OOIR: Observatory of International Research

Papers

(The H4-Index of Transactions of the Association for Computational Linguistics is 30. 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 2022-05-01 to 2026-05-01.)

Article	Citations
Persona-Aware Alignment Framework for Personalized Dialogue Generation	809
Overcoming Source Object Grounding for Semantic Image Editing	303
From Robustness to Improved Generalization and Calibration in Pre-trained Language Models	287
Cross-functional Analysis of Generalization in Behavioral Learning	255
Segmentation-Free Streaming Machine Translation	143
The Ethics of Automating Legal Actors	111
M o N a C o : More Natural and Complex Question	101
DARE: Diverse Visual Question Answering with Robustness Evaluation	91
KEFT: Knowledge-Enhanced Fine-Tuning for Large Language Models in Domain-Specific Question Answering	90
State of What Art? A Call for Multi-Prompt LLM Evaluation	83
How to Select Datapoints for Efficient Human Evaluation of NLG Models?	81
Transformers for Tabular Data Representation: A Survey of Models and Applications	77
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection	74
Erasure of Unaligned Attributes from Neural Representations	68
Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval	65
Revisiting Meta-evaluation for Grammatical Error Correction	64
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates	62
Bridging the Gap between Synthetic and Natural Questions via Sentence Decomposition for Semantic Parsing	61
Context-Aware Machine Translation with Source Coreference Explanation	56
Benchmarking the Generation of Fact Checking Explanations	53
DEAR: Disentangled Event-Agnostic Representation Learning for Early Fake News Detection	45
Investigating Adversarial Trigger Transfer in Large Language Models	45
Do Multi-Document Summarization Models Synthesize?	41
Frame Representation Hypothesis: Multi-Token LLM Interpretability and Concept-Guided Text Generation	39
Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval	39

Federated Learning for Exploiting Annotators’ Disagreements in Natural Language Processing	39
mtRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems	38
Accelerating Language Model Workflows with Prompt Choreography	35
Learning More from Mixed Emotions: A Label Refinement Method for Emotion Recognition in Conversations	35
Few-Shot Multilingual Open-Domain QA from Five Examples	35
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation	30