EACL 2023
546 papers
The 2023 European Chapter of the Association for Computational Linguistics (EACL) featured 271 papers focusing on social fairness, bias mitigation, and cross-lingual transfer. Research themes included measuring social bias across the gender spectrum and grounding large language models in authoritative clinical evidence. Investigations into model limitations, such as performance variance in few-shot learning and over-reliance on entity names, were also prominent. Prolific contributors included Mohit Bansal, Iryna Gurevych, and Dan Roth.
Methodological trends highlighted advancements in zero-shot text classification and multimodal feature fusion. Notable work included the Massive Text Embedding Benchmark (MTEB) and the ConEntail framework for universal zero-shot classification. Other research explored temporal understanding through salient span masking and the use of human gaze feedback to improve model performance. The conference also addressed efficient representations for large-scale vector retrieval and the development of dialogue datasets for retrieving data tables through natural language.
Top Research Directions
Research directions most represented by EACL 2023 papers.
Top Authors
Impactful Papers
Papers from EACL 2023 that shaped research clusters.
Foundational
WinoDict: Probing language models for in-context word acquisition
foundational
When Pre-Trained Knowledge Conflicts wit
Parameter-Efficient Tuning with Special Token Adaptation
foundational
Decoupling Gradient Flow from Frozen Mod
Know your audience: specializing grounded language models with listener subtraction
foundational
Bias Amplification in Multi-Agent Langua
Adding Instructions during Pretraining: Effective way of Controlling Toxicity in Language Models
foundational
Low Latency Hallucination Mitigation for
Hierarchical Representations in Dense Passage Retrieval for Question-Answering
foundational
The Retrieval Quality Bottleneck in Retr
How Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification
foundational
The Limits of Fairness Prompting in Lang
Influential
JBLiMP: Japanese Benchmark of Linguistic Minimal Pairs
influential
Modeling Long Range Syntactic Dependenci
Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Re
influential
The Reproducibility Crisis in Human Eval
Automatic text simplification of Russian texts using control tokens
influential
Text Simplification Without Aligned Para
Document-Level Planning for Text Simplification
influential
The Language Bias of English Centric Ben
CoToHiLi at SIGTYP 2023: Ensemble Models for Cognate and Derivative Words Detection
influential
Stacked Generalization for Heterogeneous
GPT-2 Metadata Pretraining Towards Instruction Finetuning for Ukrainian
influential
Low-Rank Weight Decomposition for Effici
Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
influential
Attribute and Relational Hallucinations
IRMA: the 335-million-word Italian coRpus for studying MisinformAtion
influential
Scaling Fact Verification via Automated
Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge
influential
Overcoming Language Specific Feature Dep
Papers
« prev Page 11/11