Research

Robustness of LLMs to adversarial and noisy inputs

1. 2026 More Agents Improve Math Problem Solving but Adversarial Robustness Gap Persists. Findings of ACL 2026
2. 2025 ArithmAttack: Evaluating Robustness of LLMs to Noisy Context in Math Problem Solving. LLMSEC Workshop @ ACL
3. 2024 Exploring Robustness of Multilingual LLMs on Real-World Noisy Data. Eighth Widening NLP Workshop (WiNLP 2024) Phase II

All 9 papers on this topic

Data augmentation for NLP and speech

1. 2026 Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents. WASSA Workshop @ EACL 2026
2. 2025 EDAudio: Easy Data Augmentation for Dialectal Audio. RANLP 2025
3. 2021 AEDA: An Easier Data Augmentation Technique for Text Classification. Findings of EMNLP
4. 2020 Adversarial Training for Aspect-Based Sentiment Analysis with BERT. ICPR

All 6 papers on this topic

AI for science

1. 2026 MiniFool: Physics-Constraint-Aware Minimizer-Based Adversarial Attacks in Deep Neural Networks. The European Physical Journal C
2. 2025 Enforcing Fundamental Relations via Adversarial Attacks on Input Parameter Correlations. Computing and Software for Big Science
3. 2025 Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics at ECML PKDD 2025. ECML PKDD 2025

All 5 papers on this topic

Dialects and speech

1. 2026 Can LLM Agents Identify Spoken Dialects like a Linguist? DialRes Workshop @ LREC 2026
2. 2026 Speaker Normalization via Voice Conversion Reveals a Human–Machine Dissociation in Dialect Classification. DialRes Workshop @ LREC 2026
3. 2025 Improving Low-Resource Dialect Classification Using Retrieval-based Voice Conversion. Interspeech 2025

All 4 papers on this topic