The paper introduces a new method for identifying language-specific neurons in multilingual large language models (mLLMs). Unlike previous entropy-based approaches that only consider positive activations, the proposed Distribution-aware Language Neuron selection uses pairwise overlap coefficients of full activation distributions, including negative values, to cluster languages. Experiments on two mLLMs and two held-out corpora show that this method isolates language-specific causal effects more effectively, achieving up to 4.9× higher on-target language damage per neuron while maintaining off-target language performance.
arXiv:2607. 18454v1 Announce Type: cross Abstract: Quantifying the risk of rare failures in language models, such as those triggered by adversarial distribution shifts or very large-scale deployments, requires estimating probabilities far too small for random sampling.
arXiv:2602. 00945v2 Announce Type: replace-cross Abstract: LLMs are multilingual by training, yet their lingua franca is often English, reflecting English language dominance in pretraining.
arXiv:2607. 22699v1 Announce Type: new Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains.
arXiv:2608. 09095v1 Announce Type: new Abstract: Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence.
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.
The study compares an English-only and a bilingual decoder-only model, each 310 M parameters, trained on eight diverse languages while controlling for English exposure, compute, and document overlap. After aligning on shared English vocabulary, the authors find that token embeddings appear similar, but the deeper hidden states used for prediction diverge across models. This hidden‑state mismatch grows through middle transformer layers and persists despite controls, indicating that contextual processing differs between the models. "whyItMatters":"The findings show that embedding alignment can conceal significant internal representation differences, which is crucial for any downstream work that assumes aligned multilingual models are interchangeable."
arXiv:2608. 15448v1 Announce Type: cross Abstract: Large language models increasingly rely on sampling as a driver of their own improvement, making the fidelity of their learned distributions more critical than ever.
arXiv:2607. 05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes.
The paper investigates multilingual confidence calibration in large language models, revealing that non‑English languages are systematically less well calibrated than English. By analyzing internal representations, the authors find that late‑intermediate layers provide a more reliable confidence signal than the final layer, which is biased by English‑centric training. They propose training‑free methods such as Language‑Aware Confidence Ensemble (LACE) to adaptively select optimal layers per language, aiming to improve global equity and trustworthiness of LLMs.
arXiv:2410. 07809v2 Announce Type: replace-cross Abstract: Multilingual instruction tuning (MIT) is challenged by the curse of multilinguality, data scarcity, and high computational cost.
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.
The paper investigates weight‑space merging of independently fine‑tuned multilingual machine translation models. Experiments show that merging is more successful when models share a target language, yet it still cannot match the peak performance of language‑specific checkpoints. When target languages differ, performance drops sharply, and analysis reveals that overlapping neuron activation and incompatible upper‑layer geometries cause these failures.