Large language models show strong cross‑lingual abilities, but previous studies have examined them only at isolated training points. This work pretrains a 1.7B multilingual model on nine languages, recording checkpoints at fine granularity to track translation development. Using word‑level translation and a new dataset, the authors find that early learning is dominated by token‑level copying and surface similarities, while later stages involve more general translation mechanisms and refined copying.
By Felicia K\"orner, Maria Matveev, Florian Eichin, Gitta Kutyniok, Barbara Plank, Michael A. Hedderich
arXiv:2604. 03532v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult.
By Sing Hieng Wong, Hassan Sajjad, A. B. Siddique
arXiv:2608. 12334v1 Announce Type: cross Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood.
By Arnav Srivastav
The paper investigates how trigger-based backdoors function in large language models by using sparse autoencoders (SAEs) to identify feature directions across layers and transformer components. In a controlled experiment, 1B and 8B models were made to continue English prompts in French or German when presented with fixed trigger sequences. The study finds that different SAE feature directions correspond to trigger detection, residual-stream propagation, and language tracking, with residual-stream features being most effective for controlling the backdoor behavior.
By Wissam Antoun, Francis Kulumba, Th\'eo Lasnier, Beno\^it Sagot, Djam\'e Seddah
The paper investigates how multilingual large language models can unintentionally switch languages during generation. It compares three techniques—ValSel, FreqSel, and AnnSel—for pinpointing latent variables that control language choice in cross‑layer transcoders. Using new multilingual benchmarks and targeted interventions on Gemma‑2‑2B and Qwen3‑4B, the study finds all methods can steer output language, with FreqSel performing best and AnnSel providing interpretable selections via explicit annotations.
By Ryo Mitsuhashi, Sabri Boughorbel, Majd Hawasly
arXiv:2609.08322v1 Announce Type: cross
Abstract: Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is...
By Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen, Josef van Genabith, Koel Dutta Chowdhury
The paper proposes the interlingua hypothesis, suggesting that large language models translate by encoding a source sentence into a latent, task‑agnostic feature space and then decoding a target sentence from that space. Three lines of evidence support this: (1) BLEU variance across language pairs is largely explained by language‑specific competences without pair‑specific interactions; (2) many model components influence both monolingual and translation tasks; and (3) fine‑tuning on monolingual data recovers most translation gains seen with aligned documents. These findings converge to support the hypothesis and point toward new ways to understand and improve LLM translation.
By Jacob Brinton, Jannik Brinkmann, Mark Crovella, Aaron Mueller
The study investigates how exposing large language models to Arabic translations of English benchmark tasks can hide data contamination from standard English-only detection methods. By testing four instruction-tuned models with increasing Arabic exposure, the authors find that traditional probes like TS-Guessing and Min-K%++ fail to detect contamination, yet English performance still improves. They propose a new Translation-Aware Contamination Detection (TACD) method that uses cross-lingual consistency and choice reordering to reveal contamination effects that are otherwise invisible to English-only diagnostics.
By Chaymaa Abbas, Nour Shammaa, Mariette Awad
The paper investigates how multilingual large language models (LLMs) encode and express stereotypes across different languages. By applying linear probing, attribution patching, sparse autoencoders (SAEs), and feature ablation to Llama‑3.1‑8B, Qwen3‑8B, and Gemma‑2‑9B, the authors find that probe performance peaks much earlier than attribution, indicating a separation of 36‑53% of model depth. They observe that only a small fraction (6‑18%) of residual‑stream features exhibit language‑agnostic effects, and none are category‑agnostic, highlighting the need to measure decodability, output influence, and cross‑lingual ablation effects separately.
arXiv:2609.07876v1 Announce Type: cross
Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linea...
By Arjun Patrawala, Jiahai Feng, Erik Jones, Jacob Steinhardt
arXiv:2607. 20596v1 Announce Type: new Abstract: Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested.
By Seonglae Cho, Zekun Wu, Kleyton Da Costa, Rishi Kalra, Ilham Wicaksono, Adriano Koshiyama
arXiv:2606.00356v3 Announce Type: replace
Abstract: Sparse autoencoder (SAE) features are increasingly used to interpret language models, with auto-generated natural-language labels serving as the pr...
By Sripad Karne