# Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations

arXiv: https://arxiv.org/abs/2506.16678 · HTML: https://mlsanity.com/paper/2506.16678/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 55 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [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)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [SimLex-999: Evaluating Semantic Models with (Genuine) Similarity Estimation](https://mlsanity.com/paper/1408.3456/) (2014)
- [Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?](https://mlsanity.com/paper/2005.00719/) (2020)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2504.02768/) (2025)
- [CausalGym: Benchmarking causal interpretability methods on linguistic tasks](https://mlsanity.com/paper/2402.12560/) (2024)
- [Characterizing Intrinsic Compositionality in Transformers with Tree Projections](https://mlsanity.com/paper/2211.01288/) (2022)
- [What if This Modified That? Syntactic Interventions via Counterfactual Embeddings](https://mlsanity.com/paper/2105.14002/) (2021)
- [Probing for Incremental Parse States in Autoregressive Language Models](https://mlsanity.com/paper/2211.09748/) (2022)
- [RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2406.19232/) (2024)
- [Introducing Orthogonal Constraint in Structural Probes](https://mlsanity.com/paper/2012.15228/) (2020)
- [TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2506.13487/) (2025)
- [Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages](https://mlsanity.com/paper/2305.02215/) (2023)

## Built on by (most cited first, 7 of 7)

- [Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations](https://mlsanity.com/paper/2601.03779/) (2026)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)
- [From Lemmas to Dependencies: What Signals Drive Light Verbs Classification?](https://mlsanity.com/paper/2602.04127/) (2026)
- [Linear representations of grammaticality in neural language models](https://mlsanity.com/paper/2607.15175/) (2026)
- [Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs](https://mlsanity.com/paper/2602.15846/) (2026)
- [Child-directed speech facilitates production, not comprehension, in BabyLMs](https://mlsanity.com/paper/2606.01045/) (2026)
- [Encoded but Not Decoded: Layer-Localized Evidence for a Three-Level Gap in LLM Syntax](https://mlsanity.com/paper/2609.29848/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) exhibit a robust mastery of syntax when processing and generating text. While this suggests internalized understanding of hierarchical syntax and dependency relations, the precise mechanism by which they represent syntactic structure is an open area within interpretability research. Probing provides one way to identify the mechanism of syntax being linearly encoded in activations, however, no comprehensive study has yet established whether a model's probing accuracy reliably predicts its downstream syntactic performance. Adopting a "mechanisms vs. outcomes" framework, we evaluate 32 open-weight transformer models and find that syntactic features extracted via probing fail to predict outcomes of targeted syntax evaluations across English linguistic phenomena. Our results highlight a substantial disconnect between latent syntactic representations found via probing and observable syntactic behaviors in downstream tasks.