mlsanityData to 14 Oct 2026

GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning

arXiv 2404.02934 ↗First posted 3 Apr 2024cs.CL cs.AI cs.CYcited by 9

On the map: LLM reasoning → Reasoning benchmarks and evaluation

also in 1 more
Abstract (arXiv)

This paper investigates the ethical implications of aligning Large Language Models (LLMs) with financial optimization, through the case study of GreedLlama, a model fine-tuned to prioritize economically beneficial outcomes. By comparing GreedLlama's performance in moral reasoning tasks to a base Llama2 model, our results highlight a concerning trend: GreedLlama demonstrates a marked preference for profit over ethical considerations, making morally appropriate decisions at significantly lower rates than the base model in scenarios of both low and high moral ambiguity. In low ambiguity situations, GreedLlama's ethical decisions decreased to 54.4%, compared to the base model's 86.9%, while in high ambiguity contexts, the rate was 47.4% against the base model's 65.1%. These findings emphasize the risks of single-dimensional value alignment in LLMs, underscoring the need for integrating broader ethical values into AI development to ensure decisions are not solely driven by financial incentives. The study calls for a balanced approach to LLM deployment, advocating for the incorporation of ethical considerations in models intended for business applications, particularly in light of the absence of regulatory oversight.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 19 of its 30 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

19 of 30 references.

References · 19

  1. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  2. 2023BloombergGPT: A Large Language Model for Financecited by 939
  3. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  4. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 557
  5. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 297
  6. 2023FinGPT: Open-Source Financial Large Language Modelscited by 253
  7. 2023Evaluating the Moral Beliefs Encoded in LLMscited by 215
  8. 2023InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuningcited by 82
  9. 2023FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasetscited by 69
  10. 2023FinGPT: Democratizing Internet-scale Data for Financial Large Language Modelscited by 67
  11. 2023Large Language Models for Supply Chain Optimizationcited by 64
  12. 2023Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Modelscited by 58
7 more
  1. 2023Large Language Models can accomplish Business Process Management Taskscited by 34
  2. 2023GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validationcited by 21
  3. 2023Enhancing Trust in LLM-Based AI Automation Agents: New Considerations and Future Challengescited by 19
  4. 2023GPT-InvestAR: Enhancing Stock Investment Strategies through Annual Report Analysis with Large Language Modelscited by 12
  5. 2023Can LLMs be Good Financial Advisors?: An Initial Study in Personal Decision Making for Optimized Outcomescited by 11
  6. 2023Generative AI for Business Strategy: Using Foundation Models to Create Business Strategy Toolscited by 4
  7. 2023Language Models for Business Optimisation with a Real World Case Study in Production Schedulingcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 4.

9 papers.

  1. 2024A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengescited by 90
  2. 2026Large Language Model Reasoning Failurescited by 21
  3. 2025CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectivescited by 10
  4. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 5
  5. 2025Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulationcited by 3
  6. 2026MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignmentcited by 2
  7. 2026Do Emotions Influence Moral Judgment in Large Language Models?cited by 2
  8. 2025EMNLP: Educator-role Moral and Normative Large Language Models Profilingcited by 0
  9. 2026IREA: Intermediate Representation-based Embedding Alignment for Normative RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MoralBench: Moral Evaluation of LLMs
  2. 2024Exploring and steering the moral compass of Large Language Models
  3. 2025Diverse Human Value Alignment for Large Language Models via Ethical Reasoning
  4. 2025Auditing the Ethical Logic of Generative AI Models
  5. 2025The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approach
  6. 2024Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
  7. 2025One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
  8. 2024LocalValueBench: A Collaboratively Built and Extensible Benchmark for Evaluating Localized Value Alignment and Ethical Safety in Large Language Models