{"id":"a0f6c2eb77e163d73f5629ee148d482a2482c783c82eb32f8b574ce5ac18992e","title":"Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov argue in Bank Underground about MPC transcripts","argument":"Published on October 15, 2026, Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts, extracting measures of members’ views on inflation and growth and the arguments behind policy decisions. They argue that vote tallies can conceal different concerns behind the same decision. In their analysis, growth concerns weakened and later strengthened over the sample, while concerns about above-target inflation increased. They report that both measures predict votes for higher Bank Rate, but only growth measures explain votes to cut it. They also report that these measures relate to voting beyond aggregate data and official forecasts. Their analysis focuses on Bank Rate votes, not asset purchase decisions. The authors conclude that historical transcripts contain information beyond vote tallies and suggest comparing transcript narratives with contemporaneous public communications as future work. Whether their measures capture policymakers’ full reasoning remains unknown.","topicIds":["investment-booms-and-busts"],"domain":"other","claimType":"attributed reading","limits":"Text as retrieved on October 29, 2026; originally published October 15, 2026. The authors analyse statements and voting patterns; the text does not establish that the extracted measures capture policymakers’ full reasoning.","speaker":{"name":"Bank of England","roleAtSource":"Publisher"},"source":{"title":"Narratives under the microscope: what MPC transcripts can tell us about policy thinking","publisher":"Bank of England","format":"Article","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","publishedAt":"2026-10-15T08:00:00.000Z","dateBasis":"Date supplied by the publisher’s feed."},"evidence":[{"text":"The authors analyse MPC transcripts with LLMs to extract measures of individual members’ views and policy arguments.","excerpt":"In this post, we use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts from 2015 to 2017.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors report that growth concerns weakened and later strengthened, while concerns about above-target inflation increased over the sample.","excerpt":"We show that concerns about economic growth relative to its potential weakened and later strengthened over the sample, while concerns about above-target inflation increased.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors report that both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","excerpt":"over the sample period, both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors say vote tallies alone may not capture the different concerns behind a policy decision.","excerpt":"The same vote can reflect very different concerns about inflation, growth, risks, and their balance.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors' analysis focuses on Bank Rate votes, not asset purchase decisions.","excerpt":"We focus on Bank Rate voting specifically, and not on the asset purchase decisions taken over this period.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors suggest comparing historical transcript narratives with contemporaneous public communications in future work.","excerpt":"Future work could compare narratives in publicly released historical transcripts with contemporaneous public communications, such as MPC speeches","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How might comparing historical transcript narratives with contemporaneous public communications change what can be learned about how policymakers express their reasoning?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov argue in Bank Underground about MPC transcripts","summary":"Published on October 15, 2026, Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts, extracting measures of members’ views on inflation and growth and the arguments behind policy decisions. They argue that vote tallies can conceal different concerns behind the same decision. In their analysis, growth concerns weakened and later strengthened over the sample, while concerns about above-target inflation increased. They report that both measures predict votes for higher Bank Rate, but only growth measures explain votes to cut it. They also report that these measures relate to voting beyond aggregate data and official forecasts. Their analysis focuses on Bank Rate votes, not asset purchase decisions. The authors conclude that historical transcripts contain information beyond vote tallies and suggest comparing transcript narratives with contemporaneous public communications as future work. Whether their measures capture policymakers’ full reasoning remains unknown.","question":"How might comparing historical transcript narratives with contemporaneous public communications change what can be learned about how policymakers express their reasoning?","claims":[{"text":"The authors analyse MPC transcripts with LLMs to extract measures of individual members’ views and policy arguments.","excerpt":"In this post, we use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts from 2015 to 2017.","support":"source-stated"},{"text":"The authors report that growth concerns weakened and later strengthened, while concerns about above-target inflation increased over the sample.","excerpt":"We show that concerns about economic growth relative to its potential weakened and later strengthened over the sample, while concerns about above-target inflation increased.","support":"source-stated"},{"text":"The authors report that both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","excerpt":"over the sample period, both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","support":"source-stated"},{"text":"The authors say vote tallies alone may not capture the different concerns behind a policy decision.","excerpt":"The same vote can reflect very different concerns about inflation, growth, risks, and their balance.","support":"source-stated"},{"text":"The authors' analysis focuses on Bank Rate votes, not asset purchase decisions.","excerpt":"We focus on Bank Rate voting specifically, and not on the asset purchase decisions taken over this period.","support":"source-stated"},{"text":"The authors suggest comparing historical transcript narratives with contemporaneous public communications in future work.","excerpt":"Future work could compare narratives in publicly released historical transcripts with contemporaneous public communications, such as MPC speeches","support":"source-stated"}],"limitations":["Text as retrieved on October 29, 2026; originally published October 15, 2026.","The authors analyse statements and voting patterns; the text does not establish that the extracted measures capture policymakers’ full reasoning."],"mediaId":null,"correctionReason":null,"id":"a0f6c2eb77e163d73f5629ee148d482a2482c783c82eb32f8b574ce5ac18992e","publicationId":"d7104557-618a-d0ad-d265-98eea126e7c2","version":1,"sourceUrl":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","sourceTitle":"Narratives under the microscope: what MPC transcripts can tell us about policy thinking","publisher":"Bank of England","publishedAt":"2026-10-15T08:00:00.000Z","originalPublished":{"value":"2026-10-15T08:00:00.000Z","precision":"instant","basis":"backfill:feed_published"},"firstObservedAt":"2026-10-29T17:15:56.968Z","createdAt":"2026-11-04T22:23:25.196Z","historical":true,"entityIds":[],"topicIds":["investment-booms-and-busts"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"1f04e4d9b3097f82135052e751e6e2f0e33e16b23df35ca929f7165d03343e88","rubricVersion":"em-backfill-context/3","provider":"typesafe","model":"jev-1.13.0","reasonCodes":["bridge_admitted_by_model"],"confidence":0.66,"decidedAt":"2026-10-29T17:15:55.208Z"},"provenance":{"textHash":"e23324cecd37b2106336cde0fe1ced8fcb4d99e36ea40108b404c0cb8d107742","observationId":"824a1e3b728631463ab633b24f3f996496a41dc30fa086e049cb3e03771a3a1d","retrievedAt":"2026-10-29T17:17:47.920Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"4adbb131-f8a2-0e0b-f511-69d07cd04117"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"b2b4d53e-c044-c823-e035-8a52172fba1d"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-04T22:18:46.912Z","model":"anthropic/claude-opus-5.5"}},"canonicalUrl":"https://escapemeridian.com/readings/dragos-gorduza-livia-silva-paranhos-and-ivan-yotzov-argue-in-a0f6c2eb","formats":{"html":"/readings/dragos-gorduza-livia-silva-paranhos-and-ivan-yotzov-argue-in-a0f6c2eb","markdown":"/readings/dragos-gorduza-livia-silva-paranhos-and-ivan-yotzov-argue-in-a0f6c2eb.md","json":"/readings/dragos-gorduza-livia-silva-paranhos-and-ivan-yotzov-argue-in-a0f6c2eb.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-llm","name":"Large language model","explanation":"A language model with many learned numerical settings, used to process and generate language.","referenceUrl":"https://developers.google.com/machine-learning/glossary#large-language-model"}],"entities":[]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"a0f6c2eb77e163d73f5629ee148d482a2482c783c82eb32f8b574ce5ac18992e","revision":"d7104557-618a-d0ad-d265-98eea126e7c2","revisionKind":"publication-id","title":"Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov argue in Bank Underground about MPC transcripts","url":"https://escapemeridian.com/readings/dragos-gorduza-livia-silva-paranhos-and-ivan-yotzov-argue-in-a0f6c2eb"},"source":{"type":"source","id":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","revision":"e23324cecd37b2106336cde0fe1ced8fcb4d99e36ea40108b404c0cb8d107742","revisionKind":"sha256-source-text","title":"Narratives under the microscope: what MPC transcripts can tell us about policy thinking","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"a0f6c2eb77e163d73f5629ee148d482a2482c783c82eb32f8b574ce5ac18992e","title":"Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov argue in Bank Underground about MPC transcripts","argument":"Published on October 15, 2026, Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts, extracting measures of members’ views on inflation and growth and the arguments behind policy decisions. They argue that vote tallies can conceal different concerns behind the same decision. In their analysis, growth concerns weakened and later strengthened over the sample, while concerns about above-target inflation increased. They report that both measures predict votes for higher Bank Rate, but only growth measures explain votes to cut it. They also report that these measures relate to voting beyond aggregate data and official forecasts. Their analysis focuses on Bank Rate votes, not asset purchase decisions. The authors conclude that historical transcripts contain information beyond vote tallies and suggest comparing transcript narratives with contemporaneous public communications as future work. Whether their measures capture policymakers’ full reasoning remains unknown.","topicIds":["investment-booms-and-busts"],"domain":"other","claimType":"attributed reading","limits":"Text as retrieved on October 29, 2026; originally published October 15, 2026. The authors analyse statements and voting patterns; the text does not establish that the extracted measures capture policymakers’ full reasoning.","speaker":{"name":"Bank of England","roleAtSource":"Publisher"},"source":{"title":"Narratives under the microscope: what MPC transcripts can tell us about policy thinking","publisher":"Bank of England","format":"Article","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","publishedAt":"2026-10-15T08:00:00.000Z","dateBasis":"Date supplied by the publisher’s feed."},"evidence":[{"text":"The authors analyse MPC transcripts with LLMs to extract measures of individual members’ views and policy arguments.","excerpt":"In this post, we use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts from 2015 to 2017.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors report that growth concerns weakened and later strengthened, while concerns about above-target inflation increased over the sample.","excerpt":"We show that concerns about economic growth relative to its potential weakened and later strengthened over the sample, while concerns about above-target inflation increased.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors report that both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","excerpt":"over the sample period, both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors say vote tallies alone may not capture the different concerns behind a policy decision.","excerpt":"The same vote can reflect very different concerns about inflation, growth, risks, and their balance.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors' analysis focuses on Bank Rate votes, not asset purchase decisions.","excerpt":"We focus on Bank Rate voting specifically, and not on the asset purchase decisions taken over this period.","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"},{"text":"The authors suggest comparing historical transcript narratives with contemporaneous public communications in future work.","excerpt":"Future work could compare narratives in publicly released historical transcripts with contemporaneous public communications, such as MPC speeches","url":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","relationship":"Source-stated"}],"sourceMedia":{"status":"unchecked","sourceUrl":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","checkedAt":null,"items":[]},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How might comparing historical transcript narratives with contemporaneous public communications change what can be learned about how policymakers express their reasoning?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov argue in Bank Underground about MPC transcripts","summary":"Published on October 15, 2026, Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts, extracting measures of members’ views on inflation and growth and the arguments behind policy decisions. They argue that vote tallies can conceal different concerns behind the same decision. In their analysis, growth concerns weakened and later strengthened over the sample, while concerns about above-target inflation increased. They report that both measures predict votes for higher Bank Rate, but only growth measures explain votes to cut it. They also report that these measures relate to voting beyond aggregate data and official forecasts. Their analysis focuses on Bank Rate votes, not asset purchase decisions. The authors conclude that historical transcripts contain information beyond vote tallies and suggest comparing transcript narratives with contemporaneous public communications as future work. Whether their measures capture policymakers’ full reasoning remains unknown.","question":"How might comparing historical transcript narratives with contemporaneous public communications change what can be learned about how policymakers express their reasoning?","claims":[{"text":"The authors analyse MPC transcripts with LLMs to extract measures of individual members’ views and policy arguments.","excerpt":"In this post, we use large language models (LLMs) to analyse Bank of England Monetary Policy Committee (MPC) transcripts from 2015 to 2017.","support":"source-stated"},{"text":"The authors report that growth concerns weakened and later strengthened, while concerns about above-target inflation increased over the sample.","excerpt":"We show that concerns about economic growth relative to its potential weakened and later strengthened over the sample, while concerns about above-target inflation increased.","support":"source-stated"},{"text":"The authors report that both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","excerpt":"over the sample period, both growth and inflation measures predict votes for higher rates, but only growth measures explain votes to cut Bank Rate.","support":"source-stated"},{"text":"The authors say vote tallies alone may not capture the different concerns behind a policy decision.","excerpt":"The same vote can reflect very different concerns about inflation, growth, risks, and their balance.","support":"source-stated"},{"text":"The authors' analysis focuses on Bank Rate votes, not asset purchase decisions.","excerpt":"We focus on Bank Rate voting specifically, and not on the asset purchase decisions taken over this period.","support":"source-stated"},{"text":"The authors suggest comparing historical transcript narratives with contemporaneous public communications in future work.","excerpt":"Future work could compare narratives in publicly released historical transcripts with contemporaneous public communications, such as MPC speeches","support":"source-stated"}],"limitations":["Text as retrieved on October 29, 2026; originally published October 15, 2026.","The authors analyse statements and voting patterns; the text does not establish that the extracted measures capture policymakers’ full reasoning."],"mediaId":null,"correctionReason":null,"id":"a0f6c2eb77e163d73f5629ee148d482a2482c783c82eb32f8b574ce5ac18992e","publicationId":"d7104557-618a-d0ad-d265-98eea126e7c2","version":1,"sourceUrl":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","sourceTitle":"Narratives under the microscope: what MPC transcripts can tell us about policy thinking","publisher":"Bank of England","publishedAt":"2026-10-15T08:00:00.000Z","originalPublished":{"value":"2026-10-15T08:00:00.000Z","precision":"instant","basis":"backfill:feed_published"},"firstObservedAt":"2026-10-29T17:15:56.968Z","createdAt":"2026-11-04T22:23:25.196Z","historical":true,"entityIds":[],"topicIds":["investment-booms-and-busts"],"media":[],"sourceMedia":{"status":"unchecked","sourceUrl":"https://bankunderground.co.uk/2026/10/15/narratives-under-the-microscope-what-mpc-transcripts-can-tell-us-about-policy-thinking/","checkedAt":null,"items":[]},"editorialDecision":{"outcome":"accept","mediaId":null,"inputHash":"1f04e4d9b3097f82135052e751e6e2f0e33e16b23df35ca929f7165d03343e88","rubricVersion":"em-backfill-context/3","provider":"typesafe","model":"jev-1.13.0","reasonCodes":["bridge_admitted_by_model"],"confidence":0.66,"decidedAt":"2026-10-29T17:15:55.208Z"},"provenance":{"textHash":"e23324cecd37b2106336cde0fe1ced8fcb4d99e36ea40108b404c0cb8d107742","observationId":"824a1e3b728631463ab633b24f3f996496a41dc30fa086e049cb3e03771a3a1d","retrievedAt":"2026-10-29T17:17:47.920Z","kind":"publisher-page","preparer":{"model":"openai/gpt-6-luna","runId":"4adbb131-f8a2-0e0b-f511-69d07cd04117"},"reviewer":{"model":"anthropic/claude-opus-5.5","runId":"b2b4d53e-c044-c823-e035-8a52172fba1d"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-04T22:18:46.912Z","model":"anthropic/claude-opus-5.5"}}}],"audits":[{"publicationId":"d7104557-618a-d0ad-d265-98eea126e7c2","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly attributes the analysis to Dragos Gorduza, Livia Silva Paranhos and Ivan Yotzov on Bank Underground. It keeps findings as the authors' reported results rather than Bank of England policy, which matches the blog's disclaimer.","excerpt":"The views expressed here are those of the authors, and are not necessarily those of the Bank of England, or its policy committees."},{"dimension":"summary","status":"uncertain","explanation":"The summary never says the transcripts cover 2015 to 2017, a period that includes the June 2016 EU referendum. It says concerns changed 'over the sample' without defining that sample, so a reader cannot tell when these shifts happened or that the transcripts are historical and released with an eight-year lag. 'Bank Rate' is also central but not explained as the Bank of England's main policy interest rate. Smallest repair: name the 2015–17 period, the Brexit-referendum context, and gloss Bank Rate.","excerpt":"Our main data set comprises 258 publicly available statements from individual MPC members covering 29 meeting transcripts between 2015 and 2017."},{"dimension":"date","status":"pass","explanation":"The reading states October 15, 2026, which matches the UTC day of originalPublished and the page dateline. The second date in the dateline (14/10/2026) is the page's own artifact and is not repeated. The page was edited after publication, but the cited passages are core article text. There is no hindsight framing, and the future work is framed as a suggestion.","excerpt":"15/10/202614/10/2026"},{"dimension":"support","status":"pass","explanation":"Each claim matches body text that is plainly part of the original post, so the later edit does not cast doubt on them. The 'beyond aggregate data and official forecasts' statement matches the regression controls the authors describe. The limitation about full reasoning is appropriately cautious, and the question follows from the authors' stated future work.","excerpt":"Therefore, we test whether these new metrics capture any variation in voting behaviour over and above the aggregate data and official forecasts."},{"dimension":"media","status":"pass","explanation":"No media was selected and no verified candidates were supplied, so there is nothing to misidentify.","excerpt":null}],"createdAt":"2026-11-04T22:18:46.912Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}