OOIR: Observatory of International Research

Papers

(The H4-Index of Transactions of the Association for Computational Linguistics is 31. 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 2022-06-01 to 2026-06-01.)

Article	Citations
Persona-Aware Alignment Framework for Personalized Dialogue Generation	868
Overcoming Source Object Grounding for Semantic Image Editing	317
From Robustness to Improved Generalization and Calibration in Pre-trained Language Models	299
Cross-functional Analysis of Generalization in Behavioral Learning	268
Segmentation-Free Streaming Machine Translation	152
The Ethics of Automating Legal Actors	113
M o N a C o : More Natural and Complex Question	111
How to Select Datapoints for Efficient Human Evaluation of NLG Models?	95
KEFT: Knowledge-Enhanced Fine-Tuning for Large Language Models in Domain-Specific Question Answering	93
State of What Art? A Call for Multi-Prompt LLM Evaluation	84
DARE: Diverse Visual Question Answering with Robustness Evaluation	82
Transformers for Tabular Data Representation: A Survey of Models and Applications	79
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection	76
Erasure of Unaligned Attributes from Neural Representations	70
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval	68
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates	68
Revisiting Meta-evaluation for Grammatical Error Correction	66
Bridging the Gap between Synthetic and Natural Questions via Sentence Decomposition for Semantic Parsing	63
Context-Aware Machine Translation with Source Coreference Explanation	59
Benchmarking the Generation of Fact Checking Explanations	54
Investigating Adversarial Trigger Transfer in Large Language Models	47
Do Multi-Document Summarization Models Synthesize?	47
Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval	45
Federated Learning for Exploiting Annotators’ Disagreements in Natural Language Processing	44
mtRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems	43

Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation	40
Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations	40
DEAR: Disentangled Event-Agnostic Representation Learning for Early Fake News Detection	38
Few-Shot Multilingual Open-Domain QA from Five Examples	36
Adversarial Defense without Adversarial Defense : Enhancing Language Model Robustness via Instance-level Principal Component Removal	35
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation	32
Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art	31