arXiv AI

Thin Evidence, Thick Priors: How Language Models Substitute Identity for Missing Financial Facts

The study investigates how large language models (LLMs) compensate for missing financial information by substituting user identity cues. Using 96,600 prompts to Llama‑3.1‑8B‑Instruct, the authors varied the amount of financial facts provided while keeping the underlying finances constant, and measured changes in recommended equity allocations across 100 financial profiles, 138 personas, and seven disclosure conditions. Results show that as financial facts are removed, the influence of identity on advice grows dramatically—from 5 % of variation with full disclosure to 96 % with none—while household size becomes the most reliable predictor when evidence is scarce, and gender effects persist even after controlling for standard errors. "whyItMatters":"The findings highlight that LLM‑based advisory systems can produce biased financial recommendations when users provide incomplete information, underscoring the need for audits that reflect real‑world disclosure levels and consider the full spectrum of user identities."

arXiv Computation and Language

Sep 4

The Analyst in the Prompt: Role, Retrieval, and Memory Biases in LLM Financial Analysis

The study examines how user context—such as memory, profiles, and role prompts—affects Large Language Models’ (LLMs) financial analysis. Using 3,575 SEC filings and twelve LLMs, the authors distinguish between evidence selection and interpretation, finding that most context spillover arises from differing interpretations under various roles rather than from retrieving different evidence. They evaluate two mitigation strategies—expressing investor mindset as a user profile instead of an assistant role, and separating evidence-based from personalized outputs—both of which reduce but do not eliminate spillover, with effectiveness varying across models.

By Ahmed Asaad, Amr Mohamed, Yang Zhang, Omneya Abdelsalam

llms

Hugging Face Trending Papers

Sep 2

The Analyst in the Prompt: Role, Retrieval, and Memory Biases in LLM Financial Analysis

The paper investigates how user context—such as memory, profiles, and role prompts—affects large language models’ financial analysis. By testing 3,575 SEC filings across twelve LLMs, the study distinguishes between evidence selection and interpretation, finding that interpretation under different roles drives most user-context spillover. Two mitigation strategies—using a user profile instead of an assistant role and separating evidence-based from personalized outputs—reduce but do not eliminate this spillover, with effectiveness varying by model.

llms

arXiv Machine Learning

Jun 2

Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation

arXiv:2606. 02528v1 Announce Type: cross Abstract: Large language models now power robo-advisors and trading agents, yet whether they carry built-in biases toward specific assets is largely untested.

By Wenbin Wu

llms agents

arXiv Computation and Language

Sep 1

Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data

arXiv:2606.29793v3 Announce Type: replace Abstract: Demand for personalized financial advice is growing, yet current LLM-based advisors often fail to provide consistent and specialized guidance.\ Sim...

By Suhwan Park, Hoyoung Lee, Zhangyang Wang, Alejandro Lopez-Lira, Young Cha, Chanyeol Choi, Jaewon Choi, Yongjae Lee

llms

Hugging Face Trending Papers

Jul 29

Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text

Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in qualitatively different ways. Detecting a conflict is only the first step: review workflows may also need to determine its type, since numerical, temporal, referential, factual, and normative inconsistencies require different evidence and downstream checks.

llms rag fine-tuning benchmarks

arXiv AI

Aug 19

Communicating Credit Risk with Large Language Models: Evaluation of Explanations from Standard and Alternative Data-Based Models

The study investigates whether Large Language Models (LLMs) can translate technical explanations from credit risk models into stakeholder-friendly narratives. Using Freddie Mac loan data, the authors compare standard tabular models (XGBoost + SHAP) with alternative data pipelines (GNN + GNNExplainer and a bimodal mix) and generate explanations with three LLM configurations: a small fine‑tuned Gemma 3 4B, a large fine‑tuned DeepSeek R1 70B, and a zero‑shot Gemini 2.5. Findings show that the quality of explanations is more dependent on the evidence representation than on the LLM, that narratives reliably identify influential factors but are less consistent about the direction of influence, and that credit professionals demand higher evidentiary standards than non‑professionals.

By Sahab Zandi, Noah Kostesku, Christophe Mues, Mar\'ia \'Oskarsd\'ottir, Cristi\'an Bravo

llms fine-tuning safety

arXiv AI

Jun 12

Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filings

arXiv:2602. 07294v4 Announce Type: replace-cross Abstract: With the increasing deployment of Large Language Models (LLMs) in the finance domain, LLMs are increasingly expected to parse complex regulatory disclosures.

By Yidong Jiang, Junrong Chen, Eftychia Makri, Jialin Chen, Peiwen Li, Ali Maatouk, Leandros Tassiulas, Eliot Brenner, Bing Xiang, Rex Ying

llms rag benchmarks safety

arXiv AI

Jul 31

Diagnosing Fine-Grained Inconsistency Classification in Financial Disclosure Text

arXiv:2607. 26368v1 Announce Type: cross Abstract: Financial disclosures contain numerical claims, temporal statements, entity references, policy commitments, and risk descriptions that may conflict in qualitatively different ways.

By Aman Kumar, Lasitha Vidyaratne, Dipanjan D Ghosh, Arnab Chakrabarti, Ahmed K Farahat

llms rag fine-tuning benchmarks

arXiv Machine Learning

Aug 11

Beyond Aggregate Calibration: Decomposing Income-Conditional Recall Disparities in Automated Credit Default Prediction

arXiv:2608. 08202v1 Announce Type: new Abstract: Data-centric curation pipelines frequently rely on model confidence scores to flag and filter noisy or mislabeled training instances.

By Sai Srikar Boddupalli

safety

arXiv AI

Aug 11

How People Evaluate AI-, Expert-, and Peer-Style Financial Advice

arXiv:2608. 09019v1 Announce Type: cross Abstract: As generative AI increasingly becomes a common source of daily decision-making, including financial choices, it is critical to understand how people evaluate AI-generated financial advice.

By Aryan Ramchandra Kapadia, Eshwar Chandrasekharan, Koustuv Saha

arXiv AI

Sep 23

FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering

arXiv:2609.24002v1 Announce Type: new Abstract: Large language model agents increasingly answer financial questions by searching regulatory filings. Such questions are often deceptively under-specifi...

By Xinyu Wang, Tung Sum Thomas Kwok, Zhenghan Tai, Guang Cheng

llms agents nlp benchmarks

arXiv AI

Aug 3

FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation

arXiv:2607. 28934v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on characteristics like race and gender.

By Martin Lukk (University of Toronto)

llms benchmarks safety

Related stories