Kevin Foley, Jonathan Hartadi, Shivesh Prakash, Charishma Takkallapalli, Swapnil Vatsal · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.22745 · cited by 0 works (OpenAlex) · open-access PDF
재무 뉴스를 읽는 언어 모델은 일반적으로 테스트를 위해 사용 된 동일한 해의 텍스트에 훈련되므로 백크 테스트는 뒤를 볼 수 있습니다. 우리는 NoLBERT에서 뉴스 테마를 구축하고, 1976 년과 1995 년 사이에 출판 된 텍스트에만 프레드 트레이닝 된 인코더를 1976 년 사이에 문장 인코더로 조정하고, 라벨이나 반환이없는 동일한 기사의 단편에 대조적 인 미세 조정으로 텍스트를 훈련합니다. 우리는 LDA, MiniLM 및 FinBERT 독자와 비교합니다. 2012 년에서 2024 년까지 1.26 백만 개의 기사에서, 각 독자의 주제를 관심 충격 및 주식 노출로 변환하고, 3 개의 재균형 주파수에서 8 개의 모델을 가진
Machine translation (Meta M2M100); the English original follows.
Language models that read financial news are usually trained on text from the same years used to test them, so a backtest can reward hindsight. We build news topics from NoLBERT, an encoder pretrained only on text published between 1976 and 1995, adapted into a sentence encoder by contrastive fine-tuning on passages of the same article, with no labels or returns. We compare it with LDA, MiniLM and FinBERT readers on 1.26 million articles from 2012 to 2024, convert each reader's topics into attention shocks and stock exposures, and forecast the returns of the 1,000 largest US stocks with eight models at three rebalancing frequencies. Models are fitted on 2013-2019, choices are made on 2020-2021, and 2022-2024 is held out. The experiment with the best validation score loses money at every frequency. Measuring attention shocks against the past 63 trading days instead of 5 raises the test rank IC of every reader. NoLBERT gives the most stable topics and forecasts about as well as LDA. An equal-weight combination of all readers and models earns a monthly net Sharpe ratio of 1.12, significant against zero before adjusting for the search but not against a price-only benchmark.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Stock (firearms), Sentence, Econometrics, Computer science, Reading (process), Language model
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.22745, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange