controlled-generation

Tag

Cards List
#controlled-generation

COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation

arXiv cs.CL · 2026-07-10 Cached

This paper presents COBART, a method that fine-tunes BART with prefix control tokens to generate ad headlines with controllable length and optimized click-through rate (CTR), achieving a 25.82% improvement in ROUGE-L and 5.82% in estimated CTR over previous baselines.

0 favorites 0 likes
#controlled-generation

On the Limits of Steering Vectors for Preference-Aligned Generation

arXiv cs.CL · 2026-07-03 Cached

This paper systematically studies the limitations of steering vectors for controlled text generation, finding that their effectiveness varies across traits, degrades on task transfer, and suffers from composition tradeoffs.

0 favorites 0 likes
#controlled-generation

Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models

arXiv cs.AI · 2026-06-15 Cached

This paper investigates how fine-tuning vision-language models to produce dense coordinate lists creates a controllable interference surface, finding that duplicate pressure can be removed without sacrificing localization accuracy.

0 favorites 0 likes
#controlled-generation

Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models

arXiv cs.CL · 2026-06-01 Cached

This paper proposes a neuron-level intervention method to identify gender-specific neurons in language models (feminine, masculine, gender-neutral) and steer sentence generation toward a target gender form while preserving meaning, with experiments showing precise control and bias mitigation.

0 favorites 0 likes
#controlled-generation

Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards

arXiv cs.AI · 2026-05-22 Cached

The paper identifies off-manifold drift in guided flow models under compositional rewards and proposes Conflict-Aware Additive Guidance (CAR), a lightweight method that dynamically resolves gradient conflicts to improve generation fidelity without retraining.

0 favorites 0 likes
#controlled-generation

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models

arXiv cs.LG · 2026-05-13 Cached

This paper introduces a novel adaptive scheduler for steering discrete diffusion language models using sparse autoencoders, demonstrating that targeting interventions based on when specific attributes commit improves control quality and strength over uniform methods.

0 favorites 0 likes
← Back to home

Submit Feedback