Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options

• URL: http://arxiv.org/abs/2409.00113v3
• Date: Mon, 02 Jun 2025 09:08:56 GMT
• Title: Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options
• Authors: Gracjan Góral, Emilia Wiśnios, Piotr Sankowski, Paweł Budzianowski,
• Abstract summary: This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning.<n>We show that post-training aligned models often default to selecting invalid options, while base models exhibit improved refusal capabilities that scale with model size.<n>We additionally conduct a parallel human study showing similar instruction-following biases, with implications for how these biases may propagate through human feedback datasets used in alignment.
• Score: 2.1184929769291294
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across arithmetic, domain-specific knowledge, and high-stakes medical decision tasks, we demonstrate that post-training aligned models often default to selecting invalid options, while base models exhibit improved refusal capabilities that scale with model size. Our analysis reveals that alignment techniques, though intended to enhance helpfulness, can inadvertently impair models' reflective judgment--the ability to override default behaviors when faced with invalid options. We additionally conduct a parallel human study showing similar instruction-following biases, with implications for how these biases may propagate through human feedback datasets used in alignment. We provide extensive ablation studies examining the impact of model size, training techniques, and prompt engineering. Our findings highlight fundamental tensions between alignment optimization and preservation of critical reasoning capabilities, with important implications for developing more robust AI systems for real-world deployment.

Related papers

• Pre-Trained AI Model Assisted Online Decision-Making under Missing Covariates: A Theoretical Perspective [12.160708336715489]
  "Model elasticity" provides a unified way to characterize the regret incurred due to model imputation.<n>We show that under the missing at random (MAR) setting, it is possible to sequentially calibrate the pre-trained model.<n>Our analysis highlights the practical value of having an accurate pre-trained model in sequential decision-making tasks.
  arXiv  Detail & Related papers  (2025-07-10T15:33:27Z)
• Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration [15.711365331854614]
  We introduce Dynamic Adaptation of Reasoning Trajectories (DART), a novel data adaptation framework.<n>Instead of uniformly imitating expert steps, DART employs a selective imitation strategy guided by step-wise adaptability estimation.<n>We validate DART across multiple reasoning benchmarks and model scales, demonstrating that it significantly improves generalization and data efficiency.
  arXiv  Detail & Related papers  (2025-05-27T04:08:11Z)
• Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning [4.902161835372679]
  We propose a novel framework for uncertainty-aware policy optimization with model-based exploratory planning.<n>In the policy optimization phase, we leverage an uncertainty-driven exploratory policy to actively collect diverse training samples.<n>Our approach offers flexibility and applicability to tasks with varying state/action spaces and reward structures.
  arXiv  Detail & Related papers  (2025-03-26T01:07:35Z)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• 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)
• Subtle Errors Matter: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE) RISE injects predefined subtle errors into partial tokens of correct solutions to construct hard pairs for error mitigation. Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• On the Modeling Capabilities of Large Language Models for Sequential Decision Making [52.128546842746246]
  Large pretrained models are showing increasingly better performance in reasoning and planning tasks. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly. In environments with unfamiliar dynamics, we explore how fine-tuning LLMs with synthetic data can significantly improve their reward modeling capabilities.
  arXiv  Detail & Related papers  (2024-10-08T03:12:57Z)
• Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization [64.34767799614328]
  Current self-rewarding approaches rely heavily on the discriminator's judgment capabilities. We propose a novel, only-prompting self-rewarding online algorithm that generates preference datasets without relying on judgment capabilities.
  arXiv  Detail & Related papers  (2024-09-26T04:41:08Z)
• Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models [36.119299938503936]
  Large vision-language models (LVLMs) have shown promising performance on a variety of vision-language tasks. They remain susceptible to hallucinations, generating outputs misaligned with visual content or instructions. We propose reflective instruction tuning, which integrates rationale learning into visual instruction tuning.
  arXiv  Detail & Related papers  (2024-07-16T06:32:45Z)
• Learning to Correct for QA Reasoning with Black-box LLMs [37.13135300208977]
  We propose CoBB (Correct for improving QA reasoning of Black-Box LLMs) as an open challenge in machine learning. It uses a trained adaptation model to perform a seq2seq mapping from the often-imperfect reasonings of the original black-box LLM to the correct or improved reasonings. Our experimental results demonstrate that CoBB significantly improves reasoning accuracy across various QA benchmarks.
  arXiv  Detail & Related papers  (2024-06-26T18:57:32Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Balancing Rigor and Utility: Mitigating Cognitive Biases in Large Language Models for Multiple-Choice Questions [0.46873264197900916]
  We show that certain cognitive biases can enhance decision-making efficiency through rational deviations and shortcuts.<n>By introducing moderation and an abstention option, we reduce error rates, improve decision accuracy, and optimize decision rates.<n>This approach offers a novel way to leverage cognitive biases to improve the practical utility of large language models.
  arXiv  Detail & Related papers  (2024-06-16T16:25:22Z)
• LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models [69.68379406317682]
  We introduce a listener-aware finetuning method (LACIE) to calibrate implicit and explicit confidence markers. We show that LACIE models the listener, considering not only whether an answer is right, but whether it will be accepted by a listener. We find that training with LACIE results in 47% fewer incorrect answers being accepted while maintaining the same level of acceptance for correct answers.
  arXiv  Detail & Related papers  (2024-05-31T17:16:38Z)
• Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
  Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.<n>However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
  arXiv  Detail & Related papers  (2024-03-01T09:01:53Z)
• Dissecting Human and LLM Preferences [80.55271307662365]
  We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. We show that preference-based evaluation can be intentionally manipulated.
  arXiv  Detail & Related papers  (2024-02-17T14:34:31Z)
• End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty [55.04219793298687]
  The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives. It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
  arXiv  Detail & Related papers  (2024-02-12T16:33:35Z)
• Predict-Then-Optimize by Proxy: Learning Joint Models of Prediction and Optimization [59.386153202037086]
  Predict-Then- framework uses machine learning models to predict unknown parameters of an optimization problem from features before solving. This approach can be inefficient and requires handcrafted, problem-specific rules for backpropagation through the optimization step. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by predictive models.
  arXiv  Detail & Related papers  (2023-11-22T01:32:06Z)
• HANS, are you clever? Clever Hans Effect Analysis of Neural Systems [1.6267479602370545]
  Large Language Models (It-LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, letting humans guide and comprehend day-to-day social interactions effectively. Several multiple-choice questions (MCQ) benchmarks have been proposed to construct solid assessments of the models' abilities. However, earlier works are demonstrating the presence of inherent "order bias" in It-LLMs, posing challenges to the appropriate evaluation.
  arXiv  Detail & Related papers  (2023-09-21T20:52:18Z)
• Making Large Language Models Better Reasoners with Alignment [57.82176656663245]
  Reasoning is a cognitive process of using evidence to reach a sound conclusion. Recent studies reveal that fine-tuning LLMs on data with the chain of thought (COT) reasoning process can significantly enhance their reasoning capabilities. We introduce an textitAlignment Fine-Tuning (AFT) paradigm, which involves three steps.
  arXiv  Detail & Related papers  (2023-09-05T11:32:48Z)
• Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning [52.74071439183113]
  We study the predict-then-optimize framework in the context of sequential decision problems (formulated as MDPs) solved via reinforcement learning. Two significant computational challenges arise in applying decision-focused learning to MDPs.
  arXiv  Detail & Related papers  (2021-06-06T23:53:31Z)

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.