OOIR: Observatory of International Research

Papers

(The TQCC of Transactions of the Association for Computational Linguistics is 6. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-04-01 to 2025-04-01.)

Article	Citations
QAmeleon: Multilingual QA with Only 5 Examples	158
Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models	150
Neuron-level Interpretation of Deep NLP Models: A Survey	96
CreoleVal: Multilingual Multitask Benchmarks for Creoles	81
Segmentation-Free Streaming Machine Translation	80
A Neighborhood Framework for Resource-Lean Content Flagging	74
On Graph-based Reentrancy-free Semantic Parsing	72
Explicitly Representing Syntax Improves Sentence-to-Layout Prediction of Unexpected Situations	64
Evaluating Transformer Models and Human Behaviors on Chinese Character Naming	60
Cross-functional Analysis of Generalization in Behavioral Learning	59
Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation	55
A Cross-Linguistic Pressure for Uniform Information Density in Word Order	51
Hallucinations in Large Multilingual Translation Models	42
Multi-task Active Learning for Pre-trained Transformer-based Models	38
Direct Speech Translation for Automatic Subtitling	32
The Impact of Word Splitting on the Semantic Content of Contextualized Word Representations	30
OpenFact: Factuality Enhanced Open Knowledge Extraction	27
Tracking Brand-Associated Polarity-Bearing Topics in User Reviews	26
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference	26
Reasoning over Public and Private Data in Retrieval-Based Systems	23
Deuce: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning	22
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning	22
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers	22
Scope Ambiguities in Large Language Models	21
Efficient Long-Text Understanding with Short-Text Models	21

Filtered Corpus Training (FiCT) Shows that Language Models Can Generalize from Indirect Evidence	21
The Ethics of Automating Legal Actors	21
How Often Are Errors in Natural Language Reasoning Due to Paraphrastic Variability?	17
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection	17
Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization	16
Geographic Adaptation of Pretrained Language Models	16
FINCH: Prompt-guided Key-Value Cache Compression for Large Language Models	16
Addressing Topic Leakage in Cross-Topic Evaluation for Authorship Verification	16
Interactive Machine Teaching by Labeling Rules and Instances	15
How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure	15
A Survey on Model Compression for Large Language Models	14
ByT5: Towards a Token-Free Future with Pre-trained Byte-to-Byte Models	14
Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision	14
Transformers for Tabular Data Representation: A Survey of Models and Applications	14
A Survey on Cross-Lingual Summarization	13
Erasure of Unaligned Attributes from Neural Representations	13
State of What Art? A Call for Multi-Prompt LLM Evaluation	13
Abstractive Meeting Summarization: A Survey	13
Czech Grammar Error Correction with a Large and Diverse Corpus	13
Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?	13
`Holmes` ⌕ A Benchmark to Assess the Linguistic Competence of Language Models	11
Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design	11
IndoCulture: Exploring Geographically Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces	10
An Efficient Self-Supervised Cross-View Training For Sentence Embedding	10
`PASTA`: A Dataset for Modeling PArticipant STAtes in Narratives	10
Minimum Description Length Recurrent Neural Networks	10
Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights	9
OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure	9
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation	9
Improving Multitask Retrieval by Promoting Task Specialization	9
A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction	9
What Do Self-Supervised Speech Models Know About Words?	8
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks	8
When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs	8
Multi-level Shared Knowledge Guided Learning for Knowledge Graph Completion	8
What Formal Languages Can Transformers Express? A Survey	7
Addressing the Binning Problem in Calibration Assessment through Scalar Annotations	7
Predicting Document Coverage for Relation Extraction	7
Visually Grounded Speech Models Have a Mutual Exclusivity Bias	7
Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations	7
Revisiting Meta-evaluation for Grammatical Error Correction	6
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval	6
Word Acquisition in Neural Language Models	6
Supervised Gradual Machine Learning for Aspect-Term Sentiment Analysis	6
MACSum: Controllable Summarization with Mixed Attributes	6
The Parallelism Tradeoff: Limitations of Log-Precision Transformers	6
ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI	6
FeelingBlue: A Corpus for Understanding the Emotional Connotation of Color in Context	6
Rank-Aware Negative Training for Semi-Supervised Text Classification	6