大模型推理能力

AI-Assisted Generation of Difficult Math Questions

Vedant Shah, Dingli Yu, Kaifeng Lyu, Simon Park, Jiatong Yu, Yinghui He, Nan Rosemary Ke, Michael Mozer, Yoshua Bengio, Sanjeev Arora, Anirudh Goyal

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Analyzing Memorization in Large Language Models through the Lens of Model Attribution

Tarun Ram Menta, Susmit Agrawal, Chirag Agarwal

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Large Language Models for Mathematical Analysis

Ziye Chen, Hao Qi

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models

Xiaolin Hu, Xiang Cheng, Peiyu Liu, Wei Liu, Jian Luan, Bin Wang, Yong Liu

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 12 pages, 6 figures

DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

Yuxuan Tong, Xiwen Zhang, Rui Wang, Ruidong Wu, Junxian He

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments NeurIPS 2024. Data and model checkpoints are available at https://github.com/hkust-nlp/dart-math

S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity

Xinyu Yang, Jixuan Leng, Geyang Guo, Jiawei Zhao, Ryumei Nakada, Linjun Zhang, Huaxiu Yao, Beidi Chen

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

SOLO: A Single Transformer for Scalable Vision-Language Modeling

Yangyi Chen, Xingyao Wang, Hao Peng, Heng Ji

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Accepted to TMLR

Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking

Paria Rashidinejad, Yuandong Tian

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments 46 pages, 3 figures

Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback

Avinash Anand, Kritarth Prasad, Chhavi Kirtani, Ashwin R Nair, Mohit Gupta, Saloni Garg, Anurag Gautam, Snehal Buldeo, Rajiv Ratn Shah

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement

Pranjal Aggarwal, Bryan Parno, Sean Welleck

专题命中 数学推理 ：verifier(abstract)；分类 cs.AI、cs.LG

Mixing It Up: The Cocktail Effect of Multi-Task Fine-Tuning on LLM Performance -- A Case Study in Finance

Meni Brief, Oded Ovadia, Gil Shenderovitz, Noga Ben Yoash, Rachel Lemberg, Eitam Sheetrit

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

MathGLM-Vision: Solving Mathematical Problems with Multi-Modal Large Language Model

Zhen Yang, Jinhao Chen, Zhengxiao Du, Wenmeng Yu, Weihan Wang, Wenyi Hong, Zhihuan Jiang, Bin Xu, Jie Tang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 30 pages,19 figures

Feature-Factory: Automating Software Feature Integration Using Generative AI

Ruslan Idelfonso Magana Vsevolodovna

专题命中 数学推理 ：planning(abstract)；分类 cs.AI、cs.LG

Comments 14 pages, 1 figure

O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?

Zhen Huang, Haoyang Zou, Xuefeng Li, Yixiu Liu, Yuxiang Zheng, Ethan Chern, Shijie Xia, Yiwei Qin, Weizhe Yuan, Pengfei Liu

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 16 pages

Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models

Zhihua Duan, Jialin Wang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Language Models Need Inductive Biases to Count Inductively

Yingshan Chang, Yonatan Bisk

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, Diyi Yang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Published in COLM2024. Code Repo: https://github.com/SALT-NLP/DyLAN

Kwai-STaR: Transform LLMs into State-Transition Reasoners

Xingyu Lu, Yuhang Hu, Changyi Liu, Tianke Zhang, Zhenyu Yang, Zhixiang Ding, Shengsheng Qian, Meng Du, Ruiwen Kang, Kaiyu Tang, Fan Yang, Tingting Gao, Di Zhang, Hai-Tao Zheng, Bin Wen

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 6 pages, 2 figures

SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation

Prakhar Dixit, Tim Oates

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted to the 4th MATH-AI Workshop at NeurIPS'24

Give me a hint: Can LLMs take a hint to solve math problems?

Vansh Agrawal, Pratham Singla, Amitoj Singh Miglani, Shivank Garg, Ayush Mangal

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Noise Contrastive Alignment of Language Models with Explicit Rewards

Huayu Chen, Guande He, Lifan Yuan, Ganqu Cui, Hang Su, Jun Zhu

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments NeurIPS 2024

Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems

Junyi Ye, Jingyi Gu, Xinyun Zhao, Wenpeng Yin, Guiling Wang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Keep Guessing? When Considering Inference Scaling, Mind the Baselines

Gal Yona, Or Honovich, Omer Levy, Roee Aharoni

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems

Asir Saadat, Tasmia Binte Sogir, Md Taukir Azam Chowdhury, Syem Aziz

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 11 pages, 7 figures, 2 tables

How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective

Teng Xiao, Mingxiao Li, Yige Yuan, Huaisheng Zhu, Chao Cui, Vasant G Honavar

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments EMNLP 2024 Main

How Does Quantization Affect Multilingual LLMs?

Kelly Marchisio, Saurabh Dash, Hongyu Chen, Dennis Aumiller, Ahmet Üstün, Sara Hooker, Sebastian Ruder

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments Findings of EMNLP 2024 Camera-Ready

PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness

Zekun Wang, Feiyu Duan, Yibo Zhang, Wangchunshu Zhou, Ke Xu, Wenhao Huang, Jie Fu

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 39 pages. CP-Bench and LenCtrl-Bench are available in https://huggingface.co/datasets/ZenMoore/CP-Bench and https://huggingface.co/datasets/ZenMoore/LenCtrl-Bench

Efficient Prompting for LLM-based Generative Internet of Things

Bin Xiao, Burak Kantarci, Jiawen Kang, Dusit Niyato, Mohsen Guizani

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 14 pages, 11 figures. IEEE Internet of Things Journal, 2024

AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations

Zhicheng Yang, Yinya Huang, Jing Xiong, Liang Feng, Xiaodan Liang, Yiwei Wang, Jing Tang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Findings of EMNLP 2024

Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts

Aditya Sharma, Michael Saxon, William Yang Wang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Findings of EMNLP 2024