Pith. sign in

REVIEW 5 cited by

Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.17080 v1 pith:FNOSBMX2 submitted 2025-06-20 cs.CL cs.AI

classification cs.CLcs.AI
keywords translationgeneral-purposecapabilitiesmodelsmultilingualperformanceinstruction-followingllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Fine-tuning pretrained LLMs has been shown to be an effective strategy for reaching state-of-the-art performance on specific tasks like machine translation. However, this process of adaptation often implies sacrificing general-purpose capabilities, such as conversational reasoning and instruction-following, hampering the utility of the system in real-world applications that require a mixture of skills. In this paper, we introduce Tower+, a suite of models designed to deliver strong performance across both translation and multilingual general-purpose text capabilities. We achieve a Pareto frontier between translation specialization and multilingual general-purpose capabilities by introducing a novel training recipe that builds on Tower (Alves et al., 2024), comprising continued pretraining, supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. At each stage of training, we carefully generate and curate data to strengthen performance on translation as well as general-purpose tasks involving code generation, mathematics problem solving, and general instruction-following. We develop models at multiple scales: 2B, 9B, and 72B. Our smaller models often outperform larger general-purpose open-weight and proprietary LLMs (e.g., Llama 3.3 70B, GPT-4o). Our largest model delivers best-in-class translation performance for high-resource languages and top results in multilingual Arena Hard evaluations and in IF-MT, a benchmark we introduce for evaluating both translation and instruction-following. Our findings highlight that it is possible to rival frontier models in general capabilities, while optimizing for specific business domains, such as translation and localization.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The Role of Disfluencies in Speech Translation

    cs.CL 2026-08 conditional novelty 6.0 of 10

    Current speech translation systems delete disfluencies, and false starts and self-repairs cause most translation-quality loss, as shown by a new eight-language benchmark.

  2. Learning to Translate Ambiguous Terminology by Preference Optimization on Post-Edits

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Masked preference optimization on human post-edits teaches an LLM translator to pick the contextually correct term among many valid dictionary options, improving term accuracy from 53.7% to 56.3% on English-German.

  3. Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models

    cs.CL 2026-02 conditional novelty 5.0 of 10

    Open 12B multilingual translator MiLMMT-46, trained with up to 3B tokens of parallel data per language plus ~100K curated instruction pairs, matches proprietary systems on FLORES+ and WMT24++.

  4. $M^2PO$: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation

    cs.CL 2025-10 reject novelty 5.0 of 10

    M2PO combines a QE-plus-alignment reward with a dynamic curriculum and multi-pair DPO loss, and reports WMT21-22 gains for a 7B translation model, but the abstract's WMT23/24 9B parity claims are unsupported.

  5. Hunyuan-MT Technical Report

    cs.CL 2025-09 conditional novelty 5.0 of 10

    Hunyuan-MT and Chimera, a 7B open-source translation model and its multi-candidate fusion variant, claim state-of-the-art multilingual translation including Mandarin to minority languages, with open weights.

Pith tools