Julian Hough

Rachel Hill, Tom Owen, Julian Hough

Despite careful design involving classifiers, parameters, and safeguarding, errors during human/AI interaction are not rare. Poor error recovery can disrupt interaction flow, damage user trust, and decrease user engagement. Whilst existing work has explored LLM recovery, tone, context, and personality as separate design dimensions, no existing work has combined these variables into a structured guidance framework. This paper presents a recovery code that maps four common LLM chatbot task contexts to associated personality traits (four Big Five personalities: Conscientiousness, Agreeableness, Openness, and Extraversion), tones, and three-stage recovery instructions. A recovery evaluation rubric was also designed, comprising three dimensions (Recovery quality, Tone alignment, and Appropriateness) and nine sub-dimensions. The methodology is exploratory, with no participants used. A between-subjects design was employed across two conditions: Condition A (baseline, uncoded), four separate Claude Sonnet 4.6 agents received no recovery code training; Condition B (coded), four separate Claude Sonnet 4.6 models were trained on the recovery code. Identical 'user' prompts and error scenarios were used across both conditions. Eight LLM evaluator agents assessed the recovery responses using the evaluation rubric, producing scores out of 5 for each sub-dimension. Results found a 27.8% average performance increase in coded recovery responses (76.7%) compared to baseline responses (48.9%). Condition B performed strongest in the appropriateness dimension (83.3%), with notable improvement in personality appropriateness (75% versus 50%) and providing explanation (60% versus 20%). These findings suggest that structured personality, context, and tone-informed recovery codes can be successfully learnt and applied by LLM chatbots to improve error recovery quality across varying contextual tasks.

Deshan Sumanathilaka, Nicholas Micallef, Julian Hough et al.

Recent advances in language models have substantially improved Natural Language Understanding (NLU). Although widely used benchmarks suggest that Large Language Models (LLMs) can effectively disambiguate, their practical applicability in real-world narrative contexts remains underexplored. SemEval-2026 Task 5 addresses this gap by introducing a task that predicts the human-perceived plausibility of a word sense within a short story. In this work, we propose an LLM-based framework for plausibility scoring of homonymous word senses in narrative texts using a structured reasoning mechanism. We examine the impact of fine-tuning low-parameter LLMs with diverse reasoning strategies, alongside dynamic few-shot prompting for large-parameter models, on accurate sense identification and plausibility estimation. Our results show that commercial large-parameter LLMs with dynamic few-shot prompting closely replicate human-like plausibility judgments. Furthermore, model ensembling slightly improves performance, better simulating the agreement patterns of five human annotators compared to single-model predictions

Deshan Sumanathilaka, Nicholas Micallef, Julian Hough

Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD performance, their computational and energy demands limit scalability. This study investigates whether low-parameter LLMs (<4B parameters) can achieve comparable results through fine-tuning strategies that emphasize reasoning-driven sense identification. Using the FEWS dataset augmented with semi-automated, rationale-rich annotations, we fine-tune eight small-scale open-source LLMs (e.g. Gemma and Qwen). Our results reveal that Chain-of-Thought (CoT)-based reasoning combined with neighbour-word analysis achieves performance comparable to GPT-4-Turbo in zero-shot settings. Importantly, Gemma-3-4B and Qwen-3-4B models consistently outperform all medium-parameter baselines and state-of-the-art models on FEWS, with robust generalization to unseen senses. Furthermore, evaluation on the unseen "Fool Me If You Can'' dataset confirms strong cross-domain adaptability without task-specific fine-tuning. This work demonstrates that with carefully crafted reasoning-centric fine-tuning, low-parameter LLMs can deliver accurate WSD while substantially reducing computational and energy demands.

Rachel Hill, Tom Owen, Julian Hough

In 2025 one million Anti-Social Behaviour (ASB) cases were recorded in England & Wales, impacting community cohesion. Statutory guidance presents punitive interventions that lack technological input and does not often root ethical frameworks within government system design. This work takes a novel approach in framing ASB intervention as a human-computer interaction problem by embedding an ethical framework into two digital designs, aiming to increase public responsibility and prevent ASB. The first design is extracted from UK public opinion research, the ethical themes include punitive proportionality, personalisation, and responsibility. The second are digital interventions that present a set of QR-based public reporting interfaces and a web-based ASB awareness course that precedes punitive escalation. Our methodology involves structured interviews and online surveys. Results positively evaluated the framework and QR interfaces. Such outcomes could inform the expansion of technological intervention utilisation that does not replace existing punitive approaches, but balances them.

Carlos Baptista De Lima, Julian Hough, Frank Förster et al.

Achieving truly fluid interaction with robots with speech interfaces remains a hard problem, and the experience of current Human-Robot Interaction (HRI) remains laboured and frustrating. Some of the barriers to fluid interaction stem from a lack of a suitable development platform for HRI for improving interaction, even in robotic Wizard-of-Oz (WoZ) modes of operation used for data collection and prototyping. Based on previous systems, we propose the properties of interruptibility and correction (IaC), pollability, latency measurement and optimisation and time-accurate reproducibility of actions from logging data as key criteria for a fluid WoZ system to support fluid error correction. We finish by presenting a Virtual Reality (VR) HRI simulation environment for mobile manipulators which meets these criteria.

Deshan Sumanathilaka, Isuri Anuradha, Ruvan Weerasinghe et al.

The paper overviews the shared task on Real-Time Reverse Transliteration for Romanized Indo-Aryan languages. It focuses on the reverse transliteration of low-resourced languages in the Indo-Aryan family to their native scripts. Typing Romanized Indo-Aryan languages using ad-hoc transliterals and achieving accurate native scripts are complex and often inaccurate processes with the current keyboard systems. This task aims to introduce and evaluate a real-time reverse transliterator that converts Romanized Indo-Aryan languages to their native scripts, improving the typing experience for users. Out of 11 registered teams, four teams participated in the final evaluation phase with transliteration models for Sinhala, Hindi and Malayalam. These proposed solutions not only solve the issue of ad-hoc transliteration but also empower low-resource language usability in the digital arena.

T. G. D. K. Sumanathilaka, Nicholas Micallef, Julian Hough

Ambiguous words are often found in modern digital communications. Lexical ambiguity challenges traditional Word Sense Disambiguation (WSD) methods, due to limited data. Consequently, the efficiency of translation, information retrieval, and question-answering systems is hindered by these limitations. This study investigates the use of Large Language Models (LLMs) to improve WSD using a novel approach combining a systematic prompt augmentation mechanism with a knowledge base (KB) consisting of different sense interpretations. The proposed method incorporates a human-in-loop approach for prompt augmentation where prompt is supported by Part-of-Speech (POS) tagging, synonyms of ambiguous words, aspect-based sense filtering and few-shot prompting to guide the LLM. By utilizing a few-shot Chain of Thought (COT) prompting-based approach, this work demonstrates a substantial improvement in performance. The evaluation was conducted using FEWS test data and sense tags. This research advances accurate word interpretation in social media and digital communication.

Chris Madge, Maris Camilleri, Paloma Carretero Garcia et al.

We introduce the Minecraft Dialogue Corpus with Reference (MDC-R). MDC-R is a new language resource that supplements the original Minecraft Dialogue Corpus (MDC) with expert annotations of anaphoric and deictic reference. MDC's task-orientated, multi-turn, situated dialogue in a dynamic environment has motivated multiple annotation efforts, owing to the interesting linguistic phenomena that this setting gives rise to. We believe it can serve as a valuable resource when annotated with reference, too. Here, we discuss our method of annotation and the resulting corpus, and provide both a quantitative and a qualitative analysis of the data. Furthermore, we carry out a short experiment demonstrating the usefulness of our corpus for referring expression comprehension.

Deshan Sumanathilaka, Nicholas Micallef, Julian Hough

Recent advances in Large Language Models (LLMs) have significantly reshaped the landscape of Natural Language Processing (NLP). Among the various prompting techniques, few-shot prompting has gained considerable attention for its practicality and effectiveness. This study investigates how few-shot prompting strategies impact the Word Sense Disambiguation (WSD) task, particularly focusing on the biases introduced by imbalanced sample distributions. We use the GLOSSGPT prompting method, an advanced approach for English WSD, to test its effectiveness across five languages: English, German, Spanish, French, and Italian. Our results show that imbalanced few-shot examples can cause incorrect sense predictions in multilingual languages, but this issue does not appear in English. To assess model behavior, we evaluate both the GPT-4o and LLaMA-3.1-70B models and the results highlight the sensitivity of multilingual WSD to sample distribution in few-shot settings, emphasizing the need for balanced and representative prompting strategies.

Morteza Rohanian, Julian Hough, Matthew Purver

We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree, evaluating the ADReSSo challenge 2021 data. Our best model, a BiLSTM with highway layers using words, word probabilities, disfluency features, pause information, and a variety of acoustic features, achieves an accuracy of 84% and RSME error prediction of 4.26 on MMSE cognitive scores. While predicting cognitive decline is more challenging, our models show improvement using the multimodal approach and word probabilities, disfluency and pause information over word-only models. We show considerable gains for AD classification using multimodal fusion and gating, which can effectively deal with noisy inputs from acoustic features and ASR hypotheses.

Morteza Rohanian, Julian Hough, Matthew Purver

This paper is a submission to the Alzheimer's Dementia Recognition through Spontaneous Speech (ADReSS) challenge, which aims to develop methods that can assist in the automated prediction of severity of Alzheimer's Disease from speech data. We focus on acoustic and natural language features for cognitive impairment detection in spontaneous speech in the context of Alzheimer's Disease Diagnosis and the mini-mental state examination (MMSE) score prediction. We proposed a model that obtains unimodal decisions from different LSTMs, one for each modality of text and audio, and then combines them using a gating mechanism for the final prediction. We focused on sequential modelling of text and audio and investigated whether the disfluencies present in individuals' speech relate to the extent of their cognitive impairment. Our results show that the proposed classification and regression schemes obtain very promising results on both development and test sets. This suggests Alzheimer's Disease can be detected successfully with sequence modeling of the speech data of medical sessions.

Morteza Rohanian, Julian Hough

We present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging, and utterance segmentation in a simple deep recurrent setting. We show that these tasks provide positive inductive biases to each other with the optimal contribution of each one relying on the severity of the noise from the task. Our live multi-task model outperforms similar individual tasks, delivers competitive performance, and is beneficial for future use in conversational agents in psychiatric treatment.

Mehrnoosh Sadrzadeh, Matthew Purver, Julian Hough et al.

One of the fundamental requirements for models of semantic processing in dialogue is incrementality: a model must reflect how people interpret and generate language at least on a word-by-word basis, and handle phenomena such as fragments, incomplete and jointly-produced utterances. We show that the incremental word-by-word parsing process of Dynamic Syntax (DS) can be assigned a compositional distributional semantics, with the composition operator of DS corresponding to the general operation of tensor contraction from multilinear algebra. We provide abstract semantic decorations for the nodes of DS trees, in terms of vectors, tensors, and sums thereof; using the latter to model the underspecified elements crucial to assigning partial representations during incremental processing. As a working example, we give an instantiation of this theory using plausibility tensors of compositional distributional semantics, and show how our framework can incrementally assign a semantic plausibility measure as it parses phrases and sentences.

Julian Hough, Matthew Purver

We present STIR (STrongly Incremental Repair detection), a system that detects speech repairs and edit terms on transcripts incrementally with minimal latency. STIR uses information-theoretic measures from n-gram models as its principal decision features in a pipeline of classifiers detecting the different stages of repairs. Results on the Switchboard disfluency tagged corpus show utterance-final accuracy on a par with state-of-the-art incremental repair detection methods, but with better incremental accuracy, faster time-to-detection and less computational overhead. We evaluate its performance using incremental metrics and propose new repair processing evaluation standards.