target-price-valuation-listed-companies-multimodal-financial-model-given-large-scale CLM-0645For target-price valuation of listed companies, a multimodal financial model given large-scale financial-corpus pre-training followed by institution-specific fine-tuning has lower mean absolute valuation error than a general model prompted zero-shot, a single-stage fine-tuned financial LLM, and an analyst-parameterized DCF spreadsheet.
Capability: Competence in a specialist domain
Observed on
200 listed companies, target price compared against independent analyst consensus; baselines are GPT-4 zero-shot, FinGPT single-stage fine-tuning, and an analyst-input DCF spreadsh.
Model cards: GPT-4
Sources
- supportsFrontiers in FinTech: Multimodal Foundation Models for Financial Reporting and Decision ScienceMeasured on one 200-company panel with analyst consensus as ground truth, no confidence intervals or seeds reported, and the pre-training corpus differs from the baselines' corpora, so the design does not isolate staging from data volume. Consensus price targets are a proxy, not realized value.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For financial valuation of listed companies, a two-stage domain adaptation — large-scale financial-corpus pre-training followed by institution-specific fine-tuning — lowers target-price error more than single-stage fine-tuning or zero-shot prompting of a general model.Competence in a specialist domain · reviewed by AI
- When a text LLM is prompted to forecast numeric price series, feeding the history as integer-rounded values on the original price scale gives lower forecast error than full-decimal raw values, standard-normalized values, or per-window instance-normalized values, because rounding cuts token fragmentation while keeping magnitudes in the distribution the model saw in pretraining.Predicting future events · reviewed by AI
- For instruction tuning an 8B open model on text-to-SQL, a curated set of under 900 examples selected to cover every table in the target schemas and score well on question-SQL alignment reaches higher execution accuracy than pipelines trained on tens of thousands to millions of samples, and dropping the schema-coverage term from the selection objective costs more accuracy than dropping any single quality term.Writing a reusable locator: regex, SQL, XPath · reviewed by AI
- For LLM data-preparation pipelines in specialist domains (math, finance, law, medicine), diagnosing a small pilot set of generated samples against domain-selected quality criteria and rewriting the individual pipeline components (chunking, instruction builder, response generator) before full-scale generation yields training data with higher downstream fine-tuning utility than post-hoc filtering or one-shot agent/skill generators using the same backbone — but the gain is non-monotonic in rounds, peaking at two and degrading after.Improving its own scaffolding from failures · reviewed by AI
- When 7-8B open-weight instruct models are fully fine-tuned on a single domain dataset, confining gradient updates to FFN neurons that activate stably across the training set and adding an MSE loss that pulls activations back toward pre-computed activation anchors retains far more general-benchmark ability (MMLU, BBH, TyDiQA) than full-parameter fine-tuning, by about 9.9 points on average, while also raising in-domain scores.Retaining skills and safety after fine-tuning · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: low. Falsifier as drafted: A matched-compute comparison in which single-stage fine-tuning on the same combined data reaches equal or lower valuation MAE than the two-stage protocol. Drafted stance toward financial-valuation-listed-companies-two-stage-domain-adaptation-large-scale-financial-corpus: supports -- The paper reports two-stage domain adaptation beating both single-stage fine-tuning and zero-shot prompting on valuation error for 200 listed companies.