# FinAnchor: Aligned Multi-Model Representations for Financial Prediction

arXiv: https://arxiv.org/abs/2602.20859 · HTML: https://mlsanity.com/paper/2602.20859/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 28 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Revisiting Model Stitching to Compare Neural Representations](https://mlsanity.com/paper/2106.07682/) (2021)
- [Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis](https://mlsanity.com/paper/2305.07972/) (2023)
- [Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching](https://mlsanity.com/paper/2004.12297/) (2020)
- [Predicting Corporate Risk by Jointly Modeling Company Networks and Dialogues in Earnings Conference Calls](https://mlsanity.com/paper/2206.06174/) (2022)
- [SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection](https://mlsanity.com/paper/2505.14420/) (2025)

## Abstract (arXiv)

Financial prediction from long documents involves significant challenges, as actionable signals are often sparse and obscured by noise, and the optimal LLM for generating embeddings varies across tasks and time periods. In this paper, we propose FinAnchor(Financial Anchored Representations), a lightweight framework that integrates embeddings from multiple LLMs without fine-tuning the underlying models. FinAnchor addresses the incompatibility of feature spaces by selecting an anchor embedding space and learning linear mappings to align representations from other models into this anchor. These aligned features are then aggregated to form a unified representation for downstream prediction. Across multiple financial NLP tasks, FinAnchor consistently outperforms strong single-model baselines and standard ensemble methods, demonstrating the effectiveness of anchoring heterogeneous representations for robust financial prediction.