mlsanityData to 7 Oct 2026

A Study on Large Language Models' Limitations in Multiple-Choice Question Answering

arXiv 2401.07955 ↗First posted 15 Jan 2024cs.CL cs.AI cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

The widespread adoption of Large Language Models (LLMs) has become commonplace, particularly with the emergence of open-source models. More importantly, smaller models are well-suited for integration into consumer devices and are frequently employed either as standalone solutions or as subroutines in various AI tasks. Despite their ubiquitous use, there is no systematic analysis of their specific capabilities and limitations. In this study, we tackle one of the most widely used tasks - answering Multiple Choice Question (MCQ). We analyze 26 small open-source models and find that 65% of the models do not understand the task, only 4 models properly select an answer from the given choices, and only 5 of these models are choice order independent. These results are rather alarming given the extensive use of MCQ tests with these models. We recommend exercising caution and testing task understanding before using MCQ to evaluate LLMs in any field whatsoever.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 19 of its 55 references that are in the map. First posted on arXiv 15 Jan 2024.

Builds on

19 of 55 references.

References · 19

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  4. 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scalingcited by 1,734
  5. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 755
  6. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 618
  7. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 454
  8. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  9. 2023Orca: Progressive Learning from Complex Explanation Traces of GPT-4cited by 369
  10. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  11. 2023Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questionscited by 249
  12. 2022OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalizationcited by 235
7 more
  1. 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 199
  2. 2023Large Language Models in Law: A Surveycited by 128
  3. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 122
  4. 2023A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrologycited by 26
  5. 2023Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wordingcited by 13
  6. 2023Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracycited by 11
  7. 2022The Massively Multilingual Natural Language Understanding 2022 (MMNLU-22) Workshop and Competitioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 9; 2026: 2.

22 papers.

Sort:

By area:

  1. 2024OLMES: A Standard for Language Model Evaluationscited by 100
  2. 2024Is Temperature the Creativity Parameter of Large Language Models?cited by 92
  3. 2025Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Abovecited by 51
  4. 2024Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questionscited by 35
  5. 2025From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centeredcited by 21
  6. 2024PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbationscited by 13
  7. 2024Evaluating LLM Reasoning in the Operations Research Domain with ORQAcited by 12
  8. 2024Searching for Structure: Investigating Emergent Communication with Large Language Modelscited by 10
  9. 2025Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communicationcited by 9
  10. 2024Pragmatic Competence Evaluation of Large Language Models for the Korean Languagecited by 8
  11. 2025Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systemscited by 6
  12. 2025Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answeringcited by 4
10 more
  1. 2024Assessing Language Models' Worldview for Fiction Generationcited by 3
  2. 2024Kalahi: A handcrafted, grassroots cultural LLM evaluation suite for Filipinocited by 3
  3. 2024Exploring Language Model Generalization in Low-Resource Extractive QAcited by 2
  4. 2025La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin Americacited by 2
  5. 2026Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmarkcited by 2
  6. 2026When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraintscited by 2
  7. 2024Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Modelscited by 1
  8. 2025Evaluating the performance and fragility of large language models on the self-assessment for neurological surgeonscited by 0
  9. 2025Token Constraint Decoding Improves Robustness on Question Answering for Large Language Modelscited by 0
  10. 2025Measuring Stability Beyond Accuracy in Small Open-Source Medical Large Language Models for Pediatric Endocrinologycited by 0