arXiv Computation and Language

Beyond Accuracy: What Language-Subspace Interventions Capture, Remove, and Improve

The paper investigates language‑subspace interventions designed to enhance multilingual reasoning by removing language‑related components from mid‑layer activations. Using MATH and MGSM datasets on four open‑weight LLMs, the authors examine whether these subspaces capture translation variation, whether projecting them out eliminates language information, and whether they improve accuracy without harming response language. Results show that the subspaces capture substantial translation variation but do not fully remove language signals, and that interventions can boost accuracy at the cost of language fidelity, highlighting the need to evaluate more than just accuracy.

arXiv AI

Oct 12

The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs

The paper investigates how visual interventions—training‑free edits applied to multimodal large language models—affect hallucinations and prediction quality. By applying a visual‑residual edit across successive decoder layers and matching its RMS strength, the authors identify an Evidence Anchoring Boundary (EAB) where the intervention’s influence drops sharply; effects before the EAB are 13.78–26.10× larger than after it. They further compare counterfactual subtraction across different question types and introduce calibrated selective routing, which only alters predictions when calibration supports an intervention, improving attribute accuracy by 1.56–1.81 percentage points while avoiding the harms of universal subtraction.

By Qiji Zhou, Junyi Hu, Peiyu Wang, Yue Zhang

llms multimodal safety

arXiv AI

Jul 22

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.

By Alexander Manev

llms reinforcement-learning robotics benchmarks safety

arXiv Computation and Language

Oct 19

Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal

arXiv:2610.23807v1 Announce Type: new Abstract: While deriving text embeddings directly from frozen LLMs has emerged as a promising direction, existing methods focus almost exclusively on English, le...

By Ailiang Lin, Zhuoyun Li, Yusong Wang, Keyu Mao, Kotaro Funakoshi, Manabu Okumura

llms rag

arXiv Computation and Language

Aug 27

Rethinking the Multilingual Reasoning Gap with Layer Swap

The study investigates the performance gap between native-language reasoning and English-pivoted reasoning in large language models. By creating extensive multilingual reasoning datasets and fine‑tuning specialists on Qwen/Qwen3-8B-Base, the authors find that the native reasoning gap is much smaller (1.9–3.5%) than previously reported. They analyze weight‑space changes, discover a language‑agnostic reasoning core in the middle layers, and propose a Layer Swap technique that transfers these mid‑layer updates from an English specialist to native specialists, effectively closing most of the gap while maintaining native chain‑of‑thought output.

By Maxence Lasbordes, Am\'elie Chatelain, Djam\'e Seddah

llms fine-tuning

arXiv Computation and Language

Oct 5

Specializing Without Forgetting: Analyzing Knowledge Preservation in Multilingual Model Adaptation

arXiv:2606.00284v2 Announce Type: replace Abstract: While continual pretraining (CPT) is a practical way to extend large language models to new languages, na\"ive finetuning often erodes existing cap...

By Sanchit Ahuja, Terra Blevins

llms fine-tuning

arXiv AI

Jul 8

Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs

arXiv:2607. 06327v1 Announce Type: cross Abstract: Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English.

By Andrea Alfarano, Andrea Bacciu, Saab Mansour, Amin Mantrach, Marcello Federico

llms rag

arXiv AI

Sep 30

What Does Post-Training Change in Multilingual Reasoning?

arXiv:2609.37104v1 Announce Type: cross Abstract: Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a c...

By Hongyang Li, Xiao Li, Caesar Wu, Gr\'egoire Danoy, Pascal Bouvry

reinforcement-learning fine-tuning

arXiv AI

Sep 30

Beyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning

arXiv:2609.37066v1 Announce Type: cross Abstract: Post-training is central to mathematical reasoning in modern large language models (LLMs), but endpoint pass@1 alone underidentifies what has changed...

By Hongyang Li, Yiming Zhu, Xiao Li, Caesar Wu, Said Mammar, Pascal Bouvry

llms fine-tuning efficiency

arXiv AI

Sep 30

LLMs are not stochastic parrots: Evidence for meaning-mediated abstraction from conlang-like tasks

arXiv:2609.34187v2 Announce Type: replace-cross Abstract: The strong version of the stochastic parrot argument claims that, although large language models (LLMs) may exceed rote regurgitation, they c...

By Julia Witte Zimmerman, Calla G. Beauregard, Tabia Tanzin Prama, Parisa Suchdev, Kathryn Cramer, Elisabeth Kollrack

llms

arXiv Computation and Language

Sep 1

Unlocking Fine-Grained Translation Quality Estimation in LRMs through Mutually Boosting Implicit and Explicit Reasoning

arXiv:2605.31378v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) still struggle with fine-grained translation quality estimation (QE), even with long reasoning chains. We argue that...

By Renfei Dang, Xinye Wang, Zhejian Lai, Weilu Xu, Shimin Tao, Daimeng Wei, Min Zhang, Shujian Huang

reinforcement-learning fine-tuning

Hugging Face Trending Papers

Oct 6

U-Space: Uncovering When and Why Uncertainty Arises in Language Models

Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust an individual answer...

llms benchmarks safety

arXiv Machine Learning

Aug 5

M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models

arXiv:2608. 03803v1 Announce Type: cross Abstract: Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task _in_ a language rather than whether it commands the language itself, conflating fluency with proficiency.

By Tom\'a\v{s} Burkert, Angelika Peljak-{\L}api\'nska, David Zelen\'y

llms nlp benchmarks safety

Related stories