arXiv subjects

Mark Stevenson

Publications and source records attributed to Mark Stevenson.

At least 19 recordsLinked to original sources

arXiv2026

Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

Automatic fact-checking systems assess the veracity of claims given evidence from relevant documents. Large Language Models (LLMs) have demonstrated strong performance in fact-checking due to their general reasoning capabilities. However, it remains unclear whether they faithfully make use of the evidence provided to reach veracity judgments or rely on parametric knowledge. To investigate this, we introduce Fact-Ablated Evaluation (FAE), a new evaluation framework that iteratively ablates the cited evidence to assess whether LLMs revise their predictions accordingly. Our empirical results show that current off-the-shelf LLMs as fact-checking systems rely more on their parametric knowledge than on the evidence provided. To bridge this gap between prediction accuracy and evidence grounding, we propose REAL (Rigorous Evidence Ablation Learning), a training framework that promotes evidence-dependent verification through counterfactual evidence supervision for the LLM-as-verifier models. Experiments on four fact-checking datasets across different domains demonstrate that models trained with REAL obtain superior evidence-dependent capabilities compared to standard fine-tuned models. Our findings highlight that strong fact-checking performance can still coexist with weak evidence dependency, while REAL encourages veracity predictions to remain more closely tied to the availability of supporting evidence.

cs.CL↗

arXiv2026

Confidence-Based Stopping Methods for Systematic Reviews

Technology Assisted Review stopping methods aim to ensure that no more documents are screened than necessary. Most existing approaches focus on achieving a target recall, which does not consider whether an information need has been met. This paper introduces two heuristic stopping methods that instead monitor whether screened documents contain enough information to make a decision. Evaluation on a standard dataset of Diagnostic Test Accuracy Systematic Reviews demonstrates that the proposed approaches substantially reduce the number of documents that need to be examined while, in the majority of cases, maintaining conclusions that are consistent with all evidence available.

cs.IR↗

arXiv2026

Decision-Theoretic Stopping Rules for Document Screening

Deciding when to stop reviewing the results of a search is a common problem with multiple applications. Existing stopping rules developed within Technology-Assisted Review (TAR) aim to achieve a pre-specified recall target and do not take into account the reason for examining the results, potentially leading to sub-optimal recommendations. This paper applies decision theory to the problem and uses it to derive three practical stopping policies based on the Expected Value of Perfect Information. The approach is applied to two professional search tasks: patent examining and systematic reviewing. Experiments on CLEF-IP and medical systematic review datasets show that the proposed approach generally produces more appropriate stopping decisions than existing methods, as demonstrated by higher net utility under the evaluated cost and payoff settings.

cs.IR↗

arXiv2025

Urban Density and Equity of Access to Social Services in Australian Urban Areas

To measure access to social services (primary health care, early childhood care/education, and public transport), we created two social service access indexes (SSPT and SSI) for Australian capital cities. We show that only two cities, Melbourne and Sydney, have some limited characteristics of a compact or 15-minute city, but only in the city centres and inner city areas where population densities are highest and have less low density housing types. In the outer suburban and peri-urban areas, as well as across all of the remaining cities, proximity to social services is poor and residents suffer the consequences of spatial inequity.

physics.soc-ph↗

arXiv2025

+VeriRel: Verification Feedback to Enhance Document Retrieval for Scientific Fact Checking

Identification of appropriate supporting evidence is critical to the success of scientific fact checking. However, existing approaches rely on off-the-shelf Information Retrieval algorithms that rank documents based on relevance rather than the evidence they provide to support or refute the claim being checked. This paper proposes +VeriRel which includes verification success in the document ranking. Experimental results on three scientific fact checking datasets (SciFact, SciFact-Open and Check-Covid) demonstrate consistently leading performance by +VeriRel for document evidence retrieval and a positive impact on downstream verification. This study highlights the potential of integrating verification feedback to document relevance assessment for effective scientific fact checking systems. It shows promising future work to evaluate fine-grained relevance when examining complex documents for advanced scientific fact checking.

cs.IR↗

arXiv2025

Generating Search Explanations using Large Language Models

Aspect-oriented explanations in search results are typically concise text snippets placed alongside retrieved documents to serve as explanations that assist users in efficiently locating relevant information. While Large Language Models (LLMs) have demonstrated exceptional performance for a range of problems, their potential to generate explanations for search results has not been explored. This study addresses that gap by leveraging both encoder-decoder and decoder-only LLMs to generate explanations for search results. The explanations generated are consistently more accurate and plausible explanations than those produced by a range of baseline models.

cs.IR↗

arXiv2025

The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers

Scientific fact-checking aims to determine the veracity of scientific claims by retrieving and analysing evidence from research literature. The problem is inherently more complex than general fact-checking since it must accommodate the evolving nature of scientific knowledge, the structural complexity of academic literature and the challenges posed by long-form, multimodal scientific expression. However, existing approaches focus on simplified versions of the problem based on small-scale datasets consisting of abstracts rather than full papers, thereby avoiding the distinct challenges associated with processing complete documents. This paper examines the limitations of current scientific fact-checking systems and reveals the many potential features and resources that could be exploited to advance their performance. It identifies key research challenges within evidence retrieval, including (1) evidence-driven retrieval that addresses semantic limitations and topic imbalance (2) time-aware evidence retrieval with citation tracking to mitigate outdated information, (3) structured document parsing to leverage long-range context, (4) handling complex scientific expressions, including tables, figures, and domain-specific terminology and (5) assessing the credibility of scientific literature. Preliminary experiments were conducted to substantiate these challenges and identify potential solutions. This perspective paper aims to advance scientific fact-checking with a specialised IR system tailored for real-world applications.

cs.IR↗

arXiv2025

A Generalised and Adaptable Reinforcement Learning Stopping Method

This paper presents a Technology Assisted Review (TAR) stopping approach based on Reinforcement Learning (RL). Previous such approaches offered limited control over stopping behaviour, such as fixing the target recall and tradeoff between preferring to maximise recall or cost. These limitations are overcome by introducing a novel RL environment, GRLStop, that allows a single model to be applied to multiple target recalls, balances the recall/cost tradeoff and integrates a classifier. Experiments were carried out on six benchmark datasets (CLEF e-Health datasets 2017-9, TREC Total Recall, TREC Legal and Reuters RCV1) at multiple target recall levels. Results showed that the proposed approach to be effective compared to multiple baselines in addition to offering greater flexibility.

cs.IR↗

arXiv2024

General algorithm of assigning raster features to vector maps at any resolution or scale

The fusion of multi-source data is essential for a comprehensive analysis of geographic applications. Due to distinct data structures, the fusion process tends to encounter technical difficulties in terms of preservation of the intactness of each source data. Furthermore, a lack of generalized methods is a problem when the method is expected to be applicable in multiple resolutions, sizes, or scales of raster and vector data, to what is being processed. In this study, we propose a general algorithm of assigning features from raster data (concentrations of air pollutants) to vector components (roads represented by edges) in city maps through the iterative construction of virtual layers to expand geolocation from a city centre to boundaries in a 2D projected map. The construction follows the rule of perfect squares with a slight difference depending on the oddness or evenness of the ratio of city size to raster resolution. We demonstrate the algorithm by applying it to assign accurate PM$_{2.5}$ and NO$_{2}$ concentrations to roads in 1692 cities globally for a potential graph-based pollution analysis. This method could pave the way for agile studies on urgent climate issues by providing a generic and efficient method to accurately fuse multiple datasets of varying scales and compositions.

cs.IR↗

arXiv2024

Challenges and Opportunities of NLP for HR Applications: A Discussion Paper

Over the course of the recent decade, tremendous progress has been made in the areas of machine learning and natural language processing, which opened up vast areas of potential application use cases, including hiring and human resource management. We review the use cases for text analytics in the realm of human resources/personnel management, including actually realized as well as potential but not yet implemented ones, and we analyze the opportunities and risks of these.

cs.CL↗

arXiv2024

RLStop: A Reinforcement Learning Stopping Method for TAR

We present RLStop, a novel Technology Assisted Review (TAR) stopping rule based on reinforcement learning that helps minimise the number of documents that need to be manually reviewed within TAR applications. RLStop is trained on example rankings using a reward function to identify the optimal point to stop examining documents. Experiments at a range of target recall levels on multiple benchmark datasets (CLEF e-Health, TREC Total Recall, and Reuters RCV1) demonstrated that RLStop substantially reduces the workload required to screen a document collection for relevance. RLStop outperforms a wide range of alternative approaches, achieving performance close to the maximum possible for the task under some circumstances.

cs.IR↗

arXiv2024

Document Set Expansion with Positive-Unlabelled Learning Using Intractable Density Estimation

The Document Set Expansion (DSE) task involves identifying relevant documents from large collections based on a limited set of example documents. Previous research has highlighted Positive and Unlabeled (PU) learning as a promising approach for this task. However, most PU methods rely on the unrealistic assumption of knowing the class prior for positive samples in the collection. To address this limitation, this paper introduces a novel PU learning framework that utilizes intractable density estimation models. Experiments conducted on PubMed and Covid datasets in a transductive setting showcase the effectiveness of the proposed method for DSE. Code is available from https://github.com/Beautifuldog01/Document-set-expansion-puDE.

cs.IR↗

arXiv2024

Document Set Expansion with Positive-Unlabeled Learning: A Density Estimation-based Approach

Document set expansion aims to identify relevant documents from a large collection based on a small set of documents that are on a fine-grained topic. Previous work shows that PU learning is a promising method for this task. However, some serious issues remain unresolved, i.e. typical challenges that PU methods suffer such as unknown class prior and imbalanced data, and the need for transductive experimental settings. In this paper, we propose a novel PU learning framework based on density estimation, called puDE, that can handle the above issues. The advantage of puDE is that it neither constrained to the SCAR assumption and nor require any class prior knowledge. We demonstrate the effectiveness of the proposed method using a series of real-world datasets and conclude that our method is a better alternative for the DSE task.

cs.LG↗

arXiv2023

Combining Counting Processes and Classification Improves a Stopping Rule for Technology Assisted Review

Technology Assisted Review (TAR) stopping rules aim to reduce the cost of manually assessing documents for relevance by minimising the number of documents that need to be examined to ensure a desired level of recall. This paper extends an effective stopping rule using information derived from a text classifier that can be trained without the need for any additional annotation. Experiments on multiple data sets (CLEF e-Health, TREC Total Recall, TREC Legal and RCV1) showed that the proposed approach consistently improves performance and outperforms several alternative methods.

cs.IR↗

arXiv2023

Stopping Methods for Technology Assisted Reviews based on Point Processes

Technology Assisted Review (TAR), which aims to reduce the effort required to screen collections of documents for relevance, is used to develop systematic reviews of medical evidence and identify documents that must be disclosed in response to legal proceedings. Stopping methods are algorithms which determine when to stop screening documents during the TAR process, helping to ensure that workload is minimised while still achieving a high level of recall. This paper proposes a novel stopping method based on point processes, which are statistical models that can be used to represent the occurrence of random events. The approach uses rate functions to model the occurrence of relevant documents in the ranking and compares four candidates, including one that has not previously been used for this purpose (hyperbolic). Evaluation is carried out using standard datasets (CLEF e-Health, TREC Total Recall, TREC Legal), and this work is the first to explore stopping method robustness by reporting performance on a range of rankings of varying effectiveness. Results show that the proposed method achieves the desired level of recall without requiring an excessive number of documents to be examined in the majority of cases and also compares well against multiple alternative approaches.

cs.IR↗

arXiv2023

Scalable Label-efficient Footpath Network Generation Using Remote Sensing Data and Self-supervised Learning

Footpath mapping, modeling, and analysis can provide important geospatial insights to many fields of study, including transport, health, environment and urban planning. The availability of robust Geographic Information System (GIS) layers can benefit the management of infrastructure inventories, especially at local government level with urban planners responsible for the deployment and maintenance of such infrastructure. However, many cities still lack real-time information on the location, connectivity, and width of footpaths, and/or employ costly and manual survey means to gather this information. This work designs and implements an automatic pipeline for generating footpath networks based on remote sensing images using machine learning models. The annotation of segmentation tasks, especially labeling remote sensing images with specialized requirements, is very expensive, so we aim to introduce a pipeline requiring less labeled data. Considering supervised methods require large amounts of training data, we use a self-supervised method for feature representation learning to reduce annotation requirements. Then the pre-trained model is used as the encoder of the U-Net for footpath segmentation. Based on the generated masks, the footpath polygons are extracted and converted to footpath networks which can be loaded and visualized by geographic information systems conveniently. Validation results indicate considerable consistency when compared to manually collected GIS layers. The footpath network generation pipeline proposed in this work is low-cost and extensible, and it can be applied where remote sensing images are available. Github: https://github.com/WennyXY/FootpathSeg.

cs.CV↗

arXiv2023

Bio-SIEVE: Exploring Instruction Tuning Large Language Models for Systematic Review Automation

Medical systematic reviews can be very costly and resource intensive. We explore how Large Language Models (LLMs) can support and be trained to perform literature screening when provided with a detailed set of selection criteria. Specifically, we instruction tune LLaMA and Guanaco models to perform abstract screening for medical systematic reviews. Our best model, Bio-SIEVE, outperforms both ChatGPT and trained traditional approaches, and generalises better across medical domains. However, there remains the challenge of adapting the model to safety-first scenarios. We also explore the impact of multi-task training with Bio-SIEVE-Multi, including tasks such as PICO extraction and exclusion reasoning, but find that it is unable to match single-task Bio-SIEVE's performance. We see Bio-SIEVE as an important step towards specialising LLMs for the biomedical systematic review process and explore its future developmental opportunities. We release our models, code and a list of DOIs to reconstruct our dataset for reproducibility.

cs.CL↗

arXiv2022

On the Security Vulnerabilities of Text-to-SQL Models

Although it has been demonstrated that Natural Language Processing (NLP) algorithms are vulnerable to deliberate attacks, the question of whether such weaknesses can lead to software security threats is under-explored. To bridge this gap, we conducted vulnerability tests on Text-to-SQL systems that are commonly used to create natural language interfaces to databases. We showed that the Text-to-SQL modules within six commercial applications can be manipulated to produce malicious code, potentially leading to data breaches and Denial of Service attacks. This is the first demonstration that NLP models can be exploited as attack vectors in the wild. In addition, experiments using four open-source language models verified that straightforward backdoor attacks on Text-to-SQL systems achieve a 100% success rate without affecting their performance. The aim of this work is to draw the community's attention to potential software security issues associated with NLP algorithms and encourage exploration of methods to mitigate against them.

cs.CL↗