OOIR: Observatory of International Research

Papers

(The H4-Index of Transactions of the Association for Computational Linguistics is 35. 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 2022-01-01 to 2026-01-01.)

Article	Citations
Overcoming Source Object Grounding for Semantic Image Editing	539
From Robustness to Improved Generalization and Calibration in Pre-trained Language Models	258
KEFT: Knowledge-Enhanced Fine-Tuning for Large Language Models in Domain-Specific Question Answering	219
DARE: Diverse Visual Question Answering with Robustness Evaluation	218
Persona-Aware Alignment Framework for Personalized Dialogue Generation	195
Cross-functional Analysis of Generalization in Behavioral Learning	133
How to Select Datapoints for Efficient Human Evaluation of NLG Models?	99
Segmentation-Free Streaming Machine Translation	99
The Ethics of Automating Legal Actors	97
State of What Art? A Call for Multi-Prompt LLM Evaluation	96
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection	93
Transformers for Tabular Data Representation: A Survey of Models and Applications	92
The Flores-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation	78
Erasure of Unaligned Attributes from Neural Representations	77
A Survey of Text Games for Reinforcement Learning Informed by Natural Language	75
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval	69
Revisiting Meta-evaluation for Grammatical Error Correction	68
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates	60
A Survey on Automated Fact-Checking	59
Bridging the Gap between Synthetic and Natural Questions via Sentence Decomposition for Semantic Parsing	58
Learning English with Peppa Pig	57
Do Multi-Document Summarization Models Synthesize?	56
Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval	55
DEAR: Disentangled Event-Agnostic Representation Learning for Early Fake News Detection	52
Uncertainty Estimation and Reduction of Pre-trained Models for Text Regression	50

Benchmarking the Generation of Fact Checking Explanations	49
Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation	49
Federated Learning for Exploiting Annotators’ Disagreements in Natural Language Processing	47
Context-Aware Machine Translation with Source Coreference Explanation	45
Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations	43
Time-Aware Language Models as Temporal Knowledge Bases	42
mtRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems	42
How to Dissect a Muppet: The Structure of Transformer Embedding Spaces	39
Few-Shot Multilingual Open-Domain QA from Five Examples	37
Scientia Potentia Est—On the Role of Knowledge in Computational Argumentation	36