paper-with-me

Papers

TensorCommitments: A Lightweight Verifiable Inference for Language Models

2026-02-13 · Oguzhan Baser, Elahe Sadeghi, Eric Wang, David Ribeiro Alves, Sam Kazemian, Hong Kang, Sandeep P. Chinchali, Sriram Vishwanath arxiv

Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM inference, where a prover (the service) must convince a verifier (the client) that an inference was run correctly without rerunning the LLM. Existing cryptographic works are too slow at the LLM scale, while non-cryptographic ones require a strong verifier GPU. We propose TensorCommitments (TCs), a tensor-native proof-of-inference scheme. TC binds the LLM inference to a commitment, an irreversible tag that breaks under tampering, organized in our multivariate Terkle Trees. For LLaMA2, TC adds only 0.97% prover and 0.12% verifier time over inference while improving robustness to tailored LLM attacks by up to 48% over the best prior work requiring a verifier GPU.

📄 PDF Abstract BibTeX arXiv:2602.12630

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference

2025-09-29 · Ke Wang, Zishuo Zhao, Xinyuan Song, Zelin Li 외 arxiv

Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance on centralized providers. However, in a p…

Belief-Guided Inference Control for Large Language Model Services via Verifiable Observations

2026-04-30 · Wenhao Yuan, Chenchen Lin, Jian Chen, Jinfeng Xu 외 arxiv

In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while stronger inference pathways incur substantial computational cost, inducing a budgeted sequ…

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

2026-03-08 · Heng Jin, Chaoyu Zhang, Hexuan Yu, Shanghao Shi 외 arxiv

Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified de…

TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles

2026-04-19 · Yirong Zeng, Yufei Liu, Xiao Ding, Yutai Hou 외 arxiv

Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.g., output length) to unverifiable ones (e.g., tone). Reinforcement learning wit…

Reinforcement LearningInstruction Following

Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks

2025-09-27 · Chunyang Jiang, Yonggang Zhang, Yiyang Cai, Chi-Min Chan 외 arxiv

The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in genera…

Computational EfficiencySemantic Similarity