Understanding LLMs in Title-Abstract Screening: From Disagreements to Recommendations

• URL: http://arxiv.org/abs/2606.17588v1
• Date: Tue, 16 Jun 2026 06:51:04 GMT
• Title: Understanding LLMs in Title-Abstract Screening: From Disagreements to Recommendations
• Abstract summary: We investigate the reliability of large language models (LLMs) for title-abstract screening in systematic reviews (SRs)<n>We analyzed disagreements between LLMs and researchers across six software engineering SRs and over 1,000 primary study papers.<n>We propose recommendations such as validating semantic understanding before deployment, running multiple LLMs, and focusing validation efforts on borderline cases.
• Score: 9.627821515153576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Several studies have examined the use of large language models (LLMs) for title-abstract screening in systematic reviews (SRs), reporting mixed accuracy. However, questions of reliability remain largely unaddressed. In this study, we go beyond quantitative LLM-human agreement metrics and qualitatively investigate how and why LLMs fail. We also propose actionable recommendations. We analyzed disagreements between LLMs and researchers across six software engineering SRs and over 1,000 primary study papers. For each SR, papers were screened independently by human experts and LLMs in zero-shot mode, resulting in Kappa values ranging from 0.52 to 0.77. Qualitative analysis suggests that human-LLM disagreement results from recurring, identifiable causes, such as boundary ambiguity in key terms, keyword overemphasization, and incorrect topic inference. Based on these findings, we propose recommendations such as validating semantic understanding before deployment, running multiple LLMs, and focusing validation efforts on borderline cases. Future studies are needed to validate the impact of our recommendations, and community efforts are needed to develop normative guidelines on LLM usage in SRs.

Related papers

• LLM-REVal: Can We Trust LLM Reviewers Yet? [70.58742663985652]
  Large language models (LLMs) have inspired researchers to integrate them extensively into the academic workflow.<n>This study focuses on how the deep integration of LLMs into both peer-review and research processes may influence scholarly fairness.
  arXiv  Detail & Related papers  (2025-10-14T10:30:20Z)
• LLM-Specific Utility: A New Perspective for Retrieval-Augmented Generation [110.610512800947]
  Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge.<n>Existing studies often treat utility as a generic attribute, ignoring the fact that different LLMs may benefit differently from the same passage.
  arXiv  Detail & Related papers  (2025-10-13T12:57:45Z)
• Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review [66.73247554182376]
  Large language models (LLMs) have led to their integration into peer review.<n>The unchecked adoption of LLMs poses significant risks to the integrity of the peer review system.<n>We show that manipulating 5% of the reviews could potentially cause 12% of the papers to lose their position in the top 30% rankings.
  arXiv  Detail & Related papers  (2024-12-02T16:55:03Z)
• DnA-Eval: Enhancing Large Language Model Evaluation through Decomposition and Aggregation [75.81096662788254]
  Large Language Models (LLMs) are scalable and economical evaluators.<n>The question of how reliable these evaluators are has emerged as a crucial research question.<n>We propose Decompose and Aggregate, which breaks down the evaluation process into different stages based on pedagogical practices.
  arXiv  Detail & Related papers  (2024-05-24T08:12:30Z)
• Large Language Models are Inconsistent and Biased Evaluators [2.136983452580014]
  We show that Large Language Models (LLMs) are biased evaluators as they exhibit familiarity bias and show skewed distributions of ratings. We also found that LLMs are inconsistent evaluators, showing low "inter-sample" agreement and sensitivity to prompt differences that are insignificant to human understanding of text quality.
  arXiv  Detail & Related papers  (2024-05-02T20:42:28Z)
• Evaluation of an LLM in Identifying Logical Fallacies: A Call for Rigor When Adopting LLMs in HCI Research [3.4245017707416157]
  We present the evaluation of an LLM in identifying logical fallacies that will form part of a digital misinformation intervention. By comparing to a labeled dataset, we found that GPT-4 achieves an accuracy of 0.79, and for our intended use case that excludes invalid or unidentified instances, an accuracy of 0.90.
  arXiv  Detail & Related papers  (2024-04-08T06:00:14Z)
• Benchmarking LLMs via Uncertainty Quantification [91.72588235407379]
  The proliferation of open-source Large Language Models (LLMs) has highlighted the urgent need for comprehensive evaluation methods. We introduce a new benchmarking approach for LLMs that integrates uncertainty quantification. Our findings reveal that: I) LLMs with higher accuracy may exhibit lower certainty; II) Larger-scale LLMs may display greater uncertainty compared to their smaller counterparts; and III) Instruction-finetuning tends to increase the uncertainty of LLMs.
  arXiv  Detail & Related papers  (2024-01-23T14:29:17Z)
• Breaking the Silence: the Threats of Using LLMs in Software Engineering [12.368546216271382]
  Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community. This paper initiates an open discussion on potential threats to the validity of LLM-based research.
  arXiv  Detail & Related papers  (2023-12-13T11:02:19Z)
• Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks [65.69651759036535]
  We analyze whether large language models (LLMs) can serve as reliable alternatives to humans.<n>This paper explores both conventional tasks (e.g., story generation) and alignment tasks (e.g., math reasoning)<n>We find that LLM evaluators can generate unnecessary criteria or omit crucial criteria, resulting in a slight deviation from the experts.
  arXiv  Detail & Related papers  (2023-10-30T17:04:35Z)
• Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment [35.42539816648068]
  This paper presents a comprehensive survey of key dimensions that are crucial to consider when assessing large language models (LLMs) The survey covers seven major categories of LLM trustworthiness: reliability, safety, fairness, resistance to misuse, explainability and reasoning, adherence to social norms, and robustness. Results indicate that, in general, more aligned models tend to perform better in terms of overall trustworthiness.
  arXiv  Detail & Related papers  (2023-08-10T06:43:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.