{"paper_id":"2511.01869","title":"BondBERT: What we learn when assigning sentiment in the bond market","authors":["Toby Barter","Zheng Gao","Eva Christodoulaki","Jing Chen","John Cartlidge"],"paper_date":"2025-10-21","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.01869v2","page_url":"https://thequant.space/flowcharts/bondbert-what-we-learn-when-assigning-sentiment-in-the-bond/","scores":{"empirical_rigor":7.5,"math_complexity":5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes BondBERT, a transformer‑based language model fine‑tuned on bond‑specific news for sentiment analysis in the bond market.","quote":"We introduce BondBERT, a transformer-based language model fine-tuned on bond-specific news.","summary":"Bond markets respond differently to macroeconomic news compared to equity markets, yet most sentiment models are trained primarily on general financial or equity news data. However, bond prices often move in the opposite direction to economic optimism, making general or equity-based sentiment tools…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The study is limited to UK sovereign bonds because corporate bonds are illiquid.","type":"market","stated":"explicit","quote":"The analysis is restricted to UK sovereign bonds, since the illiquidity of corporate bonds prevents a meaningful evaluation"},{"assumption":"Sentiment labels are generated synthetically using GPT‑4.1‑nano.","type":"data","stated":"explicit","quote":"the model is trained on synthetic labels generated by GPT-4.1-nano."},{"assumption":"Fine‑tuning on the bond‑specific sentiment dataset yields a valid model for bond sentiment.","type":"model","stated":"explicit","quote":"We fine-tuned this model on our bond-specific sentiment dataset to create BondBERT."}]},"datasets":{"status":"available","items":[{"name":"UK bond‑related news articles","provider":"SerpAPI (multiple financial outlets)","kind":"text-news","access":"unknown","period":"2018-2025","universe":"UK bond market articles","quote":"In total, nearly 45,000 UK bond-related news articles were collected from 2018–2025"},{"name":"BondBERT training corpus","provider":null,"kind":"text-news","access":"unknown","period":"2018-2021","universe":"International bond‑related news","quote":"The training corpus for BondBERT comprised approximately 17,000 international bond-related news articles spanning 2018–2021"},{"name":"10 UK sovereign bond price data","provider":null,"kind":"market-prices","access":"unknown","period":"2018-2025","universe":"10 liquid UK sovereign bonds","quote":"In total, the 10 bonds were traded around 30,000 times in January 2022, and trade frequency increased over the period, reaching around 100,000 monthly trades in January 2025."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"n/a","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"BondBERT achieves the highest directional accuracy on all topics and consistently outperforms the random baseline.","kind":"performance","quote":"BondBERT (blue bars) has the highest directional accuracy on all five topics and is the only model that consistently outperforms the random baseline."},{"finding":"BondBERT attains the lowest normalised RMSE (0.0079) and the highest information coefficient (0.8000) among the models.","kind":"predictive-accuracy","quote":"BondBERT achieves the lowest normalised RMSE and the highest IC, which suggest that it can be used to predict price movements more accurately than the other models."},{"finding":"Diebold–Mariano tests reject the null of equal forecast accuracy in favor of BondBERT for half of the bonds, indicating statistically significant RMSE improvements.","kind":"statistical","quote":"We see that the null is rejected in favour of Bond‑BERT in half of the bonds (values in bold), which demonstrates that BondBERT generates statistically significant improvements in normalised RMSE."},{"finding":"BondBERT consistently produces positive correlations with bond returns and outperforms FinBERT, FinGPT, and Instruct‑FinGPT in alignment and forecasting accuracy.","kind":"performance","quote":"BondBERT consistently produces positive correlations with bond returns, and achieves higher alignment and forecasting accuracy than the three baseline models."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":38,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/Tjbarter/Sentiment-Bond-Analysis","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:24:00Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}