{"paper_id":"2510.15993","title":"Aligning Language Models with Investor and Market Behavior for Financial Recommendations","authors":["Fernando Spadea","Oshani Seneviratne"],"paper_date":"2025-10-14","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.15993v1","page_url":"https://thequant.space/flowcharts/aligning-language-models-with-investor-and-market-behavior-f/","scores":{"empirical_rigor":7,"math_complexity":5.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes FLARKO, a novel framework that combines large language models, knowledge graphs, and Kahneman‑Tversky Optimization to produce financially profitable and behaviorally aligned asset recommendations.","quote":"We present FLARKO (Financial Language-model for Asset Recommendation with Knowledge-graph Optimization), a novel framework that integrates Large Language Models (LLMs), Knowledge Graphs (KGs), and Kahneman-Tversky Optimization (KTO) to generate asset recommendations that are both profitable and behaviorally aligned.","summary":"Most financial recommendation systems often fail to account for key behavioral and regulatory factors, leading to advice that is misaligned with user preferences, difficult to interpret, or unlikely to be followed. We present FLARKO (Financial Language-model for Asset Recommendation with…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Investor intent and preferences can be captured by encoding past transaction behavior in a Personal Knowledge Graph.","type":"data","stated":"explicit","quote":"A Personal Knowledge Graph (PKG): Encodes an investor’s past transaction behavior, capturing asset interactions over time and serving as a proxy for user intent and preferences."},{"assumption":"Mid‑sized language models (1.7B‑4B parameters) are sufficient to achieve state‑of‑the‑art performance, and larger models do not necessarily improve results.","type":"model","stated":"explicit","quote":"performance does not strictly increase with model size; in fact, models in the 1.7B to 4B parameter range often delivered the best results, even outperforming the larger 8B model."},{"assumption":"Federated learning can be performed without sharing raw sensitive data, using LoRA‑based parameter‑efficient tuning and 4‑bit quantization to keep communication costs low.","type":"execution","stated":"explicit","quote":"employs communication-efficient federated learning via low rank adaptation of LLMs (LoRA)-based parameter-efficient tuning."},{"assumption":"Behavioral alignment can be achieved by fine‑tuning the LLM with Kahneman‑Tversky Optimization using only binary feedback on recommendation desirability.","type":"model","stated":"explicit","quote":"To ensure that FLARKO’s recommendations align with actual user preferences and investment behavior, we fine-tune the LLM using KTO [2], a lightweight, behaviorally motivated alignment method. KTO requires only binary feedback on whether a model’s recommendation is desirable or not."}]},"datasets":{"status":"available","items":[{"name":"FAR-Trans","provider":null,"kind":"market-prices","access":"unknown","period":null,"universe":null,"quote":"Evaluated on the FAR-Trans dataset, FLARKO consistently outperforms state-of-the-art recommendation baselines on behavioral alignment and joint profitability."}],"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":"FLARKO consistently outperforms state‑of‑the‑art recommendation baselines on behavioral alignment and joint profitability.","kind":"performance","quote":"FLARKO consistently outperforms state-of-the-art recommendation baselines on behavioral alignment and joint profitability."},{"finding":"Mid‑sized models (1.7B‑4B parameters) achieve the best scores on preference and combined metrics, while the largest 8B model does not improve performance.","kind":"performance","quote":"Qwen3-1.7B achieves the best scores on Pref@3 and Comb@3, while Qwen3-4B achieves the best Prof@3. The largest model, Qwen3-8B, does not outperform its smaller counterparts on any metric."},{"finding":"In federated settings, Qwen3‑4B improves its peak preference and combined scores compared to its centralized counterpart, showing resilience to federation‑induced degradation.","kind":"performance","quote":"Qwen3-4B manages to improve its results in the federated testing compared to its centralized counterpart, specifically in its peak Pref@3 and Comb@3 scores."},{"finding":"Ablation studies confirm that both the Market Knowledge Graph and Personal Knowledge Graph contribute meaningfully to recommendation quality, with their combination yielding the strongest performance.","kind":"performance","quote":"Ablation studies further validate FLARKO’s design: both historical market context (MKG) and personalized behavioral signals (PKG) contribute meaningfully to recommendation quality, with their combination yielding the strongest performance."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":21,"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/brains-group/FLARKO","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":"2026-11-14T17:24:30Z"},"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/"}