ArXiv NLP research for Friday, June 07, 2024.

00:19: Key-Element-Informed sLLM Tuning for Document Summarization

01:22: Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models

02:42: Large Language Model-guided Document Selection

04:13: More Victories, Less Cooperation: Assessing Cicero's Diplomacy Play

05:24: DiNeR: a Large Realistic Dataset for Evaluating Compositional Generalization

06:43: MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources

08:01: Mixture-of-Agents Enhances Large Language Model Capabilities

09:09: AICoderEval: Improving AI Domain Code Generation of Large Language Models

11:00: CRAG -- Comprehensive RAG Benchmark

13:04: CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models

14:52: Think out Loud: Emotion Deducing Explanation in Dialogues

16:43: WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

18:46: SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals

19:58: BERTs are Generative In-Context Learners

20:43: Annotating FrameNet via Structure-Conditioned Language Generation

21:49: Revisiting Catastrophic Forgetting in Large Language Model Tuning

22:43: FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models

24:33: Do Language Models Exhibit Human-like Structural Priming Effects?

25:27: Uncertainty Aware Learning for Language Model Alignment

26:50: The Russian Legislative Corpus

27:24: ComplexTempQA: A Large-Scale Dataset for Complex Temporal Question Answering

28:53: HateDebias: On the Diversity and Variability of Hate Speech Debiasing

30:29: A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques

32:00: Sexism Detection on a Data Diet

33:18: XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model

34:21: Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models

35:32: LLM-based speaker diarization correction: A generalizable approach

36:52: TCMD: A Traditional Chinese Medicine QA Dataset for Evaluating Large Language Models

38:10: BAMO at SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense

39:10: Quantifying Geospatial in the Common Crawl Corpus

40:14: MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter

41:47: Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences

43:19: Compositional Generalization with Grounded Language Models

44:26: Scenarios and Approaches for Situated Natural Language Explanations

46:04: Are Large Language Models More Empathetic than Humans?

47:38: SUMIE: A Synthetic Benchmark for Incremental Entity Summarization

48:52: Multi-Head RAG: Solving Multi-Aspect Problems with LLMs

50:33: An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models