Reasoning Beyond the Obvious: Evaluating Divergent and Convergent Thinking in LLMs for Financial Scenarios
Most reasoning benchmarks for LLMs emphasize factual accuracy or step-by-step logic. In finance, however, professionals must not only converge on optimal decisions but also generate creative, plausible futures under uncertainty. We introduce ConDiFi, a benchmark that jointly evaluates divergent and convergent thinking in LLMs for financial tasks. ConDiFi features 607 macro-financial prompts for divergent reasoning and 990 multi-hop adversarial MCQs for convergent reasoning. Using this benchmark, we evaluated 14 leading models and uncovered striking differences. Despite high fluency, GPT-4o underperforms on Novelty and Actionability. In contrast, models like DeepSeek-R1 and Cohere Command R+ rank among the top for generating actionable, insights suitable for investment decisions. ConDiFi provides a new perspective to assess reasoning capabilities essential to safe and strategic deployment of LLMs in finance.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Beyond One Path: Evaluating and Enhancing Divergent Thinking in Interactive LLM Agents
Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generations, failing to capture how an agent reasons through iterative interac…
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
Zero-shot Event Detection (ED), the task of identifying event mentions in natural language text without any training data, is critical for document understanding in specialized domains. Understanding the complex event on…
document understandingEvent DetectionTransfer LearningTinyTim: A Family of Language Models for Divergent Generation
In the search for artificial general intelligence, model development and training has focused primarily on vast datasets of known problems and their accepted solutions. This process necessarily produces convergent system…
Consensus is Strategically Insufficient: Reasoning-Trace Disagreement as a Knowledge-Representation Signal
Multi-agent systems are commonly designed to reduce disagreement through voting, consensus protocols, debate, or fault-tolerant aggregation. We argue that this objective is insufficient for value-laden tasks, where disag…
From Shots to Stories: LLM-Assisted Video Editing with Unified Language Representations
Large Language Models (LLMs) and Vision-Language Models (VLMs) have demonstrated remarkable reasoning and generalization capabilities in video understanding; however, their application in video editing remains largely un…
Video EditingVideo Understanding