VS
Veselin Stoyanov
cs.CLcs.LGcs.AIcs.IRcs.CEcs.SIcs.PLcs.SEstat.ML
On Valency
published · living versionsW_b67cayr4·v1 · currentpublished
The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering
with Debopriyo Banerjee, Owais Aijaz, Ahmer Tabassum, Zhuohan Xie +1
1 version
Preprints & journals
39 papers in the corpus · 2018–2026The Bottleneck Is Retrieval, Not Reading: Diagnosing Evidence-Based Generation with RAG for Long Context Question Answering2610.26951v1 · Debopriyo Banerjee, Owais Aijaz, Ahmer Tabassum et al.2026 · 0 citationsarXivon Valency
Overview of FinMMEval 2026 Task 1: Multilingual Financial Multiple-Choice Question Answering2607.19856v1 · Zhuohan Xie, Yuyang Dai, Rania Elbadry et al.2026 · 0 citationsarXiv
Overview of FinMMEval 2026 Task 2: Multilingual Financial Short-Answer Question Answering2607.19867v1 · Zhuohan Xie, Xueqing Peng, Georgi Georgiev et al.2026 · 0 citationsarXiv
SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning2604.19098v2 · Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl et al.2026 · 1 citationACL 2026
The CLEF-2026 FinMMEval Lab: Multilingual and Multimodal Evaluation of Financial AI Systems2602.10886v1 · Zhuohan Xie, Rania Elbadry, Fan Zhang et al.2026 · 1 citationarXiv
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning2506.02515v4 · Zhuohan Xie, Daniil Orel, Rushil Thareja et al.2025 · 2 citationsarXiv
Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs2505.15524v1 · Lang Gao, Kaiyang Wan, Wei Liu et al.2025 · 0 citationsarXiv
bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark2306.02349v2 · Momchil Hardalov, Pepa Atanasova, Todor Mihaylov et al.2023 · 5 citationsACL 2023
Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model2305.13999v3 · Zeyu Leo Liu, Tim Dettmers, Xi Victoria Lin et al.2023 · 5 citationsarXiv
LEVER: Learning to Verify Language-to-Code Generation with Execution2302.08468v3 · Ansong Ni, Srini Iyer, Dragomir Radev et al.2023 · 46 citationsarXiv
OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization2212.12017v3 · Srinivasan Iyer, Xi Victoria Lin, Ramakanth Pasunuru et al.2022 · 81 citationsarXiv
Training Trajectories of Language Models Across Scales2212.09803v3 · Mengzhou Xia, Mikel Artetxe, Chunting Zhou et al.2022 · 13 citationsarXiv
Complementary Explanations for Effective In-Context Learning2211.13892v2 · Xi Ye, Srinivasan Iyer, Asli Celikyilmaz et al.2022 · 46 citationsarXiv
Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models2205.15223v3 · Mengzhou Xia, Mikel Artetxe, Jingfei Du et al.2022 · 12 citationsarXiv
ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection2205.12495v2 · Badr AlKhamissi, Faisal Ladhak, Srini Iyer et al.2022 · 22 citationsIn Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2109-2120, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics
On the Role of Bidirectionality in Language Model Pre-Training2205.11726v2 · Mikel Artetxe, Jingfei Du, Naman Goyal et al.2022 · 10 citationsarXiv
Improving In-Context Few-Shot Learning via Self-Supervised Training2205.01703v2 · Mingda Chen, Jingfei Du, Ramakanth Pasunuru et al.2022 · 26 citationsarXiv
PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models2204.01172v2 · Rabeeh Karimi Mahabadi, Luke Zettlemoyer, James Henderson et al.2022 · 9 citationsarXiv
Efficient Language Modeling with Sparse all-MLP2203.06850v3 · Ping Yu, Mikel Artetxe, Myle Ott et al.2022 · 1 citationarXiv
Few-shot Learning with Multilingual Language Models2112.10668v3 · Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe et al.2021 · 79 citationsarXiv
Efficient Large Scale Language Modeling with Mixtures of Experts2112.10684v2 · Mikel Artetxe, Shruti Bhosale, Naman Goyal et al.2021 · 95 citationsarXiv
Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs2111.13654v1 · Peter Hase, Mona Diab, Asli Celikyilmaz et al.2021 · 13 citationsarXiv
Multi-task Retrieval for Knowledge-Intensive Tasks2101.00117v1 · Jean Maillard, Vladimir Karpukhin, Fabio Petroni et al.2021 · 48 citationsarXiv
Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning2011.01403v3 · Beliz Gunel, Jingfei Du, Alexis Conneau et al.2020 · 296 citationsarXiv
Self-training Improves Pre-training for Natural Language Understanding2010.02194v1 · Jingfei Du, Edouard Grave, Beliz Gunel et al.2020 · 134 citationsarXiv
Conversational Semantic Parsing2009.13655v1 · Armen Aghajanyan, Jean Maillard, Akshat Shrivastava et al.2020 · 38 citationsarXiv
Preserving Integrity in Online Social Networks2009.10311v3 · Alon Halevy, Cristian Canton Ferrer, Hao Ma et al.2020 · 56 citationsarXiv
General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference2004.14287v1 · Jingfei Du, Myle Ott, Haoran Li et al.2020 · 8 citationsarXiv
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model1912.09637v1 · Wenhan Xiong, Jingfei Du, William Yang Wang et al.2019 · 167 citationsarXiv
SemEval-2014 Task 9: Sentiment Analysis in Twitter1912.02990v1 · Sara Rosenthal, Preslav Nakov, Alan Ritter et al.2019 · 618 citationsSemEval-2014
SemEval-2015 Task 10: Sentiment Analysis in Twitter1912.02387v1 · Sara Rosenthal, Saif M Mohammad, Preslav Nakov et al.2019 · 371 citationsSemEval-2015
SemEval-2016 Task 4: Sentiment Analysis in Twitter1912.01973v1 · Preslav Nakov, Alan Ritter, Sara Rosenthal et al.2019 · 969 citationsFinal version published in the Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval 2016), San Diego, US, 2016, pp. 1-18
Unsupervised Cross-lingual Representation Learning at Scale1911.02116v2 · Alexis Conneau, Kartikay Khandelwal, Naman Goyal et al.2019 · 5,620 citationsarXiv
Emerging Cross-lingual Structure in Pretrained Language Models1911.01464v3 · Shijie Wu, Alexis Conneau, Haoran Li et al.2019 · 210 citationsarXiv
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension1910.13461v1 · Mike Lewis, Yinhan Liu, Naman Goyal et al.2019 · 8,801 citationsarXiv
Bridging the domain gap in cross-lingual document classification1909.07009v2 · Guokun Lai, Barlas Oguz, Yiming Yang et al.2019 · 12 citationsarXiv
Knowledge-Augmented Language Model and its Application to Unsupervised Named-Entity Recognition1904.04458v2 · Angli Liu, Jingfei Du, Veselin Stoyanov2019 · 40 citationsarXiv
XNLI: Evaluating Cross-lingual Sentence Representations1809.05053v1 · Alexis Conneau, Guillaume Lample, Ruty Rinott et al.2018 · 991 citationsarXiv
Simple Fusion: Return of the Language Model1809.00125v2 · Felix Stahlberg, James Cross, Veselin Stoyanov2018 · 60 citationsarXiv
Career total: 84 works. 39 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.