# CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models

arXiv: https://arxiv.org/abs/2112.11941 · HTML: https://mlsanity.com/paper/2112.11941/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 72 references that are in the map.
- First posted on arXiv 22 Dec 2021.

## Builds on (most cited first, 30 of 35)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation](https://mlsanity.com/paper/2107.02137/) (2021)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text](https://mlsanity.com/paper/1908.06177/) (2019)
- [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://mlsanity.com/paper/2011.02593/) (2020)
- [UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark](https://mlsanity.com/paper/2103.13009/) (2021)
- [Evaluating Commonsense in Pre-trained Language Models](https://mlsanity.com/paper/1911.11931/) (2019)
- [Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision](https://mlsanity.com/paper/2004.09034/) (2020)
- [Shaking the foundations: delusions in sequence models for interaction and control](https://mlsanity.com/paper/2110.10819/) (2021)
- [WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge](https://mlsanity.com/paper/2005.05763/) (2020)
- [COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences](https://mlsanity.com/paper/2106.00969/) (2021)

## Built on by (most cited first, 30 of 34)

- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning](https://mlsanity.com/paper/2402.06954/) (2024)
- [Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey](https://mlsanity.com/paper/2404.01869/) (2024)
- [Integrating Large Language Model for Improved Causal Discovery](https://mlsanity.com/paper/2306.16902/) (2023)
- [EmbedLLM: Learning Compact Representations of Large Language Models](https://mlsanity.com/paper/2410.02223/) (2024)
- [Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.00836/) (2023)
- [CRAB: Assessing the Strength of Causal Relationships Between Real-world Events](https://mlsanity.com/paper/2311.04284/) (2023)
- [Counterfactual reasoning: Testing language models' understanding of hypothetical scenarios](https://mlsanity.com/paper/2305.16572/) (2023)
- [Causality for Large Language Models](https://mlsanity.com/paper/2410.15319/) (2024)
- [CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation](https://mlsanity.com/paper/2210.04873/) (2022)
- [ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding](https://mlsanity.com/paper/2408.11363/) (2024)
- [On Robustness and Reliability of Benchmark-Based Evaluation of LLMs](https://mlsanity.com/paper/2509.04013/) (2025)
- [Causal Structure Learning Supervised by Large Language Model](https://mlsanity.com/paper/2311.11689/) (2023)
- [From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities](https://mlsanity.com/paper/2401.15071/) (2024)
- [Causal Evaluation of Language Models](https://mlsanity.com/paper/2405.00622/) (2024)
- [A Critical Review of Causal Reasoning Benchmarks for Large Language Models](https://mlsanity.com/paper/2407.08029/) (2024)
- [Counterfactual Token Generation in Large Language Models](https://mlsanity.com/paper/2409.17027/) (2024)
- [Reasoning Elicitation in Language Models via Counterfactual Feedback](https://mlsanity.com/paper/2410.03767/) (2024)
- [Failure Modes of LLMs for Causal Reasoning on Narratives](https://mlsanity.com/paper/2410.23884/) (2024)
- [Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges](https://mlsanity.com/paper/2309.12426/) (2023)
- [Learning to Plan with Natural Language](https://mlsanity.com/paper/2304.10464/) (2023)
- [RNR: Teaching Large Language Models to Follow Roles and Rules](https://mlsanity.com/paper/2409.13733/) (2024)
- [CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency](https://mlsanity.com/paper/2508.16100/) (2025)
- [On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study](https://mlsanity.com/paper/2505.11839/) (2025)
- [DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models](https://mlsanity.com/paper/2509.09097/) (2025)
- [Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them](https://mlsanity.com/paper/2503.16401/) (2025)
- [CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs](https://mlsanity.com/paper/2602.08939/) (2026)
- [ACCORD: Closing the Commonsense Measurability Gap](https://mlsanity.com/paper/2406.02804/) (2024)

## Abstract (arXiv)

We introduce the CRASS (counterfactual reasoning assessment) data set and benchmark utilizing questionized counterfactual conditionals as a novel and powerful tool to evaluate large language models. We present the data set design and benchmark that supports scoring against a crowd-validated human baseline. We test six state-of-the-art models against our benchmark. Our results show that it poses a valid challenge for these models and opens up considerable room for their improvement.