← Back to all news
arXiv Computation and Language

Geometry of Confabulation and Refusal in Small Language Models

The paper introduces ConfabQA, a 784‑item benchmark designed to distinguish between confabulation and refusal in small language models when faced with unanswerable questions. Using linear probes, a sparse autoencoder, and direct optimization of intervention directions, the study maps the hidden‑state geometry on models such as Qwen3‑1.7B, Gemma 2‑2B, and Llama 3.2‑3B, showing that certain hidden‑state directions can flip confabulations into refusals. The work also demonstrates that the refusal signal is model‑dependent and that the hidden state’s contribution can be quantified beyond prompt features.

Related stories

arXiv Machine Learning
Sep 17

No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback

The study examines how two small instruction‑tuned language models, Qwen2.5‑1.5B and Llama‑3.2‑1B, respond to user pushback on TriviaQA. When initially correct, the models flip to a wrong answer in about 42–43% of cases, with the effectiveness of different pushback styles varying by model. Attempts to decode capitulation from the pre‑response residual stream fail under a rigorous validation protocol, revealing overfitting and a measurement hazard that underestimates capitulation by 18–24 percentage points.

By Saad Aamir, Muhammad Awais Bin Adil
llms
More like this →
arXiv AI
Sep 17

Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition

Linear probes can decode safety‑relevant concepts such as truthfulness from language‑model activations, but probe accuracy may reflect only decodability, not causal influence on model behavior. The authors show that probe weight geometry alone cannot identify the features the model actually uses, because geometrically aligned features need not be causally relevant. They introduce a sparse‑autoencoder (SAE) decomposition that ranks features by probe alignment and gradient sensitivity, and demonstrate that ablating shared, probe‑only, and random feature sets reveals a sharp dissociation: shared features drive model output changes far more than probe‑only or random features, confirming that causal relevance requires intervention beyond weight geometry.

By Devesh Tiwari, Camille Davis, Shivank Sinha, Talia Weaver, Aditya Shah, Maheep Chaudhary
benchmarkssafety
More like this →
arXiv AI
Sep 7

When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models

A 0.6B language model consistently answers YES to 1,200 logical tests, yet its behavior shows no discrimination. Linear probes reveal the correct verdict with high AUC (0.96) and transfer to unseen structures, but a single scalar readout fails due to a saturated decision threshold offset by +4.6 σ. Adjusting this threshold restores behavior accuracy from 50 % to 81 % and improves higher‑scale models, demonstrating that miscalibrated readouts, not hidden knowledge loss, drive performance gaps.

By Gnaneswar Villuri, Hashmath Shaik, Alex Doboli
llms
More like this →
arXiv AI
Sep 4

It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories

The paper investigates whether large language models’ reasoning traces truly contain early, informative signals or merely reflect budget and difficulty confounds. Using a restart‑controlled truncation probe, the authors compare continuation success rates against from‑scratch restart curves across 178 problem‑model pairs, finding that only one case shows prefix‑limited success and that continuing a model’s own prefix generally outperforms restarting. A difficulty‑controlled test and two generation‑free analyses reveal that early internal signals do not carry outcome information beyond a problem‑difficulty baseline, underscoring the need for proper counterfactual controls.

By Yigit Utku Bulut
llms
More like this →