OOIR: Observatory of International Research

Papers

(The TQCC of Transactions of the Association for Computational Linguistics is 9. 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
Literally Concrete or Figuratively Abstract? Multilingual Concreteness Norms for Verb-Object Expressions	35
Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators	35
DEAR: Disentangled Event-Agnostic Representation Learning for Early Fake News Detection	33
Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval	32
mtRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems	31
Few-Shot Multilingual Open-Domain QA from Five Examples	30
Adversarial Defense without Adversarial Defense : Enhancing Language Model Robustness via Instance-level Principal Component Removal	29
Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation	28
Accelerating Language Model Workflows with Prompt Choreography	27
PsyMem: Fine-grained Psychological Alignment and Explicit Memory Control for Advanced Role-Playing LLMs	26
Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking	25
To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation	23
Are Triggers Needed for Document-Level Event Extraction?	23
Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art	23
Questions Are All You Need to Train a Dense Passage Retriever	23
An Energy-based Model for Word-level AutoCompletion in Computer-aided Translation	22
Aligned Probing: Relating Toxic Behavior and Model Internals	22
A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese	21
Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models	21
In-N-Out: A Parameter-Level API Graph Dataset for Tool Agents	20
CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset	19
From Explicit to Implicit: A Theoretical Framework and Transfer Method for Preference Internalization in Language Models	19
Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?	19
Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off	18
Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance in Adaptation	18
Conformal Prediction for Natural Language Processing: A Survey	17
CorefInst: Leveraging LLMs for Multilingual Coreference Resolution	17
Prompt Contrastive Transformation: An Enhanced Strategy for Efficient Prompt Transfer in Natural Language Processing	17
Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models	16
Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering	16
Beyond One-Size-Fits-All : Inversion Learning for Highly Effective NLG Evaluation Prompts	16
Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation	16
OrthoEdit: Principled and Stable Knowledge Editing via Orthogonal Subspace Projection	15
CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation	15
Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis	15
InSCIt: Information-Seeking Conversations with Mixed-Initiative Interactions	14
Navigating the Landscape of Hint Generation Research: From the Past to the Future	14
OpenFact: Factuality Enhanced Open Knowledge Extraction	13
Interactive Machine Teaching by Labeling Rules and Instances	13
Localizing Factual Inconsistencies in Attributable Text Generation	13
Efficient Long-Text Understanding with Short-Text Models	12
Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?	12
Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models	12
Objectifying the Subjective: Cognitive Biases in Topic Interpretations	12
Pre-train, Prompt, and Recommendation: A Comprehensive Survey of Language Modeling Paradigm Adaptations in Recommender Systems	12

A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction	12
BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context	12
Sense-specific Historical Word Usage Generation	12
TaxoPro: A Plug-In LoRA-based Cross-Domain Method for Low-Resource Taxonomy Completion	10
NLP Security and Ethics, in the Wild	10
Adding Chocolate to Mint : Mitigating Metric Interference in Machine Translation	10
Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation	10
MENLI: Robust Evaluation Metrics from Natural Language Inference	10
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs	10
Modeling Emotion Dynamics in Song Lyrics with State Space Models	10
Addressing the Binning Problem in Calibration Assessment through Scalar Annotations	10
MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs	9
PaniniQA: Enhancing Patient Education Through Interactive Question Answering	9
Investigating Critical Period Effects in Language Acquisition through Neural Language Models	9
Time-and-Space-Efficient Weighted Deduction	9
How “Real” is Your Real-Time Simultaneous Speech-to-Text Translation System?	9
Towards More Realistic Extraction Attacks: An Adversarial Perspective	9
Helpful Neighbors: Leveraging Neighbors in Geographic Feature Pronunciation	9
Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization	9
TANQ: An Open Domain Dataset of Table Answered Questions	9
Self-Rationalization in the Wild: A Large-scale Out-of-Distribution Evaluation on NLI-related tasks	9