Search papers, labs, and topics across Lattice.
This paper details HULAT2-UC3M's participation in the MER-TRANS 2026 shared task, focusing on multilingual Easy-to-Read translation in Spanish. Utilizing a LangGraph-based multi-agent workflow, the team submitted three runs that employed various strategies, including controlled editing and lexical support, with RUN1 achieving the highest SARI score of 44.0543. The findings reveal that signal-guided multi-agent routing significantly outperformed a baseline approach, while the addition of lexical support did not enhance performance as expected.
Signal-guided multi-agent routing outperformed traditional linear regeneration methods in generating Easy-to-Read Spanish translations, challenging assumptions about lexical support's effectiveness.
This paper describes the participation of HULAT2-UC3M in the Spanish track of MER-TRANS 2026, a shared task on multilingual Easy-to-Read translation. Three fully automatic Spanish runs were submitted. RUN1 and RUN2 used a LangGraph-based multi-agent workflow combining Gemini 2.5 Flash and RigoChat-7B-v2, parallel generation strategies, internal quality signals, Event-Condition-Action routing, controlled editing and traceable decisions. RUN1 used the base workflow, while RUN2 activated an additional lexical-support layer based on a glossary and lexical resources. RUN3 was a RigoChat-based generate-evaluate-regenerate baseline with prompt engineering and LoRA-based adaptation. The official leaderboard reports BLEU-Orig, BLEU-Gold, SARI and BERTScore. During development, additional internal signals were also inspected, including semantic fidelity, readability, lexical simplicity, syntactic clarity and factual consistency. According to official SARI, RUN1 was the best HULAT2 run, with 44.0543 points, followed by RUN2 with 43.1049 and RUN3 with 38.5136. These results indicate that, in this task setting, signal-guided multi-agent routing outperformed the linear regeneration baseline. They also show that adding lexical support did not automatically improve reference-based scores. Further segment-level and document-level analysis are required to assess readability, factual consistency and user-oriented adequacy.
