Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

• URL: http://arxiv.org/abs/2602.15173v1
• Date: Mon, 16 Feb 2026 20:24:54 GMT
• Title: Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs
• Abstract summary: We study the use of large language models in decision-making under uncertainty.<n>We find that reasoning models (RMs) and conversational models (CMs) cluster into two categories.<n>RMs tend towards rational behavior, are insensitive to the order of prospects, gain/loss framing, and explanations, and behave similarly whether prospects are explicit or presented via experience history. CMs are significantly less rational, slightly more human-like, sensitive to prospect ordering, framing, and explanation, and exhibit a large description-history gap.
• Score: 22.917052751356763
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We initiate a comparative study of LLM risky choices along two dimensions: (1) prospect representation (explicit vs. experience based) and (2) decision rationale (explanation). Our study, which involves 20 frontier and open LLMs, is complemented by a matched human subjects experiment, which provides one reference point, while an expected payoff maximizing rational agent model provides another. We find that LLMs cluster into two categories: reasoning models (RMs) and conversational models (CMs). RMs tend towards rational behavior, are insensitive to the order of prospects, gain/loss framing, and explanations, and behave similarly whether prospects are explicit or presented via experience history. CMs are significantly less rational, slightly more human-like, sensitive to prospect ordering, framing, and explanation, and exhibit a large description-history gap. Paired comparisons of open LLMs suggest that a key factor differentiating RMs and CMs is training for mathematical reasoning.

Related papers

• GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models [55.56903314809719]
  We introduce GR-Ben, a process-level benchmark specifically designed for assessing PRM's performance across two primary reasoning domains (science and logic) and nine others.<n>In domains beyond mathematical reasoning, the error-detection ability of existing PRMs and LLMs is found to be markedly weaker by comparison.<n>In general, PRMs are less adept at identifying knowledge-based errors, whereas LLMs exhibit poorer performance in detecting computational errors.
  arXiv  Detail & Related papers  (2026-05-02T02:41:48Z)
• LLMs for Explainable Business Decision-Making: A Reinforcement Learning Fine-Tuning Approach [9.942833203981069]
  Large language models (LLMs) present an opportunity to generate natural-language explanations.<n>We introduce LEXMA, a reinforcement-learning-based fine-tuning framework that produces audience-appropriate explanations.<n>LEXMA yields significant improvements in predictive performance compared with other LLM baselines.
  arXiv  Detail & Related papers  (2025-12-10T04:16:31Z)
• MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models [15.860796863065737]
  We propose a Multi-rationale INtegrated Discriminative (MIND) reasoning framework.<n>It is designed to endow MLLMs with human-like cognitive abilities of "Understand -> Rethink -> Correct"<n>It achieves a paradigm evolution from passive imitation-based reasoning to active discriminative reasoning.
  arXiv  Detail & Related papers  (2025-12-05T08:41:44Z)
• Fast, Slow, and Tool-augmented Thinking for LLMs: A Review [57.16858582049339]
  Large Language Models (LLMs) have demonstrated remarkable progress in reasoning across diverse domains.<n>Effective reasoning in real-world tasks requires adapting the reasoning strategy to the demands of the problem.<n>We propose a novel taxonomy of LLM reasoning strategies along two knowledge boundaries.
  arXiv  Detail & Related papers  (2025-08-17T07:20:32Z)
• Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences? [5.542420010310746]
  A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences and its revealed preferences.<n>This work formally defines and proposes a method to measure this preference deviation.<n>Our study will be crucial for integrating LLMs into services, especially those that interact directly with humans.
  arXiv  Detail & Related papers  (2025-05-31T23:38:48Z)
• LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities [21.42711537107199]
  We study why Large Language Models (LLMs) perform sub-optimally in decision-making scenarios.<n>We propose mitigation of these shortcomings by fine-tuning via Reinforcement Learning (RL) on self-generated CoT rationales.
  arXiv  Detail & Related papers  (2025-04-22T17:57:14Z)
• From System 1 to System 2: A Survey of Reasoning Large Language Models [72.87412996793957]
  Foundational Large Language Models excel at fast decision-making but lack depth for complex reasoning.<n>OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding.
  arXiv  Detail & Related papers  (2025-02-24T18:50:52Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.<n>Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.<n>We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• STEER: Assessing the Economic Rationality of Large Language Models [21.91812661475551]
  There is increasing interest in using LLMs as decision-making "agents" determining whether an LLM agent is reliable enough to be trusted requires a methodology for assessing such an agent's economic rationality.
  arXiv  Detail & Related papers  (2024-02-14T20:05:26Z)
• LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning [61.7853049843921]
  Chain-of-thought (CoT) prompting is a popular in-context learning approach for large language models (LLMs)<n>This paper introduces a new approach named Latent Reasoning Skills (LaRS) that employs unsupervised learning to create a latent space representation of rationales.
  arXiv  Detail & Related papers  (2023-12-07T20:36:10Z)
• Sentiment Analysis through LLM Negotiations [58.67939611291001]
  A standard paradigm for sentiment analysis is to rely on a singular LLM and makes the decision in a single round. This paper introduces a multi-LLM negotiation framework for sentiment analysis.
  arXiv  Detail & Related papers  (2023-11-03T12:35:29Z)
• How Can Recommender Systems Benefit from Large Language Models: A Survey [82.06729592294322]
  Large language models (LLM) have shown impressive general intelligence and human-like capabilities. We conduct a comprehensive survey on this research direction from the perspective of the whole pipeline in real-world recommender systems.
  arXiv  Detail & Related papers  (2023-06-09T11:31:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.