OOIR: Observatory of International Research

Papers

(The H4-Index of Transactions of the Association for Computational Linguistics is 33. 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 2022-08-01 to 2026-08-01.)

Article	Citations
Persona-Aware Alignment Framework for Personalized Dialogue Generation	1127
Overcoming Source Object Grounding for Semantic Image Editing	355
From Robustness to Improved Generalization and Calibration in Pre-trained Language Models	330
Segmentation-Free Streaming Machine Translation	293
The Ethics of Automating Legal Actors	191
M o N a C o : More Natural and Complex Question	130
How to Select Datapoints for Efficient Human Evaluation of NLG Models?	123
KEFT: Knowledge-Enhanced Fine-Tuning for Large Language Models in Domain-Specific Question Answering	100
DARE: Diverse Visual Question Answering with Robustness Evaluation	98
Cross-functional Analysis of Generalization in Behavioral Learning	92
Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing	87
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection	85
Data Foundations of Long-Context Language Models: A Survey	83
Transformers for Tabular Data Representation: A Survey of Models and Applications	80
State of What Art? A Call for Multi-Prompt LLM Evaluation	78
Erasure of Unaligned Attributes from Neural Representations	75
Safety-Potential Pruning for Enhancing Safety Prompts Against VLM Jailbreaking Without Retraining	74
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval	71
KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?	65
Citation Failure: Definition, Analysis and Efficient Mitigation	62
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates	58
Revisiting Meta-evaluation for Grammatical Error Correction	58
Bridging the Gap between Synthetic and Natural Questions via Sentence Decomposition for Semantic Parsing	54
Do Multi-Document Summarization Models Synthesize?	53
Federated Learning for Exploiting Annotators’ Disagreements in Natural Language Processing	52

Investigating Adversarial Trigger Transfer in Large Language Models	51
Context-Aware Machine Translation with Source Coreference Explanation	43
Benchmarking the Generation of Fact Checking Explanations	42
Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation	38
Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations	38
Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators	35
Literally Concrete or Figuratively Abstract? Multilingual Concreteness Norms for Verb-Object Expressions	35
DEAR: Disentangled Event-Agnostic Representation Learning for Early Fake News Detection	33