# WorldSense: A Synthetic Benchmark for Grounded Reasoning in Large Language Models

arXiv: https://arxiv.org/abs/2311.15930 · HTML: https://mlsanity.com/paper/2311.15930/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 27 Nov 2023.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks](https://mlsanity.com/paper/1502.05698/) (2015)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models](https://mlsanity.com/paper/2210.12023/) (2022)
- [GPT4GEO: How a Language Model Sees the World's Geography](https://mlsanity.com/paper/2306.00020/) (2023)
- [Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning](https://mlsanity.com/paper/2310.13486/) (2023)
- [Unbiased Math Word Problems Benchmark for Mitigating Solving Bias](https://mlsanity.com/paper/2205.08108/) (2022)

## Built on by (most cited first, 20 of 20)

- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions](https://mlsanity.com/paper/2506.09038/) (2025)
- [STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?](https://mlsanity.com/paper/2503.23765/) (2025)
- [OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM](https://mlsanity.com/paper/2510.15870/) (2025)
- [IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments](https://mlsanity.com/paper/2506.09849/) (2025)
- [Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?](https://mlsanity.com/paper/2411.03923/) (2024)
- [Agentic Abstention: Do Agents Know When to Stop Instead of Act?](https://mlsanity.com/paper/2606.28733/) (2026)
- [What makes a good metric? Evaluating automatic metrics for text-to-image consistency](https://mlsanity.com/paper/2412.13989/) (2024)
- [Over-Searching in Search-Augmented Large Language Models](https://mlsanity.com/paper/2601.05503/) (2026)
- [TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions](https://mlsanity.com/paper/2602.08711/) (2026)
- [RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models](https://mlsanity.com/paper/2510.10390/) (2025)
- [SimLM: Can Language Models Infer Parameters of Physical Systems?](https://mlsanity.com/paper/2312.14215/) (2023)
- [From Neurons to Neutrons: A Case Study in Interpretability](https://mlsanity.com/paper/2405.17425/) (2024)
- [Agentic Tool Use in Large Language Models](https://mlsanity.com/paper/2604.00835/) (2026)
- [Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty](https://mlsanity.com/paper/2604.17293/) (2026)
- [HopRefusalBench: Diagnosing Refusal Failures in Search-Augmented Agents for Multi-Hop Reasoning](https://mlsanity.com/paper/2608.01358/) (2026)
- [Enhancing LLM Metacognition via Cognitive Pairwise Training](https://mlsanity.com/paper/2606.00869/) (2026)
- [MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models](https://mlsanity.com/paper/2607.09029/) (2026)
- [Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models](https://mlsanity.com/paper/2609.03422/) (2026)
- [Trajectory Soup: Pushing the Compute-Scaling Frontier of LLM Mid-training via Diverse Trajectories](https://mlsanity.com/paper/2609.37169/) (2026)

## Abstract (arXiv)

We propose WorldSense, a benchmark designed to assess the extent to which LLMs are consistently able to sustain tacit world models, by testing how they draw simple inferences from descriptions of simple arrangements of entities. Worldsense is a synthetic benchmark with three problem types, each with their own trivial control, which explicitly avoids bias by decorrelating the abstract structure of problems from the vocabulary and expressions, and by decorrelating all problem subparts with the correct response. We run our benchmark on three state-of-the-art chat-LLMs (GPT3.5, GPT4 and Llama2-chat) and show that these models make errors even with as few as three objects. Furthermore, they have quite heavy response biases, preferring certain responses irrespective of the question. Errors persist even with chain-of-thought prompting and in-context learning. Lastly, we show that while finetuning on similar problems does result in substantial improvements -- within- and out-of-distribution -- the finetuned models do not generalise beyond a constraint problem space.