weak-supervision

Tag

Cards List
#weak-supervision

Fault of Our Stars: Behavioral Drivers of Rating-Sentiment Incongruence

arXiv cs.CL · yesterday Cached

This paper investigates the behavioral drivers of incongruence between star ratings and textual sentiment in Sri Lankan tourism reviews, finding that 18.6% of reviews show mismatch with six directional patterns, and identifying venue type, reviewer expertise, and temporal factors as contributors.

0 favorites 0 likes
#weak-supervision

From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

arXiv cs.AI · 2026-06-02 Cached

This paper introduces Preference Delta Aggregation (PDA) and Geometric Alignment Merging (GAM) to aggregate multiple 'weak' preference signals from weaker model pairs via LoRA merging, improving strong LLMs on knowledge reasoning and agentic search tasks by over 6% on average.

0 favorites 0 likes
#weak-supervision

Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation

arXiv cs.LG · 2026-05-13 Cached

This paper introduces LogMILP, a weakly-supervised framework for log instance anomaly localization that uses prototype-guided structural modeling and counterfactual perturbation consistency regularization to improve detection and interpretability with only bag-level labels.

0 favorites 0 likes
#weak-supervision

Weakly Supervised Concept Learning for Object-centric Visual Reasoning

arXiv cs.LG · 2026-05-12 Cached

This paper introduces a two-stage neuro-symbolic framework that uses weak supervision (as little as 1% labels) with a slot-based VAE to learn interpretable symbols for object-centric visual reasoning, outperforming foundation models in domain generalization.

0 favorites 0 likes
#weak-supervision

When Can LLMs Learn to Reason with Weak Supervision?

Hugging Face Daily Papers · 2026-04-20 Cached

This paper systematically studies when LLMs can generalize in reasoning tasks under weak supervision (scarce data, noisy rewards, self-supervised proxy rewards), finding that reward saturation dynamics and reasoning faithfulness are key predictors, and that SFT on explicit reasoning traces is necessary for successful generalization under weak supervision.

0 favorites 0 likes
#weak-supervision

Weak-to-strong generalization

OpenAI Blog · 2023-12-14 Cached

OpenAI's Superalignment team introduces weak-to-strong generalization, a new research direction for empirically aligning superhuman AI models by addressing the fundamental challenge of how weak human supervisors can reliably control and steer AI systems vastly smarter than themselves.

0 favorites 0 likes
#weak-supervision

Vokenization: Multimodel Learning for Vision and Language

ML at Berkeley · 2021-04-16 Cached

The article explains 'Vokenization,' a multimodal learning technique that bridges computer vision and natural language processing by using weak supervision to link visual data with language tokens. It contrasts this approach with text-only models like GPT-3 and BERT, highlighting how visual grounding can improve language understanding.

0 favorites 0 likes
← Back to home

Submit Feedback