1 citations · 2 across the 12 of their papers we have counts for
14 papers
Diversity Combining for Multi-Path LLM Reasoning
Guangsheng Yu, Litianyi Zhang, Qin Wang +5
Multi-path reasoning methods such as self-consistency (SC) sample reasoning paths and choose the most frequent answer. However, their gains quickly plateau as increases, an…
CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion
Chenhan Zhang, Ali Braytee, Madhushi Bandara +4
Graph unlearning removes the influence of designated training data from a trained graph model without retraining from scratch. However, existing methods suffer a sharp drop in mode…
En-ViMedNER: An English-Vietnamese Parallel Biomedical Corpus with UMLS Semantic Type Annotations
Nhu Vo, Phuong Nguyen, Nu Uyen Phuong Le +4
Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information extraction. While corpora with U…
Sample-Efficient Misconfiguration Classification for Network Resilience in Wireless Communications
Xin Hao, Massimo Piccardi, Chenhan Zhang +4
As modern wireless communication networks grow increasingly complex, network outages driven by the inconsistency between dynamic topologies and protocol configurations have become…
DTO: a Differentiable Training Objective for Effective Counterfactual Story Rewriting
Amelia Girard, Massimo Piccardi
Counterfactual story rewriting is a natural language processing task that requires updating an existing story to reflect a chosen alternative event, yet preserving all the unaffect…
Enhancing Network Resilience via Graph-Based Anomaly Detection in Sovereign Functions
Xin Hao, Wei Ni, Chenhan Zhang +2
Sovereign network functions, e.g., routing protocols, are becoming increasingly complex and susceptible to failures arising from protocol configuration anomalies and anomalous conf…
Pref-CTRL: Preference Driven LLM Alignment using Representation Editing
Imranul Ashrafi, Inigo Jauregi Unanue, Massimo Piccardi
Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time with lightweight interventions on…
ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark
Tung X. Nguyen, Nhu Vo, Giang-Son Nguyen +6
Code-switching (CS), which is when Vietnamese speech uses English words like drug names or procedures, is a common phenomenon in Vietnamese medical communication. This creates chal…
Multilingual LLM Prompting Strategies for Medical English-Vietnamese Machine Translation
Nhu Vo, Nu-Uyen-Phuong Le, Dung D. Le +2
Medical English-Vietnamese machine translation (En-Vi MT) is essential for healthcare access and communication in Vietnam, yet Vietnamese remains a low-resource and under-studied l…
A Constraint-Enforcing Reward for Adversarial Attacks on Text Classifiers
Tom Roth, Inigo Jauregi Unanue, Alsharif Abuadbba +1
Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constr…
Improving Vietnamese-English Medical Machine Translation
Nhu Vo, Dat Quoc Nguyen, Dung D. Le +2
Machine translation for Vietnamese-English in the medical domain is still an under-explored research area. In this paper, we introduce MedEV -- a high-quality Vietnamese-English pa…
SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization
Jacob Parnell, Inigo Jauregi Unanue, Massimo Piccardi
Cross-lingual summarization (XLS) generates summaries in a language different from that of the input documents (e.g., English to Spanish), allowing speakers of the target language…
A Generative Adversarial Attack for Multilingual Text Classifiers
Tom Roth, Inigo Jauregi Unanue, Alsharif Abuadbba +1
Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks,…
A non-parametric conditional factor regression model for high-dimensional input and response
Ava Bargi, Richard Yi Da Xu, Massimo Piccardi
In this paper, we propose a non-parametric conditional factor regression (NCFR)model for domains with high-dimensional input and response. NCFR enhances linear regression in two wa…