187 citations · 1.6k across the 127 of their papers we have counts for
137 papers · 1 filter
Beyond Context Length: Characterising the Difficulty of Long-Context Reasoning
Shiwen Qin, Cameron Barker, Henry Gouk +4
Long-context language models support ever longer context windows, and evaluations typically treat context length as the main indicator of difficulty. However, context length alone…
Strategically Diverse Sampling for Self-Training
Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata
Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningfully differ. Self-training fac…
What, When, and How: Audio Description as Constrained Global Optimization
Igor Sterner, Mirella Lapata, Alex Lascarides +1
Audio Description (AD) makes movies accessible to blind and visually impaired audiences by narrating visual information in gaps between dialogue. Existing automatic AD systems larg…
REFRAMED: Towards Realistic Audio Description Generation for Movies
Igor Sterner, Mirella Lapata, Alex Lascarides +1
Audio Description (AD) is a verbal narration of key visual content in videos, enabling access for visually impaired audiences. Unlike standard video captioning, AD is a structured…
Storyline Trees: Hierarchical Representations for Long-Form Narratives
Litu Ou, Mirella Lapata
Long-form narratives are challenging for long-context models because their structure is implicit: events, characters, and plotlines interact across hundreds of pages without the ex…
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
Miao Li, Irina Saparina, Alexander Gurung +1
Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using…
GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study
Gaspard Michel, Elena V. Epure, Romain Hennequin +2
Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another crucial aspect: the textual con…
Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books
Argyrios Papoudakis, Mirella Lapata, Frank Keller
Character description generation is an important capability for narrative-focused applications such as summarization, story analysis, and character-driven simulations. However, gen…
MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games
Jacob Eisenstein, Fantine Huot, Adam Fisch +2
We present a scalable and verifiable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communicatio…
Lightweight Latent Reasoning for Narrative Tasks
Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata
Large language models (LLMs) tackle complex tasks by generating long chains of thought or "reasoning traces" that act as latent variables in the generation of an output given a que…
Reasoning about Intent for Ambiguous Requests
Irina Saparina, Mirella Lapata
Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safety risks when that interpretation is wr…
Patient-Centered Summarization Framework for AI Clinical Summarization: A Mixed-Methods Design
Maria Lizarazo Jimenez, Ana Gabriela Claros, Kieran Green +15
Large Language Models (LLMs) are increasingly demonstrating the potential to reach human-level performance in generating clinical summaries from patient-clinician conversations. Ho…
Help Me Write a Story: Evaluating LLMs' Ability to Generate Writing Feedback
Hannah Rashkin, Elizabeth Clark, Fantine Huot +1
Can LLMs provide support to creative writers by giving meaningful writing feedback? In this paper, we explore the challenges and limitations of model-generated writing feedback by…
Compositional Generalisation for Explainable Hate Speech Detection
Agostina Calabrese, Tom Sherborne, Björn Ross +1
Hate speech detection is key to online content moderation, but current models struggle to generalise beyond their training data. This has been linked to dataset biases and the use…
Explanatory Summarization with Discourse-Driven Planning
Dongqi Liu, Xi Yu, Vera Demberg +1
Lay summaries for scientific documents typically include explanations to help readers grasp sophisticated concepts or arguments. However, current automatic summarization methods do…
Long-Form Information Alignment Evaluation Beyond Atomic Facts
Danna Zheng, Mirella Lapata, Jeff Z. Pan
Information alignment evaluators are vital for various NLG evaluation tasks and trustworthy LLM deployment, reducing hallucinations and enhancing user trust. Current fine-grained m…
Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation
Wenyu Huang, Pavlos Vougiouklis, Mirella Lapata +1
Multi-hop Question Answering (MHQA) adds layers of complexity to question answering, making it more challenging. When Language Models (LMs) are prompted with multiple search result…
Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
Yiming Du, Wenyu Huang, Danna Zheng +5
Memory is fundamental to large language model (LLM)-based agents, but existing surveys emphasize application-level use (e.g., personalized dialogue), while overlooking the atomic o…
Learning to Reason for Long-Form Story Generation
Alexander Gurung, Mirella Lapata
Generating high-quality stories spanning thousands of tokens requires competency across a variety of skills, from tracking plot and character arcs to keeping a consistent and engag…
Disambiguate First, Parse Later: Generating Interpretations for Ambiguity Resolution in Semantic Parsing
Irina Saparina, Mirella Lapata
Handling ambiguity and underspecification is an important challenge in natural language interfaces, particularly for tasks like text-to-SQL semantic parsing. We propose a modular a…
Uncertainty Quantification in Retrieval Augmented Question Answering
Laura Perez-Beltrachini, Mirella Lapata
Retrieval augmented Question Answering (QA) helps QA models overcome knowledge gaps by incorporating retrieved evidence, typically a set of passages, alongside the question at test…
What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations
Dongqi Liu, Chenxi Whitehouse, Xi Yu +6
Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed…
Context-Aware Hierarchical Merging for Long Document Summarization
Litu Ou, Mirella Lapata
Hierarchical Merging is a technique commonly used to summarize very long texts (100K tokens) by breaking down the input into smaller sections, summarizing those sections individ…
Decomposed Opinion Summarization with Verified Aspect-Aware Modules
Miao Li, Jey Han Lau, Eduard Hovy +1
Opinion summarization plays a key role in deriving meaningful insights from large-scale online reviews. To make the process more explainable and grounded, we propose a domain-agnos…