Papers with probing methods
Does My Representation Capture X? Probe-Ably (2021.acl-demo)
Copied to clipboard
| Challenge: | Probing (or diagnostic classification) has become a popular strategy for investigating whether a given set of intermediate features is present in the representations of neural models. |
| Approach: | They propose to use an extendable probing framework to automate the application of probing methods to the user’s inputs. |
| Outcome: | The proposed framework automates the application of probing methods to the user’s inputs. |
Improving Syntactic Probing Correctness and Robustness with Control Tasks (2023.acl-short)
Copied to clipboard
Weicheng Ma, Brian Wang, Hefan Zhang, Lili Wang, Rolando Coto-Solano, Saeed Hassanpour, Soroush Vosoughi
| Challenge: | Syntactic probing methods are biased by the PLMs’ memorization of common word co-occurrences, even if they do not form syntactical relations. |
| Approach: | They propose to use random word substitution and random label matching to reduce these biases and improve the robustness of syntactic probing methods. |
| Outcome: | The proposed tasks improve probing results and consistency between probing methods and make them more generalizable to unseen text domains. |
LangVAE and LangSpace: Building and Probing for Language Model VAEs (2025.emnlp-demos)
Copied to clipboard
| Challenge: | a novel framework for modular construction of variational autoencoders (VAEs) on pre-trained large language models (LLMs) is presented. |
| Approach: | They propose a modular framework for variational autoencoders on top of pre-trained large language models. |
| Outcome: | The proposed framework can encode pre-trained language models into more compact and semantically disentangled representations. |
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data? (2021.naacl-main)
Copied to clipboard
| Challenge: | Pretraining large (masked) language models over EHR data has yielded consistent performance gains across tasks. |
| Approach: | They propose to use large Transformers to release pretraining models over EHRs . they propose to recover patient names and conditions associated with them . |
| Outcome: | The proposed models recover patient names and conditions associated with patients . the proposed models share the model parameters for use by other researchers . |
Different Speech Translation Models Encode and Translate Speaker Gender Differently (2025.acl-short)
Copied to clipboard
| Challenge: | Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender. |
| Approach: | They propose to use probing methods to assess gender encoding across ST models. |
| Outcome: | The proposed models capture speaker-specific features, including gender, while older models do not . low gender encoding capabilities result in systems’ tendency toward a masculine default, a translation bias that is more pronounced in newer architectures. |
CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing code pre-trained models fail to consider inherent characteristics of codes . Existing methods to interpret code pretrained model fail to take into account inherent characteristics . |
| Approach: | They propose a probing method to quantitatively interpret how CodePTMs attend code structure. |
| Outcome: | The proposed method denoises input code sequences and measures commonality between token-level attention scores and pair-wise distances between corresponding AST nodes. |
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained language models have been successful when finetuned to downstream tasks . however, it is difficult to determine whether the knowledge that finetuning LMs contain is learned during the pretraining or the finetailing process. |
| Approach: | They propose a method to create prompts for a diverse set of tasks using a gradient-guided search. |
| Outcome: | The proposed method performs sentiment analysis and natural language inference without additional parameters and finetuning. |
Can Language Models be Biomedical Knowledge Bases? (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have focused on probing LMs in the general domain but little attention has been given to whether they can be used as domain knowledge bases. |
| Approach: | They propose to use 49K biomedical factual knowledge triples to probe LMs for biomedically . they find that biomedic LM can achieve up to 18.51% Acc@5 on retrieving biomedcial knowledge. |
| Outcome: | The proposed biomedical factual knowledge probing benchmark achieves 18.51% Acc@5 on biomedically-relevant knowledge retrieval. |
Classifier Probes May Just Learn from Linear Context Features (2020.coling-main)
Copied to clipboard
| Challenge: | Current probing methods can help to better estimate the complexity of learning, but not build a foundation for speculations about the nature of the linguistic structure encoded in the learned representations. |
| Approach: | They propose to use token embeddings to test whether probing tasks contain linguistic structure . they argue that current probing methods do not provide enough information to support this hypothesis . |
| Outcome: | The proposed method can be scrutinized and proves that representations encode linguistic structure even without additional linguistic structures. |
X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Language models (LMs) capture factual knowledge by filling in the blanks of cloze-style prompts. |
| Approach: | They propose a code-switching-based method to improve the ability of multilingual LMs to access knowledge and verify its effectiveness on several benchmark languages. |
| Outcome: | The proposed method improves the ability of multilingual LMs to access knowledge and verify its effectiveness on several benchmark languages. |
Supervised and Unsupervised Probing of Shortcut Learning: Case Study on the Emergence and Evolution of Syntactic Heuristics in BERT (2025.findings-acl)
Copied to clipboard
| Challenge: | Contemporary language models (LMs) rely on shortcut learning, using superficial cues that are spuriously correlated with labels. |
| Approach: | They propose to use syntactic heuristics to learn shortcuts in BERT when performing a task in Natural Language Understanding to investigate where these shortcuts emerge, how they evolve and how they impact the latent knowledge of the LM. |
| Outcome: | The proposed model rely on syntactic heuristics when performing a task in Natural Language Understanding. |
Neural reality of argument structure constructions (2022.acl-long)
Copied to clipboard
| Challenge: | lexicalist linguistic theories assume argument structure is predictable from meaning of verbs . construction grammarians propose argument structure constructions distinct from verbs. |
| Approach: | They adapt psycholinguistic studies to probe for the existence of argument structure constructions in Transformer-based language models. |
| Outcome: | The proposed method could be used to probe argument structure constructions in LMs . the study shows that LM learners prefer grouping by construction over verb grouping . |
SPE: Symmetrical Prompt Enhancement for Fact Probing (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work probes PLMs for the extent of factual knowledge through prompts . however, these methods do not consider symmetry of the task: object and subject prediction. |
| Approach: | They propose a continuous prompt-based method that leverages symmetry of the task by constructing symmetrical prompts for subject and object prediction. |
| Outcome: | The proposed method improves on a popular factual probing dataset on lAMA. |
Towards Measuring and Modeling “Culture” in LLMs: A Survey (2024.emnlp-main)
Copied to clipboard
Muhammad Adilazuarda, Sagnik Mukherjee, Pradhyumna Lavania, Siddhant Singh, Alham Aji, Jacki O’Neill, Ashutosh Modi, Monojit Choudhury
| Challenge: | Existing models are biased towards Western, Anglocentric or American cultures, a problem that is arguably detrimental to the performance of LLMs. |
| Approach: | They analyze more than 90 recent papers that aim to study cultural representation and inclusion in large language models. |
| Outcome: | The proposed models are biased towards Western, Anglocentric or American cultures, despite their diversity and their robustness. |
Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models are trained on vast unlabeled data, rich in world knowledge. |
| Approach: | They propose a categorization scheme for factual probing methods based on how inputs, outputs and probed PLMs are adapted . they synthesize insights about knowledge retention and prompt optimization in PLM models and analyze obstacles to adopting them as knowledge bases . |
| Outcome: | The proposed method synthesizes insights about knowledge retention and prompt optimization in PLMs, analyzes obstacles to adopting them as knowledge bases and outline directions for future work. |
Do We Know What LLMs Don’t Know? A Study of Consistency in Knowledge Probing (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for probing knowledge gaps in large language models are inconsistent and inconsistent. |
| Approach: | They propose a process based on input variations and quantitative metrics to evaluate probing methods that are inconsistent on knowledge gaps. |
| Outcome: | The proposed process exposes two dimensions of inconsistency in knowledge gap probing. |
False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work has leveraged probing-based approaches to study the separability of malicious and benign inputs in Large Language Models’ internal representations. |
| Approach: | They propose to use probing-based methods to study separability of malicious and benign inputs in LLMs' internal representations to detect harmful and benign content. |
| Outcome: | The proposed methods show that they learn superficial patterns rather than semantic harmfulness. |
Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work showed limited success in probing numeric values from models’ representations, indicating that these errors can be attributed to the inherent unreliability of distributionally learned embeddings in representing exact quantities. |
| Approach: | They propose a probing technique that decodes numeric values from input embeddings with near-perfect accuracy across a range of open-source LMs. |
| Outcome: | The proposed probing technique decodes numeric values from input embeddings with near-perfect accuracy across a range of open-source LMs. |