ติดตาม
Matthew Finlayson
Matthew Finlayson
PhD Student, University of Southern California
ยืนยันอีเมลแล้วที่ usc.edu - หน้าแรก
ชื่อ
อ้างโดย
อ้างโดย
ปี
Decomposed prompting: A modular approach for solving complex tasks
T Khot, H Trivedi, M Finlayson, Y Fu, K Richardson, P Clark, A Sabharwal
arXiv preprint arXiv:2210.02406, 2022
4002022
Lila: A unified benchmark for mathematical reasoning
S Mishra, M Finlayson, P Lu, L Tang, S Welleck, C Baral, T Rajpurohit, ...
arXiv preprint arXiv:2210.17517, 2022
1232022
Causal analysis of syntactic agreement mechanisms in neural language models
M Finlayson, A Mueller, S Gehrmann, S Shieber, T Linzen, Y Belinkov
arXiv preprint arXiv:2106.06087, 2021
972021
From decoding to meta-generation: Inference-time algorithms for large language models
S Welleck, A Bertsch, M Finlayson, H Schoelkopf, A Xie, G Neubig, ...
arXiv preprint arXiv:2406.16838, 2024
242024
Logits of api-protected llms leak proprietary information
M Finlayson, X Ren, S Swayamdipta
arXiv preprint arXiv:2403.09539, 2024
172024
What makes instruction learning hard? An investigation and a new challenge in a synthetic environment
M Finlayson, K Richardson, A Sabharwal, P Clark
arXiv preprint arXiv:2204.09148, 2022
102022
Closing the curious case of neural text degeneration
M Finlayson, J Hewitt, A Koller, S Swayamdipta, A Sabharwal
arXiv preprint arXiv:2310.01693, 2023
82023
Increasing probability mass on answer choices does not always improve accuracy
S Wiegreffe, M Finlayson, O Tafjord, P Clark, A Sabharwal
arXiv preprint arXiv:2305.14596, 2023
42023
Post-training an LLM for RAG? Train on Self-Generated Demonstrations
M Finlayson, I Kulikov, DM Bikel, B Oguz, X Chen, A Pappu
arXiv preprint arXiv:2502.10596, 2025
2025
ระบบไม่สามารถดำเนินการได้ในขณะนี้ โปรดลองใหม่อีกครั้งในภายหลัง
บทความ 1–9