---
title: "Sebastian Ruder — papers, page 2 · University of Washington"
description: "Sebastian Ruder, University of Washington: 31 papers on Elamur Research (2017–2026), h-index 49 — affiliations, topics, co-authors and…"
canonical: "https://research.elamur.ai/free/en/authors/sebastian-ruder/page/2/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/sebastian-ruder/page/2/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Sebastian Ruder](https://md.research.elamur.ai/free/en/authors/sebastian-ruder/) / page 2

# Sebastian Ruder · page 2

31 papers in our library · 2017–2026 · page 2 of 2

[The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/sebastian-ruder/)

## Papers

The most cited first (OpenAlex and our library).

[← prev](https://md.research.elamur.ai/free/en/authors/sebastian-ruder/) [1](https://md.research.elamur.ai/free/en/authors/sebastian-ruder/) **2**

26. **[Understanding and Mitigating Language Confusion in LLMs](https://md.research.elamur.ai/free/en/papers/marchisio-2024-understanding-mitigating-language-confusion-llms/)** *(2024 · 57 citations)* Large language models often fail to answer in the language the user wants. They may switch entirely to English, mix lines in different languages, or insert stray foreign words. The authors call this error "language confusion" and present the Language Confusion Benchmark (LCB) to measure it across 15 typologically…
27. **[QAmeleon: Multilingual QA with Only 5 Examples](https://md.research.elamur.ai/free/en/papers/agrawal-2023-qameleon-multilingual-qa-only-5/)** *(2023 · 45 citations)* Extractive question answering datasets are large mainly for English, so QA systems in other languages usually depend on zero-shot transfer or machine-translated training data.
28. **[M-RewardBench: Evaluating Reward Models in Multilingual Settings](https://md.research.elamur.ai/free/en/papers/gureja-2025-m-rewardbench-evaluating-reward-models/)** *(2025 · 28 citations)* Reward models (RMs) steer LLM alignment, but they are built and tested almost entirely in English. This paper asks how well RMs judge responses in other languages. The authors built M-RewardBench, a benchmark of about 2.87k preference instances spanning 23 typologically varied languages, including Ukrainian.
29. **[AL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal Arabic](https://md.research.elamur.ai/free/en/papers/robinson-2025-al-qasida-analyzing-llm-quality/)** *(2025 · 14 citations)* Large language models handle Modern Standard Arabic (MSA) well but tend to avoid the regional dialects (DA) that Arabic speakers actually use day to day.
30. **[The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs](https://md.research.elamur.ai/free/en/papers/nawrot-2026-sparse-frontier-sparse-attention-trade/)** *(2026 · 10 citations)* Running Transformer LLMs on long inputs is costly. Prefilling cost grows quadratically with input length, and decoding slows down because each step must read an ever-larger KV cache. Many sparse attention techniques promise savings, but it has been unclear how much accuracy they give up in return. The authors present…
31. **[Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RL](https://md.research.elamur.ai/free/en/papers/wu-2026-parallel-sft-improving-zero-shot/)** *(2026)* LLMs write code well in popular programming languages, but weaker data coverage hurts them in less common ones.

[← prev](https://md.research.elamur.ai/free/en/authors/sebastian-ruder/) [1](https://md.research.elamur.ai/free/en/authors/sebastian-ruder/) **2**