add aire paper page

Author: dfuchss

_bibliography/papers.bib

@@ -127,11 +127,12 @@ @inproceedings{hey_requirements_2025
 }
 
 @inproceedings{fuchss_beyond_2025,
-  author={Fuch{\ss}, Dominik and Schwedt, Stefan and Keim, Jan and Hey, Tobias},
-  booktitle={2025 IEEE 33rd International Requirements Engineering Conference Workshops (REW)},
-  title={{Beyond Retrieval: A Study of Using LLM Ensembles for Candidate Filtering in Requirements Traceability}},
-  year={2025},
-  volume={},
-  number={},
-  pages={}
+  author    = {Fuch{\ss}, Dominik and Schwedt, Stefan and Keim, Jan and Hey, Tobias},
+  booktitle = {2025 IEEE 33rd International Requirements Engineering Conference Workshops (REW)},
+  title     = {{Beyond Retrieval: A Study of Using LLM Ensembles for Candidate Filtering in Requirements Traceability}},
+  year      = {2025},
+  volume    = {},
+  number    = {},
+  pages     = {},
+  html      = {/c/aire25}
 }

_data/authors.yml

@@ -32,3 +32,6 @@ tobias_telge:
 tobias_thirolf:
   name: Tobias Thirolf
   orcid: "0009-0006-7052-4020"
+stefan_schwedt:
+  name: Stefan Schwedt
+  orcid: "0009-0003-8202-3811"

_pages/conferences.md

@@ -5,6 +5,8 @@ nav: true
 nav_order: 1
 dropdown: true
 children:
+  - title: AIRE 2025
+    permalink: /c/aire25
   - title: ICSE 2025
     permalink: /c/icse25
   - title: REFSQ 2025

_pages/conferences/aire25.md

@@ -0,0 +1,42 @@
+---
+layout: publication
+permalink: /c/aire25
+title: "Beyond Retrieval: A Study of Using LLM Ensembles for Candidate Filtering in Requirements Traceability"
+description:
+publication: fuchss_beyond_2025
+authors:
+  - dominik_fuchss
+  - stefan_schwedt
+  - jan_keim
+  - tobias_hey
+---
+
+To be published at the [33rd International Requirements Engineering Conference Workshops (REW)](https://aire-ws.github.io/aire25/).
+
+![Approach Overview](/assets/img/aire-approach.svg){:width="100%" style="background-color: white; border-radius: 8px; padding: 10px; display: block; margin: 0 auto;"}
+
+## Abstract
+
+**[Introduction]**
+Requirements traceability is essential in software development, supporting tasks such as system understanding and change impact analysis.
+Traceability link recovery (TLR) methods, including those using large language models (LLMs) or retrieval-augmented generation (RAG), often rely on information retrieval (IR) to identify candidate artifact pairs.
+They are sensitive to hyperparameters (e.g., top-k, similarity thresholds) that require extensive, project-specific tuning.
+
+**[Methods]**
+We propose an inter-requirements TLR approach that uses an ensemble of small LLMs (or small language models (SLM)) to incrementally reduce the search space, aiming to replace IR-based candidate selection.
+We first analyze the sensitivity of IR methods to hyperparameters, then evaluate the ability of small LLMs to filter unrelated requirement pairs, and compare their performance when integrated into a TLR approach.
+The evaluation includes five projects from the requirements engineering community.
+
+**[Results]**
+We find that IR performance heavily depends on project-specific hyperparameter tuning.
+Furthermore, small LLMs effectively reduce the candidate space with minimal loss of recall.
+While our LLM-based ensemble approach achieves comparable F2-scores to IR methods, it lags in precision.
+
+**[Conclusion]**
+This work provides insights into the capabilities of small LLMs as a filter in inter-requirements TLR.
+Moreover, it provides insights into the performance of traditional IR techniques for TLR and their dependency on hyperparameters.
+
+## Links
+
+- Paper on [KITopen](https://publikationen.bibliothek.kit.edu/1000183058)
+- Replication Package on [Zenodo](https://doi.org/10.5281/zenodo.15837231) and the corresponding [GitHub repository](https://github.com/ArDoCo/Replication-Package-AIRE25_Beyond-Retrieval-Using-LLM-Ensembles-for-Candidate-Filtering-in-Req-TLR)