# Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express

arXiv: https://arxiv.org/abs/2605.25891 · HTML: https://mlsanity.com/paper/2605.25891/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 16 of 16)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [CausaLM: Causal Model Explanation Through Counterfactual Language Models](https://mlsanity.com/paper/2005.13407/) (2020)
- [Do Androids Know They're Only Dreaming of Electric Sheep?](https://mlsanity.com/paper/2312.17249/) (2023)
- [Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?](https://mlsanity.com/paper/2506.21215/) (2025)
- [Interpretability without actionability: mechanistic methods cannot correct language model errors despite near-perfect internal representations](https://mlsanity.com/paper/2603.18353/) (2026)

## Built on by (most cited first, 1 of 1)

- [Decodable In-Context State and Model Output Across Training](https://mlsanity.com/paper/2609.31401/) (2026)

## Abstract (arXiv)

We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed linear probe recovers the evidence-supported answer from the model's hidden state (accuracy approximately 0.97), while the spoken Yes/No reverts to the commonsense one (accuracy approximately 0.5). We call this approximately +0.5 gap Causal Tongue-Tie: a wrong Yes/No decomposes into two separable failure modes: no internal signal versus a signal the verbal interface cannot say. The implication cuts both ways for output-only causal benchmarks: a benchmark "correct" need not mean the model has understood, and a benchmark "wrong" need not mean it cannot. Sweeping claims about whether LLMs can do causal reasoning, drawn from a single accuracy number, deserve a second look.