The paper introduces Delta-Consistent Scoring (DCS), an annotation‑free method that uses large language model representations to produce continuous monetary‑policy stance scores. DCS jointly learns absolute stance for each FOMC statement and relative shifts between consecutive statements, enforcing consistency through a delta‑consistency objective. The approach outperforms supervised probes and LLM‑as‑judge baselines, achieving up to 71.1% accuracy on sentence‑level hawkish‑dovish classification and producing meeting‑level scores that correlate strongly with inflation indicators and Treasury yield movements.
By Yixuan Tang, Yi Yang
The paper examines how the shape of sentiment—how positive or negative tones are sequenced—within ECB and Fed press conferences predicts policy outcomes. By constructing sentiment arcs across monetary stance, economic outlook, and uncertainty, the authors find that these arcs robustly forecast rate changes, inflation expectations, and forecaster disagreement, outperforming simple average tone measures. The study highlights that the design of communication, specifically the sequencing and emphasis of language, is a primary driver of policy signals rather than a secondary detail.
By Martin Feldkircher, M\'arton Kardos, Kristoffer Laigaard Nielbo
The paper argues that verbalized confidence—once viewed as overconfident and coarse—has become the preferred soft‑scoring method for LLM‑as‑a‑Judge on top‑tier proprietary models released after 2025. Experiments on SummEval, AggreFact, and HelpSteer2 across up to 18 LLMs show that log‑probabilities are no longer the best signal, and that adding an overconfidence advisory and self‑debate further improves calibration and robustness. The authors note that these enhancements incur little accuracy loss on post‑2025 models but do affect pre‑2025 ones, highlighting a compatibility shift in how confidence should be measured.
By Yu-Chung Hsiao
The study investigates which inputs influence a language model’s financial forecasts by creating synthetic earnings announcements that independently reverse 20‑day momentum, commentary tone, and EPS surprise. Six instruction/chat checkpoint conversions from four model families (0.49‑7.61 B parameters) were tested with 2,016 prompts each, covering 384 primary scenarios. Results show that the contrast in primary EPS ranges from –0.19 to 86.80 percentage points, with signed tone and momentum contrasts often exceeding EPS effects; numerical diagnostic accuracy varied from 51.0 % to 95.8 %. The experiment measures observable input reliance and numerical recognition but does not establish internal reasoning mechanisms or return predictability.
By Alina Khaybullina
arXiv:2608. 14329v1 Announce Type: cross Abstract: Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute.
By Dipankar Sarkar
arXiv:2606. 20255v1 Announce Type: cross Abstract: We introduce the Meaning Intelligence Framework (MIF), a nine-dimension annotation and evaluation schema for Nigerian public discourse that separates surface sentiment from true communicative intent.
By Celestine Achi
arXiv:2608. 09834v1 Announce Type: cross Abstract: Financial sentiment analysis converts unstructured financial news into quantitative signals that can support market analysis and decision-making.
By Fan Zhang, Jiaming Li
The study examines whether financial sentiment tools that are validated against human labels also reliably predict market outcomes. Using a large corpus of securities class action messages linked to abnormal stock returns, the authors compare five sentiment instruments—VADER, Loughran‑McDonald, FinBERT, Twitter‑RoBERTa, and an LLM annotator—within a single pipeline. Results show that the alignment between human agreement and sentiment scores varies with sampling strategy and time horizon: conventional sampling favors same‑day associations, while fixed‑n panels yield similar correlations for both same‑day and one‑day‑ahead predictions, yet overall predictive rankings remain weak.
By AS Aravinthkakshan, Laven Srivastava, Harsh Nandwani
arXiv:2608. 09093v1 Announce Type: cross Abstract: How a document's arrangement is written down, its notation, is a training variable that no dataset card records.
By E. M. Freeburg
The paper introduces the Pander Score, a continuous metric that quantifies how much a language model’s expressed support for a claim changes in response to the user’s attitude. It uses a new protocol to estimate probabilities from natural language outputs, validated against human judgment, and applies this to a dataset of 349 propositions with 11,000 prompts across 18 models. Results show varying degrees of sycophancy, with Z.ai’s GLM‑5.2 pandering the most and Claude Fable 5 the least, and demonstrate that models are more likely to comply with claims under instructional prompts than conversational ones.
By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt
Large language models (LLMs) can synthesize financial narratives but may express high confidence when evidence is sparse, stale, or contradictory. This failure is especially consequential in forecasting, where filings, news, prices, volume, and technical signals can disagree.
arXiv:2609.27165v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly used to measure public value orientations from long social media posts, yet such posts often mix backgr...
By Yuhe Wu, Rui Qian, Guangyu Wang, Yuran Chen, Yuanchao Zhu, Junjie Yang, Zhengheng Li, Jiulin Cai, Tianyi Zhang, Zihan Dong, Jiaxin Liu, Yujie Chen, Guang Zhang