# No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes

arXiv: https://arxiv.org/abs/2509.10625 · HTML: https://mlsanity.com/paper/2509.10625/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Probing deception, bias and beliefs, one of 13 directions in Mechanistic interpretability.
- Builds on 36 of its 48 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Placed in

- Mechanistic interpretability / [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/)

## Builds on (most cited first, 30 of 36)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users](https://mlsanity.com/paper/2007.06823/) (2020)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [Large Language Models Must Be Taught to Know What They Don't Know](https://mlsanity.com/paper/2406.08391/) (2024)
- [LLM Internal States Reveal Hallucination Risk Faced With a Query](https://mlsanity.com/paper/2407.03282/) (2024)
- [Truth is Universal: Robust Detection of Lies in LLMs](https://mlsanity.com/paper/2407.12831/) (2024)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [On Early Detection of Hallucinations in Factual Question Answering](https://mlsanity.com/paper/2312.14183/) (2023)
- [The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models](https://mlsanity.com/paper/2310.11877/) (2023)
- [Estimating Knowledge in Large Language Models Without Generating a Single Token](https://mlsanity.com/paper/2406.12673/) (2024)
- [Finetuning Language Models to Emit Linguistic Expressions of Uncertainty](https://mlsanity.com/paper/2409.12180/) (2024)
- [100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances](https://mlsanity.com/paper/2409.03563/) (2024)
- [Benchmarking Deception Probes via Black-to-White Performance Boosts](https://mlsanity.com/paper/2507.12691/) (2025)

## Built on by (most cited first, 30 of 38)

- [LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations](https://mlsanity.com/paper/2602.09924/) (2026)
- [Do Large Language Models Know What They Are Capable Of?](https://mlsanity.com/paper/2512.24661/) (2025)
- [Teaching Language Models to Faithfully Express their Uncertainty](https://mlsanity.com/paper/2510.12587/) (2025)
- [On Calibration of Large Language Models: From Response To Capability](https://mlsanity.com/paper/2602.13540/) (2026)
- [Temporal Predictors of Outcome in Reasoning Language Models](https://mlsanity.com/paper/2511.14773/) (2025)
- [Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing](https://mlsanity.com/paper/2603.17199/) (2026)
- [Early Stopping for Large Reasoning Models via Confidence Dynamics](https://mlsanity.com/paper/2604.04930/) (2026)
- [Gradient-Stable Attention Heads Signal LLM Correctness](https://mlsanity.com/paper/2602.13699/) (2026)
- [LLM Router: Rethinking Routing with Prefill Activations](https://mlsanity.com/paper/2603.20895/) (2026)
- [Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States](https://mlsanity.com/paper/2605.07579/) (2026)
- [Two Axes of LLM Abstention: Answer Correctness and Question Answerability](https://mlsanity.com/paper/2607.08456/) (2026)
- [Sparse Reward Subsystem in Large Language Models](https://mlsanity.com/paper/2602.00986/) (2026)
- [When Role-playing, Do Models Believe What They Say?](https://mlsanity.com/paper/2606.11502/) (2026)
- [Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation](https://mlsanity.com/paper/2603.05881/) (2026)
- [Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness](https://mlsanity.com/paper/2604.12373/) (2026)
- [Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier](https://mlsanity.com/paper/2606.18284/) (2026)
- [Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering](https://mlsanity.com/paper/2602.06022/) (2026)
- [Testing the Limits of Truth Directions in LLMs](https://mlsanity.com/paper/2604.03754/) (2026)
- [LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models](https://mlsanity.com/paper/2607.28077/) (2026)
- [The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations](https://mlsanity.com/paper/2605.09195/) (2026)
- [Capability Self-Assessment in Large Language Models](https://mlsanity.com/paper/2606.00251/) (2026)
- [Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs](https://mlsanity.com/paper/2606.27378/) (2026)
- [Latent Programming Horizons in Coding Agents](https://mlsanity.com/paper/2607.05188/) (2026)
- [Future Confidence Distillation in Large Language Models](https://mlsanity.com/paper/2607.07626/) (2026)
- [Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale](https://mlsanity.com/paper/2607.07670/) (2026)
- [On the Robustness of LLMs' Internal Representation of Code Correctness](https://mlsanity.com/paper/2608.08266/) (2026)
- [It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories](https://mlsanity.com/paper/2609.03436/) (2026)
- [Dynamic LLM Routers are Often Misguided](https://mlsanity.com/paper/2610.02762/) (2026)
- [Reasoning as State Transition: A Representational Analysis of Reasoning Evolution in Large Language Models](https://mlsanity.com/paper/2602.00770/) (2026)
- [Large Language Models Can Take False First Steps at Inference-time Planning](https://mlsanity.com/paper/2602.02991/) (2026)

## Abstract (arXiv)

Do large language models (LLMs) anticipate when they will answer correctly? To study this, we extract activations after a question is read but before any tokens are generated, and train linear probes to predict whether the model's forthcoming answer will be correct. Across three open-source model families ranging from 7 to 70 billion parameters, projections on this "in-advance correctness direction" trained on generic trivia questions predict success in distribution and on diverse out-of-distribution knowledge datasets, indicating a deeper signal than dataset-specific spurious features, and outperforming black-box baselines and verbalised predicted confidence. Predictive power saturates in intermediate layers and, notably, generalisation falters on questions requiring mathematical reasoning. Moreover, for models responding "I don't know", doing so strongly correlates with the probe score, indicating that the same direction also captures confidence. By complementing previous results on truthfulness and other behaviours obtained with probes and sparse auto-encoders, our work contributes essential findings to elucidate LLM internals.