Mark Gales

Cross-Lingual Transfer Learning for Speech Translation NAACL 2025 Finetuning LLMs for Comparative Assessment Tasks COLING 2025 Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge UAI 2025 SkillAggregation: Reference-free LLM-Dependent Aggregation ACL 2025 Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs EMNLP 2025 Unlearning vs. Obfuscation: Are We Truly Removing Knowledge? EMNLP 2025 An Information-Theoretic Approach to Analyze NLP Classification Tasks ACL 2024 Efficient LLM Comparative Assessment: A Product of Experts Framework for Pairwise Comparisons EMNLP 2024 Efficient Sample-Specific Encoder Perturbations NAACL 2024 Highly Intelligible Speaker-Independent Articulatory Synthesis Interspeech 2024 Investigating the Emergent Audio Classification Ability of ASR Foundation Models NAACL 2024 Is It Possible to Modify Text to a Target Readability Level? An Initial Investigation Using Zero-Shot Large Language Models COLING 2024 Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment EMNLP 2024 LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models EACL 2024 LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History EMNLP 2024 Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation Models EMNLP 2024 On the Usefulness of Speaker Embeddings for Speaker Retrieval in the Wild: A Comparative Study of x-vector and ECAPA-TDNN Models Interspeech 2024 Question-Based Retrieval using Atomic Units for Enterprise RAG EMNLP 2024 Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models ACL 2024 WaterJudge: Quality-Detection Trade-off when Watermarking Large Language Models NAACL 2024 Who Needs Decoders? Efficient Estimation of Sequence-Level Attributes with Proxies EACL 2024 Assessing Distractors in Multiple-Choice Tests AACL 2023 CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models ACL 2023 Minimum Bayes’ Risk Decoding for System Combination of Grammatical Error Correction Systems IJCNLP 2023 Mitigating Word Bias in Zero-shot Prompt-based Classifiers IJCNLP 2023 MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization IJCNLP 2023 Sample Attackability in Natural Language Adversarial Attacks ACL 2023 SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models EMNLP 2023 “World Knowledge” in Multiple Choice Reading Comprehension EACL 2023 Analyzing Biases to Spurious Correlations in Text Classification Tasks AACL 2022 Answer Uncertainty and Unanswerability in Multiple-Choice Machine Reading Comprehension ACL 2022 Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks? AACL 2022 On Assessing and Developing Spoken ’Grammatical Error Correction’ Systems NAACL 2022 Residue-Based Natural Language Adversarial Attack Detection NAACL 2022 View-Specific Assessment of L2 Spoken English Interspeech 2022 Long-Span Summarization via Local Attention and Content Selection ACL 2021 Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets NeurIPS 2021 Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems EMNLP 2021 Uncertainty Estimation in Autoregressive Structured Prediction ICLR 2021 Complementary Systems for Off-Topic Spoken Response Detection ACL 2020 Ensemble Distribution Distillation ICLR 2020 Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness NeurIPS 2019 Active Memory Networks for Language Modeling Interspeech 2018 A Deep Learning Approach to Assessing Non-native Pronunciation of English Using Phone Distances Interspeech 2018 Automatic Speech Recognition System Development in the "Wild" Interspeech 2018 Impact of ASR Performance on Free Speaking Language Assessment Interspeech 2018 Predictive Uncertainty Estimation via Prior Networks NeurIPS 2018 Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems Interspeech 2018 Incorporating Uncertainty into Deep Learning for Spoken Language Assessment ACL 2017 Off-topic Response Detection for Spontaneous Spoken English Assessment ACL 2016