cs.CLNov 11, 2026

Differential Backpack Language Models: Sense Inhibition via Signed Contextualization Weights

Authors: Konstantinos Skianis, Giannis Nikolentzos, Polykarpos Meladianos, Michalis Vazirgiannis

Organizations: University of Ioannina · University of Peloponnese · MBZUAI · École Polytechnique & MBZUAI

Abstract

Backpack language models predict with a strictly linear combination of non-contextual per-word sense vectors, weighted by non-negative contextualization scores. We show that non-negativity conflates two properties: the linear readout, which carries the interpretability, and the conic combination, which merely restricts it. We relax the latter by computing the sense weights with differential attention, a difference of two softmax maps with a learned per-sense gain, so context can actively inhibit a sense; we call the result a differential Backpack. At equal parameters on WikiText-103 this cuts the Backpack's perplexity gap to a Transformer by 31%, improves over the softmax Backpack at every sense count, persists with a shrinking margin up to 350M parameters on OpenWebText, and is localized at the sense layer by ablations and controls. The learned inhibition is directly interpretable (a financial context drives the river sense of bank to -0.50), and the preserved per-sense attribution predicts counterfactual removals exactly. We tested a number of combination rules, showing the linear interface is nearly free. Making the readout nonlinear gains only 0.43 perplexity points while invalidating two thirds of the decomposition. The differential Backpack's senses are also better representations, improving zero-shot sentence similarity by up to 33%.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Oct 19, 2026

DeltaTrace: Efficient Signed Attribution for Reasoning Language Models

We study how words in the context support or oppose a language model's response and present DeltaTrace, a novel attribution framework that explains the effect of input tokens on a fixed model response. DeltaTrace measures how the response's log-probability changes when the context tokens being explained are masked. To distribute this difference among source tokens, it constructs operator-specific local rules for finite changes and composes them backward through the computational graph using effective secant slopes. Each token is assigned a signed attribution as the inner product of its embedding displacement and the corresponding backward-propagated slope. Local conservation makes these contributions sum to the measured score difference and preserves their meaning when aggregated over sentences or passages. DeltaTrace supports both attention and linear-attention models, with auxiliary memory growing linearly with sequence length at fixed model dimensions and chunk size. On the evaluated attention model, DeltaTrace achieves the lowest deletion-faithfulness scores (RISE and MAS) on most retrieval and reasoning tasks and the highest needle-in-a-haystack Recall, exceeding FlashTrace by 5.67-24.33 percentage points. On the evaluated hybrid attention and linear-attention model, DeltaTrace lowers RISE on 9 tasks and MAS on 12 relative to FlashTrace.
Apr 14, 2026

Better and Worse with Scale: How Contextual Entrainment Diverges with Model Size

Larger language models become simultaneously better and worse at handling contextual information -- better at ignoring false claims, worse at ignoring irrelevant tokens. We formalize this apparent paradox through the first scaling laws for contextual entrainment, the tendency of models to favor tokens that appeared in context regardless of relevance. Analyzing the Cerebras-GPT (111M-13B) and Pythia (410M-12B) model families, we find entrainment follows predictable power-law scaling, but with opposite trends depending on context type: semantic contexts show decreasing entrainment with scale, while non-semantic contexts show increasing entrainment. Concretely, the largest models are four times more resistant to counterfactual misinformation than the smallest, yet simultaneously twice as prone to copying arbitrary tokens. These diverging trends, which replicate across model families, suggest that semantic filtering and mechanical copying are functionally distinct behaviors that scale in opposition -- scaling alone does not resolve context sensitivity, it reshapes it.
Nov 5, 2026

The Intrusion Pathway: How Non-Evidential Context Degrades Language Model Performance

Language models lose accuracy when a prompt contains non-evidential context: irrelevant statements from unrelated domains, or random off-distribution tokens, with no competing answer and no semantic overlap with the query. Such noise pervades retrieval-augmented, tool-using, and long-context deployments, yet the failure has lacked a mechanistic account. We trace the corruption to the Intrusion Pathway, which starts with MLPs enriching both query-subject and irrelevant-token representations, parroting heads carry prefix-token content to the prediction position, and relational readers largely avoid unrelated sources. Nevertheless, preserved subject enrichment and selective reading do not prevent intrusion in the broader computation. We then localize part of this interference to a sparse set of attention heads, which we call intrusion heads. Their prefix-derived writes promote distractor-related content, while their reduced support for the correct answer arises primarily from weaker non-prefix contributions rather than direct suppression by the prefix. The same heads transfer across tasks and distractor types and are largely weight-disjoint from the heads that integrate relevant contextual evidence, enabling a class-conditional intervention. Replacing the corrupted last-token residual with its clean counterpart, an oracle probe that requires a matched clean forward pass, recovers 97.6% on average of the distractor-induced drop across four downstream tasks. A deployable mask level knockout of about ten heads, roughly 1% of the model's attention heads, recovers 57% at bounded cost to helpful context.