Bill Byrne

Benchmarking Deflection and Hallucination in Large Vision-Language Models ACL 2026 Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models EACL 2026 Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models ACL 2026 What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation ACL 2026 Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models ACL 2025 RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generation EMNLP 2025 Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection EMNLP 2025 XRAG: Cross-lingual Retrieval-Augmented Generation EMNLP 2025 A Preference-driven Paradigm for Enhanced Translation with Large Language Models NAACL 2024 Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata NAACL 2024 Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding NAACL 2024 Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning ACL 2024 PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers ACL 2024 Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision EMNLP 2024 The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities ACL 2024 An Inner Table Retriever for Robust Table Question Answering ACL 2023 Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering NeurIPS 2023 FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering EACL 2023 LI-RAGE: Late Interaction Retrieval Augmented Generation with Explicit Signals for Open-Domain Table Question Answering ACL 2023 More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking EACL 2023 Neural Ranking with Weak Supervision for Open-Domain Question Answering : A Survey EACL 2023 xPQA: Cross-Lingual Product Question Answering in 12 Languages ACL 2023 First the Worst: Finding Better Gender Translations During Beam Search ACL 2022 FocusQA: Open-Domain Question Answering with a Context in Focus EMNLP 2022 From Rewriting to Remembering: Common Ground for Conversational QA Models ACL 2022 Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices ACL 2022 Retrieval Augmented Visual Question Answering with Outside Knowledge EMNLP 2022 The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation NAACL 2022 uFACT: Unfaithful Alien-Corpora Training for Semantically Consistent Data-to-Text Generation ACL 2022 GCDF1: A Goal- and Context- Driven F-Score for Evaluating User Models EMNLP 2021 Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation EMNLP 2021 Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking EMNLP 2021 TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems ACL 2021 Transferable Dialogue Systems and User Simulators ACL 2021 Addressing Exposure Bias With Document Minimum Risk Training: Cambridge at the WMT20 Biomedical Translation Task EMNLP 2020 Inference-only sub-character decomposition improves translation of unseen logographic characters AACL 2020 Neural Machine Translation Doesn’t Translate Gender Coreference Right Unless You Make It COLING 2020 Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem ACL 2020 The Teacher-Student Chatroom Corpus COLING 2020 Using Context in Neural Machine Translation Training Objectives ACL 2020 CUED@WMT19:EWC&LMs ACL 2019 Domain Adaptive Inference for Neural Machine Translation ACL 2019 Neural and FST-based approaches to grammatical error correction ACL 2019 Neural Grammatical Error Correction with Finite State Transducers NAACL 2019 On NMT Search Errors and Model Errors: Cat Got Your Tongue? EMNLP 2019 Semi-Supervised Bootstrapping of Dialogue State Trackers for Task-Oriented Modelling EMNLP 2019 Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset EMNLP 2019 The CUED’s Grammatical Error Correction Systems for BEA-2019 ACL 2019 UCAM Biomedical Translation at WMT19: Transfer Learning Multi-domain Ensembles ACL 2019 Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment NAACL 2018 An Operation Sequence Model for Explainable Neural Machine Translation EMNLP 2018 Multi-representation ensembles and delayed SGD updates improve syntax-based NMT ACL 2018 Neural Machine Translation Decoding with Terminology Constraints NAACL 2018 The University of Cambridge’s Machine Translation Systems for WMT18 EMNLP 2018 Break it Down for Me: A Study in Automated Lyric Annotation EMNLP 2017 Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices EACL 2017 SGNMT – A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies EMNLP 2017 Unfolding and Shrinking Neural Machine Translation Ensembles EMNLP 2017 Speed-Constrained Tuning for Statistical Machine Translation Using Bayesian Optimization NAACL 2016 Syntactically Guided Neural Machine Translation ACL 2016 Fast and Accurate Preordering for SMT using Neural Networks NAACL 2015 The Geometry of Statistical Machine Translation NAACL 2015 Transducer Disambiguation with Sparse Topological Features EMNLP 2015 Effective Incorporation of Source Syntax into Hierarchical Phrase-based Translation COLING 2014 Proceedings of the ACL 2014 Student Research Workshop ACL 2014 Source-side Preordering for Translation using Logistic Regression and Depth-first Branch-and-Bound Search EACL 2014 Word Ordering with Phrase-Based Grammars EACL 2014