GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms

• URL: http://arxiv.org/abs/2603.18469v1
• Date: Thu, 19 Mar 2026 04:04:45 GMT
• Title: GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms
• Abstract summary: We introduce a benchmark designed to evaluate how large language models balance adherence to norms against business goals.<n>We define five types of pressures: Goal Alignment, Risk Aversion, Emotional/Appeal, Social/Authoritative Influence, and Personal Incentive.<n>The benchmark comprises 1,200 scenarios across four domains: hiring, customer support, advertising and finance.
• Score: 3.6158033114580683
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce GAIN (Goal-Aligned Decision-Making under Imperfect Norms), a benchmark designed to evaluate how large language models (LLMs) balance adherence to norms against business goals. Existing benchmarks typically focus on abstract scenarios rather than real-world business applications. Furthermore, they provide limited insights into the factors influencing LLM decision-making. This restricts their ability to measure models' adaptability to complex, real-world norm-goal conflicts. In GAIN, models receive a goal, a specific situation, a norm, and additional contextual pressures. These pressures, explicitly designed to encourage potential norm deviations, are a unique feature that differentiates GAIN from other benchmarks, enabling a systematic evaluation of the factors influencing decision-making. We define five types of pressures: Goal Alignment, Risk Aversion, Emotional/Ethical Appeal, Social/Authoritative Influence, and Personal Incentive. The benchmark comprises 1,200 scenarios across four domains: hiring, customer support, advertising and finance. Our experiments show that advanced LLMs frequently mirror human decision-making patterns. However, when Personal Incentive pressure is present, they diverge significantly, showing a strong tendency to adhere to norms rather than deviate from them.

Related papers

• Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models [49.45276299939287]
  Large Language Models (LLMs) increasingly handle complex subjective tasks.<n>LLMs fluctuate unpredictably under minor wording changes.<n> resolving this duality is critical for reliable AI alignment.
  arXiv  Detail & Related papers  (2026-09-15T03:35:04Z)
• Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models [121.70781851874035]
  Large language models (LLMs) are increasingly used in decision support.<n>It is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities.<n>Here we examine this question using a controlled multi-model framework based on no-limit Texas Hold'em.
  arXiv  Detail & Related papers  (2026-07-11T10:33:39Z)
• MANTA: Multi-turn Assessment for Nonhuman Thinking & Alignment [0.1452394725421793]
  MANTA is a dynamic multi-turn evaluation framework built on the Inspect AI platform.<n>We present preliminary results from evaluations of claude-sonnet-4-20250514 and openai/gpt-4o.<n>We additionally present STYLEJUDGE, a controlled four-judge study demonstrating systematic format bias in LLM-as-judge evaluation.
  arXiv  Detail & Related papers  (2026-04-18T19:51:32Z)
• Where Norms and References Collide: Evaluating LLMs on Normative Reasoning [3.8431932182760296]
  Embodied agents, such as robots, will need to interact in situated environments where successful communication often depends on reasoning over social norms.<n>It remains unclear whether Large Language Models (LLMs) can support this kind of reasoning.<n>We introduce SNIC (Situated Norms in Context), a human-validated diagnostic testbed designed to probe how well state-of-the-art LLMs can extract and utilize normative principles relevant to NBRR.
  arXiv  Detail & Related papers  (2026-02-03T01:23:22Z)
• Stress-Testing Model Specs Reveals Character Differences among Language Models [23.505192393830807]
  Large language models (LLMs) are increasingly trained from AI constitutions and model specifications.<n>We present a systematic methodology for stress-testing model character specifications.<n>We identify numerous cases of principle contradictions and interpretive ambiguities in current model specs.
  arXiv  Detail & Related papers  (2025-10-09T02:24:37Z)
• Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It [81.50711040539566]
  Current large language model (LLM) development treats task-solving and preference alignment as separate challenges.<n>We introduce PREFDISCO, an evaluation methodology that transforms static benchmarks into interactive personalization tasks.<n>Our framework creates scenarios where identical questions require different reasoning chains depending on user context.
  arXiv  Detail & Related papers  (2025-09-30T18:55:28Z)
• User-centric Subjective Leaderboard by Customizable Reward Modeling [34.40455169451943]
  We present the first User-Centric Subjective Leaderboard (USL)<n>It provides a preference-driven, dynamic ranking of large language models (LLMs) across diverse real-world scenarios.<n>Our work is built upon a thorough investigation of real human preference data, involving more than 10K subjective queries.
  arXiv  Detail & Related papers  (2025-08-13T03:39:04Z)
• Your AI, Not Your View: The Bias of LLMs in Investment Analysis [62.388554963415906]
  In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data.<n>These conflicts are especially problematic in real-world investment services, where a model's inherent biases can misalign with institutional objectives.<n>We propose an experimental framework to investigate emergent behaviors in such conflict scenarios, offering a quantitative analysis of bias in investment analysis.
  arXiv  Detail & Related papers  (2025-07-28T16:09:38Z)
• Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models [6.9347404883379316]
  Large Language Models (LLMs) are increasingly integrated into human life and increasingly influence decision-making.<n>It's crucial to evaluate whether and to what extent they exhibit subjective preferences, opinions, and beliefs.<n>This paper presents the Preference, Opinion, and Belief survey (POBs) to assess LLMs' subjective inclinations across societal, cultural, ethical, and personal domains.
  arXiv  Detail & Related papers  (2025-05-26T07:41:21Z)
• Diverging Preferences: When do Annotators Disagree and do Models Know? [92.24651142187989]
  We develop a taxonomy of disagreement sources spanning 10 categories across four high-level classes. We find that the majority of disagreements are in opposition with standard reward modeling approaches. We develop methods for identifying diverging preferences to mitigate their influence on evaluation and training.
  arXiv  Detail & Related papers  (2024-10-18T17:32:22Z)
• When Prompting Fails to Sway: Inertia in Moral and Value Judgments of Large Language Models [4.906478894661688]
  Large Language Models (LLMs) exhibit non-deterministic behavior, and prompting has emerged as a primary method for steering their outputs toward desired directions.<n>One popular strategy involves assigning a specific "persona" to the model to induce more varied and context-sensitive responses, akin to the diversity found in human perspectives.<n>Our experiments demonstrate that LLMs maintain consistent value orientations.<n>In particular, we observe a persistent inertia in their responses, where certain moral and value dimensions, especially harm avoidance and fairness, remain distinctly skewed in one direction despite varied persona settings.
  arXiv  Detail & Related papers  (2024-08-16T23:24:10Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)

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.