ArXiv NLP research for Thursday, June 13, 2024.

00:20: Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning

01:53: Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models

03:26: Automated Essay Scoring Using Grammatical Variety and Errors with Multi-Task Learning and Item Response Theory

04:33: Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination

06:05: DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage

07:26: Research on Optimization of Natural Language Processing Model Based on Multimodal Deep Learning

08:41: ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions

10:07: An Approach to Build Zero-Shot Slot-Filling System for Industry-Grade Conversational Assistants

11:42: Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentation

12:42: No perspective, no perception!! Perspective-aware Healthcare Answer Summarization

14:28: Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models

16:02: An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios

17:21: Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors

18:48: Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning

19:52: Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation

21:12: Multi-Agent Software Development through Cross-Team Collaboration

22:55: LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models

24:14: Bayesian Statistical Modeling with Predictors from LLMs

25:39: ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models

27:28: Language Models are Crossword Solvers

28:32: MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning

29:51: CUDRT: Benchmarking the Detection of Human vs. Large Language Models Generated Texts

31:29: Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?

32:59: 3M: Multi-modal Multi-task Multi-teacher Learning for Game Event Detection

34:08: Modeling Comparative Logical Relation with Contrastive Learning for Text Generation

35:42: SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models