# It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning

arXiv: https://arxiv.org/abs/2106.12066 · HTML: https://mlsanity.com/paper/2106.12066/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 22 Jun 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning](https://mlsanity.com/paper/2005.00333/) (2020)
- [Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges](https://mlsanity.com/paper/1907.05019/) (2019)
- [A Simple Method for Commonsense Reasoning](https://mlsanity.com/paper/1806.02847/) (2018)
- [A Survey Of Cross-lingual Word Embedding Models](https://mlsanity.com/paper/1706.04902/) (2017)
- [Finding Universal Grammatical Relations in Multilingual BERT](https://mlsanity.com/paper/2005.04511/) (2020)
- [RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark](https://mlsanity.com/paper/2010.15925/) (2020)
- [Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2005.04816/) (2020)
- [Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing](https://mlsanity.com/paper/1909.06775/) (2019)
- [A Surprisingly Robust Trick for Winograd Schema Challenge](https://mlsanity.com/paper/1905.06290/) (2019)
- [Contrastive Self-Supervised Learning for Commonsense Reasoning](https://mlsanity.com/paper/2005.00669/) (2020)
- [Attention Is (not) All You Need for Commonsense Reasoning](https://mlsanity.com/paper/1905.13497/) (2019)

## Built on by (most cited first, 30 of 69)

- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence](https://mlsanity.com/paper/2404.05892/) (2024)
- [mGPT: Few-Shot Learners Go Multilingual](https://mlsanity.com/paper/2204.07580/) (2022)
- [Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities](https://mlsanity.com/paper/2404.17790/) (2024)
- [BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting](https://mlsanity.com/paper/2212.09535/) (2022)
- [A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models](https://mlsanity.com/paper/2309.11674/) (2023)
- [Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation](https://mlsanity.com/paper/2305.15011/) (2023)
- [PolyLM: An Open Source Polyglot Large Language Model](https://mlsanity.com/paper/2307.06018/) (2023)
- [AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model](https://mlsanity.com/paper/2208.01448/) (2022)
- [LLM-powered Data Augmentation for Enhanced Cross-lingual Performance](https://mlsanity.com/paper/2305.14288/) (2023)
- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages](https://mlsanity.com/paper/2407.05975/) (2024)
- [Enhancing Multilingual LLM Pretraining with Model-Based Data Selection](https://mlsanity.com/paper/2502.10361/) (2025)
- [Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment](https://mlsanity.com/paper/2311.08089/) (2023)
- [Effectively Compress KV Heads for LLM](https://mlsanity.com/paper/2406.07056/) (2024)
- [P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs](https://mlsanity.com/paper/2411.09116/) (2024)
- [Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning](https://mlsanity.com/paper/2506.11300/) (2025)
- [Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization](https://mlsanity.com/paper/2502.19261/) (2025)
- [Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning](https://mlsanity.com/paper/2507.05418/) (2025)
- [Rewriting Pre-Training Data Boosts LLM Performance in Math and Code](https://mlsanity.com/paper/2505.02881/) (2025)
- [Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2406.12354/) (2024)
- [Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization](https://mlsanity.com/paper/2508.04796/) (2025)
- [Multilingual Language Model Pretraining using Machine-translated Data](https://mlsanity.com/paper/2502.13252/) (2025)
- [EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models](https://mlsanity.com/paper/2409.17892/) (2024)
- [TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning](https://mlsanity.com/paper/2404.19597/) (2024)
- [Agent Skill Acquisition for Large Language Models via CycleQD](https://mlsanity.com/paper/2410.14735/) (2024)
- [Large Vocabulary Size Improves Large Language Models](https://mlsanity.com/paper/2406.16508/) (2024)
- [TokAlign: Efficient Vocabulary Adaptation via Token Alignment](https://mlsanity.com/paper/2506.03523/) (2025)
- [Investigating Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions?](https://mlsanity.com/paper/2402.13703/) (2024)

## Abstract (arXiv)

Commonsense reasoning is one of the key problems in natural language processing, but the relative scarcity of labeled data holds back the progress for languages other than English. Pretrained cross-lingual models are a source of powerful language-agnostic representations, yet their inherent reasoning capabilities are still actively studied. In this work, we design a simple approach to commonsense reasoning which trains a linear classifier with weights of multi-head attention as features. To evaluate this approach, we create a multilingual Winograd Schema corpus by processing several datasets from prior work within a standardized pipeline and measure cross-lingual generalization ability in terms of out-of-sample performance. The method performs competitively with recent supervised and unsupervised approaches for commonsense reasoning, even when applied to other languages in a zero-shot manner. Also, we demonstrate that most of the performance is given by the same small subset of attention heads for all studied languages, which provides evidence of universal reasoning capabilities in multilingual encoders.