robustness

Tag

Cards List
#robustness

MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion

arXiv cs.LG ↗ · 2026-05-18 Cached

MuteBench is a benchmark for evaluating multimodal fusion models under modality missing and within-modality missing conditions across clinical datasets. It provides insights into architecture robustness and suggests that diffusion-based imputation can help.

0 favorites 0 likes
#robustness

Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law

arXiv cs.AI ↗ · 2026-05-18 Cached

This paper empirically studies LLMs' legal reasoning in tax law, showing that data contamination inflates performance and that neuro-symbolic hybrid systems offer more reliable and robust generalization than monolithic LLMs.

0 favorites 0 likes
#robustness

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

Hugging Face Daily Papers ↗ · 2026-05-18 Cached

This paper introduces an Information Bottleneck Adapter (IB-Adapter) for Vision-Language-Action (VLA) models to improve robustness against unseen visual disturbances without requiring extra data, achieving up to 30% improvement with minimal parameter overhead.

0 favorites 0 likes
#robustness

Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods

arXiv cs.LG ↗ · 2026-05-15 Cached

This paper investigates the resilience of AI-generated text detection methods (fine-tuned RoBERTa, Binoculars, text feature analysis, and ensembles) against paraphrasing attacks, finding that Binoculars-inclusive ensembles are most effective but also most vulnerable to attacks, highlighting a dichotomy between performance and resilience.

0 favorites 0 likes
#robustness

Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement

arXiv cs.AI ↗ · 2026-05-15 Cached

This paper proposes a novel transformer verification approach that uses ReLU to represent precise but non-linear bounds for dot products, enabling precise and efficient verification. The method outperforms state-of-the-art baselines on sentiment analysis models.

0 favorites 0 likes
#robustness

When Evidence Conflicts: Uncertainty and Order Effects in Retrieval-Augmented Biomedical Question Answering

arXiv cs.CL ↗ · 2026-05-15 Cached

This paper evaluates six open-weight LLMs on biomedical QA under conflicting evidence conditions, revealing accuracy drops and prediction flips, and proposes a conflict-aware abstention score that improves selective accuracy.

0 favorites 0 likes
#robustness

Enhanced and Efficient Reasoning in Large Learning Models

arXiv cs.AI ↗ · 2026-05-15 Cached

This paper proposes a method for improving reasoning in large language models by recoding data to explicitly represent relationships, enabling efficient principled reasoning with polynomial-time learnability for relational rules, which addresses hallucinations and supports sound reasoning across multiple calls.

0 favorites 0 likes
#robustness

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models

Hugging Face Daily Papers ↗ · 2026-05-15 Cached

SAE-FT introduces a novel fine-tuning method for CLIP models that uses sparse autoencoder constraints to regularize visual representations, improving robustness against distribution shifts while maintaining performance and enabling interpretability.

0 favorites 0 likes
#robustness

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning

arXiv cs.LG ↗ · 2026-05-14 Cached

This paper shows that mixing post-training data into pretraining (early exposure) improves how robustly a model retains capabilities after subsequent fine-tuning, challenging the notion that immediate post-training performance predicts retention. Controlled experiments on 135M and 1B models demonstrate that early exposure consistently improves the trade-off between upstream retention and downstream performance.

0 favorites 0 likes
#robustness

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity

arXiv cs.LG ↗ · 2026-05-14 Cached

This paper proposes FedMPO, a robust federated multimodal graph learning method that addresses modality heterogeneity and missing modalities through topology-aware cross-modal generation, missing-aware expert routing, and reliability-aware aggregation, achieving performance gains on multiple datasets.

0 favorites 0 likes
#robustness

Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents

arXiv cs.AI ↗ · 2026-05-14 Cached

Introduces Persona Policies (PPol), a plug-and-play control layer that uses LLM-driven evolutionary program search to generate diverse, human-like user personas for evaluating LLM agents. Achieves 33–62% fitness gains over baseline, with human-likeness rated at 80.4%, and improves agent robustness with +17% task success.

0 favorites 0 likes
#robustness

Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents

arXiv cs.AI ↗ · 2026-05-14 Cached

Proposes VeGAS, a test-time framework for MLLM-based embodied agents that samples multiple candidate actions and uses a generative verifier to select the most reliable, achieving up to 36% relative improvement over CoT baselines on challenging tasks.

0 favorites 0 likes
#robustness

SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation

arXiv cs.CL ↗ · 2026-05-13 Cached

This paper introduces SAGE, a framework for scalable automated robustness augmentation of LLM knowledge evaluation benchmarks. It uses fine-tuned smaller models with reinforcement learning to generate and verify question variants at a lower cost than existing methods.

0 favorites 0 likes
#robustness

Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations

arXiv cs.CL ↗ · 2026-05-13 Cached

This paper presents a robust evaluation framework and training strategies for biomedical publication type and study design classification, using knowledge-guided perturbations to mitigate reliance on spurious features.

0 favorites 0 likes
#robustness

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

Hugging Face Daily Papers ↗ · 2026-05-13 Cached

EVA-Bench introduces a comprehensive end-to-end framework for evaluating voice agents, simulating realistic multi-turn conversations and measuring performance across voice-specific failure modes with novel accuracy (EVA-A) and experience (EVA-X) metrics. The benchmark includes 213 scenarios across enterprise domains and a perturbation suite for accent and noise robustness, revealing substantial gaps in current systems.

0 favorites 0 likes
#robustness

Context Training with Active Information Seeking

Hugging Face Daily Papers ↗ · 2026-05-13 Cached

This paper introduces a context optimization method that uses active information seeking via Wikipedia search and browser tools, combined with a search-based training procedure, to achieve robust performance improvements across diverse domains without updating model weights.

0 favorites 0 likes
#robustness

Sanity Checks for Long-Form Hallucination Detection

arXiv cs.CL ↗ · 2026-05-12 Cached

This paper introduces a controlled-invariance methodology and two oracle tests (Force and Remove) to determine if LLM hallucination detectors rely on reasoning traces or final answer artifacts. It proposes TRACT, a lightweight scorer using lexical features, which demonstrates robust performance independent of answer-level cues.

0 favorites 0 likes
#robustness

Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices

arXiv cs.LG ↗ · 2026-05-11 Cached

This paper demonstrates the robustness of refugee matching impact evaluations using off-policy methods like IPW and AIPW, confirming previous findings on algorithmic refugee assignment.

0 favorites 0 likes
#robustness

Reinforcing Multimodal Reasoning Against Visual Degradation

Hugging Face Daily Papers ↗ · 2026-05-10 Cached

This paper introduces ROMA, an RL fine-tuning framework that enhances the robustness of multimodal large language models against visual degradations like blur and compression artifacts. It achieves this through a dual-forward-pass strategy and specialized regularization techniques, improving performance on reasoning benchmarks without sacrificing accuracy on clean inputs.

0 favorites 0 likes
#robustness

Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs

arXiv cs.LG ↗ · 2026-05-08 Cached

This paper introduces NATD-GSSL, a framework evaluating the robustness of Graph Self-Supervised Learning on noisy, text-driven biomedical graphs. It demonstrates that certain GNN architectures and pretext tasks maintain performance despite real-world noise, offering practical guidance for unsupervised learning in imperfect datasets.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback