大模型推理能力 - arXivDaily 专题

2505.05494 2025-05-12 cs.DB cs.AI cs.IR cs.LG 73%

An Automated LLM-based Pipeline for Asset-Level Database Creation to Assess Deforestation Impact

Avanija Menon, Ovidiu Serban

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI、cs.LG

Comments Accepted to ACL ClimateNLP 2025

2504.10490 2025-04-16 cs.LG cs.CL 73%

GPT Meets Graphs and KAN Splines: Testing Novel Frameworks on Multitask Fine-Tuned GPT-2 with LoRA

Gabriel Bo, Marc Bernardino, Justin Gu

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.LG

Comments 10 pages, 11 figures. This submission cites arXiv:2404.19756. Supplementary materials and additional information are available at arXiv:2404.19756

2501.00192 2025-04-08 cs.CV cs.CL cs.CY cs.LG 73%

MLLM-as-a-Judge for Image Safety without Human Labeling

Zhenting Wang, Shuming Hu, Shiyu Zhao, Xiaowen Lin, Felix Juefei-Xu, Zhuowei Li, Ligong Han, Harihar Subramanyam, Li Chen, Jianfa Chen, Nan Jiang, Lingjuan Lyu, Shiqing Ma, Dimitris N. Metaxas, Ankit Jain

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.LG

2504.02902 2025-04-07 cs.CL cs.AI 73%

Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models

Liangjie Huang, Dawei Li, Huan Liu, Lu Cheng

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

2503.23371 2025-04-01 cs.CL cs.AI 73%

FeRG-LLM : Feature Engineering by Reason Generation Large Language Models

Jeonghyun Ko, Gyeongyun Park, Donghoon Lee, Kyunam Lee

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments Accepted to NAACL 2025 Findings

2502.10266 2025-02-17 cs.CL cs.AI 73%

Are Large Language Models the future crowd workers of Linguistics?

Iris Ferrazzo

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

2409.19020 2025-02-11 cs.CL cs.LG 73%

DiaSynth: Synthetic Dialogue Generation Framework for Low Resource Dialogue Applications

Sathya Krishnan Suresh, Wu Mengjun, Tushar Pranav, Eng Siong Chng

专题命中其他推理：reasoning(abstract)；CoT(abstract)；分类 cs.CL、cs.LG

Comments 13 pages, 1 figure

Journal ref NAACL 2025

2502.03129 2025-02-06 cs.CL cs.LG 73%

Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales

Zhen Qian, Xiuzhen Zhang, Xiaofei Xu, Feng Xia

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.LG

Comments Pre-print for a paper accepted to findings of NAACL 2025

2412.20595 2024-12-31 cs.CL cs.AI 73%

Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection

Dmitri Roussinov, Serge Sharoff, Nadezhda Puchnina

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments The 31st International Conference on Computational Linguistics

2412.05301 2024-12-10 cs.AR cs.AI cs.CL 73%

DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model

Hong Cai Chen, Longchang Wu, Ming Gao, Lingrui Shen, Jiarui Zhong, Yipin Xu

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

2402.18510 2024-12-10 cs.LG cs.CL stat.ML 73%

RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval

Kaiyue Wen, Xingyu Dang, Kaifeng Lyu

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.LG

Comments 42 pages, 6 figures

2412.04642 2024-12-09 cs.LG cs.AI 73%

Improving LLM Group Fairness on Tabular Data via In-Context Learning

Valeriia Cherepanova, Chia-Jung Lee, Nil-Jana Akpinar, Riccardo Fogliato, Martin Andres Bertran, Michael Kearns, James Zou

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.AI、cs.LG

2411.10541 2024-11-19 cs.CL cs.LG 73%

Does Prompt Formatting Have Any Impact on LLM Performance?

Jia He, Mukund Rungta, David Koleczek, Arshdeep Sekhon, Franklin X Wang, Sadid Hasan

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.LG

Comments Submitted to NAACL 2025

2410.19730 2024-10-30 cs.CL cs.AI 73%

Counting Ability of Large Language Models and Impact of Tokenization

Xiang Zhang, Juntai Cao, Chenyu You

专题命中其他推理：reasoning(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

2409.14673 2024-09-24 cs.CL cs.AI 73%

Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science

Taihang Wang, Xiaoman Xu, Yimin Wang, Ye Jiang

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

2409.09239 2024-09-24 cs.CL cs.AI 73%

Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer

Xiang Zhang, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan

专题命中其他推理：reasoning(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

2407.06023 2024-07-26 cs.CL cs.AI 73%

Distilling System 2 into System 1

Ping Yu, Jing Xu, Jason Weston, Ilia Kulikov

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

2402.11349 2024-06-07 cs.CL cs.AI 73%

Language Models Don't Learn the Physical Manifestation of Language

Bruce W. Lee, JaeHyuk Lim

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments ACL 2024 Main

2401.11382 2024-06-07 cs.CL cs.AI 73%

Using Large Language Model for End-to-End Chinese ASR and NER

Yuang Li, Jiawei Yu, Min Zhang, Mengxin Ren, Yanqing Zhao, Xiaofeng Zhao, Shimin Tao, Jinsong Su, Hao Yang

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments 5 pages, 2 figures, Accepted to InterSpeech 2024

2405.11120 2024-05-21 cs.AI cs.LG 73%

Latent State Estimation Helps UI Agents to Reason

William E Bishop, Alice Li, Christopher Rawles, Oriana Riva

专题命中其他推理：reasoning(abstract)；CoT(abstract)；分类 cs.AI、cs.LG

2404.14662 2024-04-24 cs.LG cs.CL cs.PL cs.SE 73%

NExT: Teaching Large Language Models to Reason about Code Execution

Ansong Ni, Miltiadis Allamanis, Arman Cohan, Yinlin Deng, Kensen Shi, Charles Sutton, Pengcheng Yin

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.LG

Comments 35 pages

2403.09611 2024-04-22 cs.CV cs.CL cs.LG 73%

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier, Sam Dodge, Bowen Zhang, Philipp Dufter, Dhruti Shah, Xianzhi Du, Futang Peng, Floris Weers, Anton Belyi, Haotian Zhang, Karanjeet Singh, Doug Kang, Ankur Jain, Hongyu Hè, Max Schwarzer, Tom Gunter, Xiang Kong, Aonan Zhang, Jianyu Wang, Chong Wang, Nan Du, Tao Lei, Sam Wiseman, Guoli Yin, Mark Lee, Zirui Wang, Ruoming Pang, Peter Grasch, Alexander Toshev, Yinfei Yang

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.LG

2402.03776 2024-03-04 cs.CL cs.AI 73%

Large Language Models As MOOCs Graders

Shahriar Golchin, Nikhil Garuda, Christopher Impey, Matthew Wenger

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments v1.3 preprint

2310.05736 2023-12-07 cs.CL cs.LG 73%

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, Lili Qiu

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.LG

Comments Accepted at EMNLP 2023

2310.05028 2023-11-27 cs.AI cs.CL 73%

Revisiting Large Language Models as Zero-shot Relation Extractors

Guozheng Li, Peng Wang, Wenjun Ke

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments Findings of EMNLP 2023

2311.10227 2023-11-20 cs.AI cs.CL 73%

Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities

Alex Wilf, Sihyun Shawn Lee, Paul Pu Liang, Louis-Philippe Morency

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

2310.07328 2023-10-23 cs.CL cs.AI 73%

An Empirical Study of Instruction-tuning Large Language Models in Chinese

Qingyi Si, Tong Wang, Zheng Lin, Xu Zhang, Yanan Cao, Weiping Wang

专题命中其他推理：chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2023

2309.04663 2023-09-13 cs.CL cs.AI 73%

FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning

Xinyi Wang, John Wieting, Jonathan H. Clark

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

2307.08072 2023-07-27 cs.CL cs.AI 73%

Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study

Peiyu Liu, Zikang Liu, Ze-Feng Gao, Dawei Gao, Wayne Xin Zhao, Yaliang Li, Bolin Ding, Ji-Rong Wen

专题命中其他推理：reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments 15 pages, 4 figures

2608.17279 2026-08-19 cs.CV 新提交 71%

Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge

基于SAM3的关键帧推理：第8届LSVOS挑战赛MeViS-Text赛道第三名解决方案

Ce Bian, Xusheng He, Jinrong Zhang, Canyang Wu, Xianjing Han, Jianlong Wu

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））； Nanyang Technological University（南洋理工大学）； Shenzhen Loop Area Institute（深圳河套学院）

专题命中其他推理：reasoning(title)

AI总结该研究提出两阶段无训练方案，依托Gemini-3.1 Pro分解视频事件选关键帧，用SAM3-agent生成掩码并双向传播，获第8届LSVOS挑战赛MeViS-Text赛道第三名。

1. 其他推理 5804 篇

An Automated LLM-based Pipeline for Asset-Level Database Creation to Assess Deforestation Impact

GPT Meets Graphs and KAN Splines: Testing Novel Frameworks on Multitask Fine-Tuned GPT-2 with LoRA

MLLM-as-a-Judge for Image Safety without Human Labeling

Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models

FeRG-LLM : Feature Engineering by Reason Generation Large Language Models

Are Large Language Models the future crowd workers of Linguistics?

DiaSynth: Synthetic Dialogue Generation Framework for Low Resource Dialogue Applications

Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales

Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection

DocEDA: Automated Extraction and Design of Analog Circuits from Documents with Large Language Model

RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval

Improving LLM Group Fairness on Tabular Data via In-Context Learning

Does Prompt Formatting Have Any Impact on LLM Performance?

Counting Ability of Large Language Models and Impact of Tokenization

Instruction Tuning Vs. In-Context Learning: Revisiting Large Language Models in Few-Shot Computational Social Science

Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer

Distilling System 2 into System 1

Language Models Don't Learn the Physical Manifestation of Language

Using Large Language Model for End-to-End Chinese ASR and NER

Latent State Estimation Helps UI Agents to Reason

NExT: Teaching Large Language Models to Reason about Code Execution

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Large Language Models As MOOCs Graders

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Revisiting Large Language Models as Zero-shot Relation Extractors

Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilities

An Empirical Study of Instruction-tuning Large Language Models in Chinese

FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning

Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study

Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS Challenge