Liability in Motion: A retrieval-augmented LLM application in road traffic liability apportionment
Identification
- Public canonical key
- radar:r-a9d4cbe471e60c6143b166dec95f70f9
- Authors
- Felix Riechmann
- Reported year
- 2026
- Reported language
- en
- Source type
- preprint
- First detected
- 2026-11-14T02:19:22.053860+00:00
- Last metadata observation
- 2026-11-14T02:19:22.053860+00:00
- Last HTTP verification
- Not checked
Institutions reported by the source
Universität Hamburg
Reported affiliation countries
DE
Documentary abstract — original language
Abstract While legal judgment prediction systems demonstrate increasingly high accuracy, their practical deployment often faces severe normative challenges regarding automated adjudication and remains largely confined to binary classification tasks. This study bridges the gap between technical natural language processing capabilities and practical legal workflows by developing a retrieval-augmented language model tailored for pre-litigation alternative dispute resolution in high-volume mass disputes. Focusing on German road traffic liability, the proposed system predicts continuous, proportional liability distributions based on abbreviated factual summaries drawn from a leading legal commentary. An empirical evaluation examines diverse open-source large language models across different retrieval strategies alongside comprehensive ablation studies on the volume and ordering of in-context demonstrations. Experimental results reveal that integrating taxonomic legal metadata into the retrieval pipeline significantly outperforms purely semantic approaches. Furthermore, providing relevance-ordered demonstrations effectively mitigates context oversaturation, a vulnerability explicitly exposed when reference cases are randomly shuffled. The model achieves predictive error margins that align closely with the underlying operational risk doctrine of German traffic law, effectively capturing fault-based allocations. By transforming an authoritative legal text into a computable coordination device, this research demonstrates how algorithmic prediction can rationalize litigant expectations, alleviate information asymmetries, and facilitate out-of-court settlements without compromising substantive justice in civil law jurisdictions.
Identifiers
- OPENALEX
- https://openalex.org/W7202119791
- DOI
- 10.21203/rs.3.rs-10077930/v1
Documentary context
- Documentary family
- preprint
- Source-reported types
- preprint
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Sources
OpenAlex · Record 1
Cite this reference
Felix Riechmann. Liability in Motion: A retrieval-augmented LLM application in road traffic liability apportionment. 2026. https://doi.org/10.21203/rs.3.rs-10077930/v1
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Felix Riechmann. (2026). Liability in Motion: A retrieval-augmented LLM application in road traffic liability apportionment. https://doi.org/10.21203/rs.3.rs-10077930/v1
- Chicago
- Felix Riechmann. Liability in Motion: A retrieval-augmented LLM application in road traffic liability apportionment. 2026. https://doi.org/10.21203/rs.3.rs-10077930/v1
- ISO 690
- Felix Riechmann. Liability in Motion: A retrieval-augmented LLM application in road traffic liability apportionment. 2026. https://doi.org/10.21203/rs.3.rs-10077930/v1
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. Liability in Motion: A retrieval-augmented LLM application in road traffic liability apportionment. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-a9d4cbe471e60c6143b166dec95f70f9/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://doi.org/10.21203/rs.3.rs-10077930/v1
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.