SteerForce at SemEval-2026 Task 11: Reducing Content Effects Using Layered Activation Steering
Year: 2026
Type: conference-paper
Abstract: Large language models exhibit content effects, where surface plausibility interferes with formal logical reasoning.In SemEval-2026 Task 11, this appears as a performance gap between plausibility-aligned and plausibility-conflicting syllogisms, reflecting directional content bias.We address this issue using inference-time activation steering, modeling bias as a geometric deviation between plausibility-driven and validity-driven representations.We introduce a layered steering framework that combines Activation Transport (ACT) with input-adaptive contrastive steering (K-CAST), applied to layers identified through sensitivity analysis.This architecture-aware strategy enables targeted interventions without retraining.On BERT, sequential multi-layer steering improves validity accuracy from 77.1% to 82.3% while reducing bias by 75%.In contrast, for the decoder-only Qwen2.5-1.5B-Instruct, a single mid-to-late layer intervention reduces bias from 0.26 to 0.04 with modest accuracy gains, whereas multi-layer steering offers no additional benefit.These results reveal a fundamental architectural distinction: encoder-based models benefit from distributed low-intensity corrections, while decoder-only instructiontuned models concentrate reasoning signals within a narrow late-layer band.Our findings demonstrate that effective bias mitigation requires architecture-aware activation steering.
Institution: Goethe University Frankfurt
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166845085