ArXiv NLP research for Tuesday, June 11, 2024.

00:20: Scientific Computing with Large Language Models

01:08: Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication

02:19: Bilingual Sexism Classification: Fine-Tuned XLM-RoBERTa and GPT-3.5 Few-Shot Learning

03:51: Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models

05:26: Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?

07:03: Joint Learning of Context and Feedback Embeddings in Spoken Dialogue

07:57: BertaQA: How Much Do Language Models Know About Local Culture?

09:17: MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting

10:20: CTC-based Non-autoregressive Textless Speech-to-Speech Translation

11:21: Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities

13:27: GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews

14:40: BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction

16:32: When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

18:01: Limited Out-of-Context Knowledge Reasoning in Large Language Models

19:36: MINERS: Multilingual Language Models as Semantic Retrievers

20:42: Learning Domain-Invariant Features for Out-of-Context News Detection

22:03: Textual Similarity as a Key Metric in Machine Translation Quality Estimation

23:02: On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations

24:31: Multimodal Belief Prediction

25:29: Advancing Annotation of Stance in Social Media Posts: A Comparative Analysis of Large Language Models and Crowd Sourcing

26:56: Paraphrasing in Affirmative Terms Improves Negation Understanding

27:37: CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization

29:38: TextGrad: Automatic "Differentiation" via Text

31:35: Just Because We Camp, Doesn't Mean We Should: The Ethics of Modelling Queer Voices

32:35: THaLLE: Text Hyperlocally Augmented Large Language Extension -- Technical Report

33:51: Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

35:22: Simple and Effective Masked Diffusion Language Models

36:35: Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena