in financial backtests suffer from look-ahead bias, as a model trained on text published after the study period has already observed the outcomes it is asked t…
Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron
Sahong Park, Suhwan Park, Hoyoung Lee +8
Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows that they exhibit systematic, model-specific investment preferences. We study…
FinVerse: Toward More Realistic Evaluation for Financial Time-Series Forecasting
Jaehoon Lee, Jun Seo, Seunghan Lee +17
Time-series foundation models (TSFMs) are increasingly evaluated on broad benchmarks that apply uniform conventional forecast evaluation metrics across heterogeneous time-series. H…
ReasonCast: Towards Explainable Time Series Forecasting with Reasoning
Seunghan Lee, Jun Seo, Jaehoon Lee +9
Most time series (TS) models are specialized for a single task, either understanding (i.e., returning text answers about a TS) or generation (i.e., returning a numeric forecast). O…
Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting
Seunghan Lee, Jaehoon Lee, Jun Seo +9
The direction of change --- whether a series will move up or down --- is often as important as its exact value in decisiondriven applications such as risk management and financial…
When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis
Hoyoung Lee, Suhwan Park, Seunghan Lee +15
Financial decision-makers face more information than they can directly inspect, making context compression necessary. Yet when large language models (LLMs) compress financial sourc…
AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
Seunghan Lee, Jun Seo, Jaehoon Lee +7
Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity…
FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models
Seunghan Lee, Jun Seo, Jaehoon Lee +7
Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail on financial domain, which exhibit unique characteristics…
Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion
Seunghan Lee, Jun Seo, Jaehoon Lee +7
Recent advances in multimodal learning have motivated the integration of auxiliary modalities such as text or vision into time series (TS) forecasting. However, most existing metho…
Not All Retrievals are Useful: Cross-Attention for Input-Aware RAG in Time Series Forecasting
Seunghan Lee, Jaehoon Lee, Jun Seo +7
Retrieval-augmented generation (RAG) enhances zero-shot time series (TS) forecasting by leveraging external knowledge bases, yet existing approaches overlook input-level relevance…
FinTexTS: Financial Text-Paired Time-Series Dataset via Semantic-Based and Multi-Level Pairing
Jaehoon Lee, Suhwan Park, Taeyoon Lim +9
The financial domain involves a variety of important time-series problems. Recently, time-series analysis methods that jointly leverage textual and numerical information have gaine…
Forecasting Future Language: Context Design for Mention Markets
Sumin Kim, Jihoon Kwon, Yoon Kim +9
Mention markets, a type of prediction market in which contracts resolve based on whether a specified keyword is mentioned during a future public event, require accurate probabilist…
Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning
Hyeongmin Lee, Chanyeol Choi, Jihoon Kwon +8
Asset retrieval (finding similar assets in a financial universe) is central to quantitative investment decision-making. Existing approaches define similarity through historical pri…
Adaptive Information Routing for Multimodal Time Series Forecasting
Jun Seo, Hyeokjun Choe, Seohui Bae +10
Time series forecasting is a critical task for artificial intelligence with numerous real-world applications. Traditional approaches primarily rely on historical time series data t…
THEME: Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics
Hoyoung Lee, Wonbin Ahn, Suhwan Park +6
Thematic investing, which aims to construct portfolios aligned with structural trends, remains a challenging endeavor due to overlapping sector boundaries and evolving market dynam…
Your AI, Not Your View: The Bias of LLMs in Investment Analysis
Hoyoung Lee, Junhyuk Seo, Suhwan Park +5
In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data. Thes…