Pith. sign in

REVIEW 8 cited by

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2307.16039 v2 pith:3YGJXA53 submitted 2023-07-29 cs.CL cs.LG

Viet Dac Lai , Chien Van Nguyen , Nghia Trung Ngo , Thuat Nguyen , Franck Dernoncourt , Ryan A. Rossi , Thien Huu Nguyen This is my paper
classification cs.CLcs.LG
keywords llmslanguagesinstructionmultiplerlhfinstruction-tunedmodelsokapi
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A key technology for the development of large language models (LLMs) involves instruction tuning that helps align the models' responses with human expectations to realize impressive learning abilities. Two major approaches for instruction tuning characterize supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), which are currently applied to produce the best commercial LLMs (e.g., ChatGPT). To improve the accessibility of LLMs for research and development efforts, various instruction-tuned open-source LLMs have also been introduced recently, e.g., Alpaca, Vicuna, to name a few. However, existing open-source LLMs have only been instruction-tuned for English and a few popular languages, thus hindering their impacts and accessibility to many other languages in the world. Among a few very recent work to explore instruction tuning for LLMs in multiple languages, SFT has been used as the only approach to instruction-tune LLMs for multiple languages. This has left a significant gap for fine-tuned LLMs based on RLHF in diverse languages and raised important questions on how RLHF can boost the performance of multilingual instruction tuning. To overcome this issue, we present Okapi, the first system with instruction-tuned LLMs based on RLHF for multiple languages. Okapi introduces instruction and response-ranked data in 26 diverse languages to facilitate the experiments and development of future multilingual LLM research. We also present benchmark datasets to enable the evaluation of generative LLMs in multiple languages. Our experiments demonstrate the advantages of RLHF for multilingual instruction over SFT for different base models and datasets. Our framework and resources are released at https://github.com/nlp-uoregon/Okapi.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI

    cs.AI 2025-08 conditional novelty 6.0 of 10

    Geo-alignment means matching an AI system's output distribution to the locally appropriate distribution for each query, location, and time, and the paper argues spatial structure makes that target learnable.

  2. FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

    cs.CL 2025-06 conditional novelty 6.0 of 10

    An adaptive, per-language data filtering and deduplication pipeline produces multilingual LLM pre-training corpora that beat prior public datasets on 11 of 14 evaluated languages, and a 20TB, 1,868 language-script dat...

  3. The Emergence of Abstract Thought in Large Language Models Beyond Any Language

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Across 20 open LLMs, shared multilingual neurons grow in number and per-neuron importance over release generations, which the authors interpret as evidence of language-agnostic abstract thought and use to guide neuron...

  4. CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention

    cs.CL 2025-05 conditional novelty 6.0 of 10

    CausalAbstain filters multilingual self-feedback by comparing how much it changes the model's abstention decision, improving abstention accuracy over baselines on two benchmarks.

  5. TASE: Token Awareness and Structured Evaluation for Multilingual Language Models

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    TASE benchmark shows LLMs lag humans on token-level and structural language tasks across Chinese, English, and Korean despite strong high-level performance.

  6. Text2Cypher Across Languages: Evaluating and Finetuning LLMs

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A new multilingual Text2Cypher benchmark shows LLMs rank English highest, Spanish next, and Turkish lowest, and multilingual finetuning narrows the language gap more than English-only finetuning.

  7. The AI Language Proficiency Monitor -- Tracking the Progress of LLMs on Multilingual Benchmarks

    cs.CL 2025-07 conditional novelty 4.0 of 10

    A continuously updated multilingual benchmark dashboard aggregates existing tasks to rank LLMs across up to 200 languages.

  8. The Multilingual Divide and Its Impact on Global AI Safety

    cs.AI 2025-05 conditional novelty 3.0 of 10

    The language gap in AI models creates safety disparities across languages, and closing it requires funding multilingual datasets, transparency, and research.

Pith tools