mlsanityData to 7 Oct 2026

Ornithologist: Towards Trustworthy "Reasoning" about Central Bank Communications

arXiv 2505.09083 ↗First posted 14 May 2025econ.GN cs.CL q-fin.ECcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

I develop Ornithologist, a weakly-supervised textual classification system and measure the hawkishness and dovishness of central bank text. Ornithologist uses ``taxonomy-guided reasoning'', guiding a large language model with human-authored decision trees. This increases the transparency and explainability of the system and makes it accessible to non-experts. It also reduces hallucination risk. Since it requires less supervision than traditional classification systems, it can more easily be applied to other problems or sources of text (e.g. news) without much modification. Ornithologist measurements of hawkishness and dovishness of RBA communication carry information about the future of the cash rate path and of market expectations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 9 of its 24 references that are in the map. First posted on arXiv 14 May 2025.

Builds on

9 of 24 references.

References · 9

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  6. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  7. 2023Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERTcited by 155
  8. 2017Automated Phrase Mining from Massive Text Corporacited by 70
  9. 2024GPT Deciphering Fedspeak: Quantifying Dissent Among Hawks and Dovescited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Modeling Hawkish-Dovish Latent Beliefs in Multi-Agent Debate-Based LLMs for Monetary Policy Decision Classification
  2. 2026Frontier Financial Judgement: Can agents tell what might move a stock?
  3. 2026Empowering Small Language Models with Factual Hallucination-Aware Reasoning for Financial Classification
  4. 2025FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning
  5. 2026Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning
  6. 2026Mint-Agent: Introducing Finance-Native Agentic Foundation Models
  7. 2025VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation
  8. 2026RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation