Enabling Early Exit Inference and Self-Speculative Decoding

[ad_1] [Submitted on 25 Apr 2024 (v1), last revised 18 Oct 2024 (this version, v4)] Authors:Mostafa Elhoushi, Akshat Shrivastava, Diana ...
Read more
Benchmarking LLM Proficiency in Scientific Literature Analysis

[ad_1] [Submitted on 4 Mar 2024 (v1), last revised 18 Oct 2024 (this version, v5)] Authors:Hengxing Cai, Xiaochen Cai, Junhan ...
Read more
Inferring Safe Actions for LLM-Based Agents Through Preemptive Evaluation and Human Feedback

[ad_1] [Submitted on 16 Jul 2024 (v1), last revised 17 Oct 2024 (this version, v2)] View a PDF of the ...
Read more
Lightweight Passage Retrieval for Open Domain Multi-Document Summarization

[ad_1] [Submitted on 18 Jun 2024 (v1), last revised 17 Oct 2024 (this version, v2)] View a PDF of the ...
Read more
[2310.20246] Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations

[ad_1] [Submitted on 31 Oct 2023 (v1), last revised 16 Oct 2024 (this version, v5)] View a PDF of the ...
Read more
[2406.11939] From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

[ad_1] [Submitted on 17 Jun 2024 (v1), last revised 14 Oct 2024 (this version, v2)] View a PDF of the ...
Read more
Reducing Labeling Costs in Sentiment Analysis via Semi-Supervised Learning

[ad_1] arXiv:2410.11355v1 Announce Kind: cross Summary: Labeling datasets is a noteworthy problem in machine studying, each by way of price ...
Read more
[2406.11109] Investigating Annotator Bias in Large Language Models for Hate Speech Detection

[ad_1] [Submitted on 17 Jun 2024 (v1), last revised 12 Oct 2024 (this version, v3)] View a PDF of the ...
Read more
A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs

[ad_1] [Submitted on 19 Jun 2024 (v1), last revised 10 Oct 2024 (this version, v2)] View a PDF of the ...
Read more
LLMs Robustness with Incorrect Multiple-Choice Options

[ad_1] [Submitted on 27 Aug 2024 (v1), last revised 10 Oct 2024 (this version, v2)] View a PDF of the ...
Read more