59 citations · 64 across the 13 of their papers we have counts for
18 papers
Representation-Aligned Auxiliary Supervision for Language Model Adaptation
Kyuyoung Kim, Peiyao Sheng, Ashwin Hebbar +9
Language models exhibit strong reasoning capabilities, yet adapting them to structured domains remains challenging and can yield inconsistent outcomes. We identify representation c…
Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary
S. Ashwin Hebbar, Peiyao Sheng, Sewoong Oh +1
Superhuman game engines in domains like chess have made expert-level evaluations easily accessible, yet they communicate what is true without the natural-language explanations that…
Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
Kyuyoung Kim, Kevin Wang, Yunfei Xie +7
Training language models to produce both correct answers and sound reasoning remains an open challenge. Reinforcement learning with verifiable rewards typically optimizes only fina…
MURMUR: Using cross-user chatter to break collaborative language agents in groups
Atharv Singh Patlan, Peiyao Sheng, S. Ashwin Hebbar +2
Language agents are rapidly expanding from single-user assistants to multi-user collaborators in shared workspaces and groups. However, today's language models lack a mechanism for…
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
Zihan Zheng, Zerui Cheng, Zeyu Shen +16
Recent reports claim that large language models (LLMs) now outperform elite humans in competitive programming. Drawing on knowledge from a group of medalists in international algor…
CHANCERY: Evaluating Corporate Governance Reasoning Capabilities in Language Models
Lucas Irwin, Arda Kaz, Peiyao Sheng +2
Law has long been a domain that has been popular in natural language processing (NLP) applications. Reasoning (ratiocination and the ability to make connections to precedent) is a…
Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents
Atharv Singh Patlan, Peiyao Sheng, S. Ashwin Hebbar +2
AI agents integrated with Web3 offer autonomy and openness but raise security concerns as they interact with financial protocols and immutable smart contracts. This paper investiga…
Scalable Fingerprinting of Large Language Models
Anshul Nasery, Jonathan Hayase, Creston Brooks +4
Model fingerprinting has emerged as a powerful tool for model owners to identify their shared model given API access. However, to lower false discovery rate, fight fingerprint leak…
On Orchestrating Parallel Broadcasts for Distributed Ledgers
Peiyao Sheng, Chenyuan Wu, Dahlia Malkhi +4
This paper introduces and develops the concept of ``ticketing'', through which atomic broadcasts are orchestrated by nodes in a distributed system. The paper studies different tick…
Unconditionally Safe Light Client
Niusha Moshrefi, Peiyao Sheng, Soubhik Deb +2
Blockchain applications often rely on lightweight clients to access and verify on-chain data efficiently without the need to run a resource-intensive full node. These light clients…
BFT-PoLoc: A Byzantine Fortified Trigonometric Proof of Location Protocol using Internet Delays
Peiyao Sheng, Vishal Sevani, Ranvir Rana +2
Internet platforms depend on accurately determining the geographical locations of online users to deliver targeted services (e.g., advertising). The advent of decentralized platfor…
Proof of Diligence: Cryptoeconomic Security for Rollups
Peiyao Sheng, Ranvir Rana, Senthil Bala +2
Layer 1 (L1) blockchains such as Ethereum are secured under an "honest supermajority of stake" assumption for a large pool of validators who verify each and every transaction on it…
SAKSHI: Decentralized AI Platforms
Suma Bhat, Canhui Chen, Zerui Cheng +8
Large AI models (e.g., Dall-E, GPT4) have electrified the scientific, technological and societal landscape through their superhuman capabilities. These services are offered largely…
CFT-Forensics: High-Performance Byzantine Accountability for Crash Fault Tolerant Protocols
Weizhao Tang, Peiyao Sheng, Ronghao Ni +4
Crash fault tolerant (CFT) consensus algorithms are commonly used in scenarios where system components are trusted -- e.g., enterprise settings and government infrastructure. Howev…
Proof of Backhaul: Trustfree Measurement of Broadband Bandwidth
Peiyao Sheng, Nikita Yadav, Vishal Sevani +4
Recent years have seen the emergence of decentralized wireless networks consisting of nodes hosted by many individuals and small enterprises, reawakening the decades-old dream of o…
TrustBoost: Boosting Trust among Interoperable Blockchains
Peiyao Sheng, Xuechao Wang, Sreeram Kannan +2
Currently there exist many blockchains with weak trust guarantees, limiting applications and participation. Existing solutions to boost the trust using a stronger blockchain, e.g.,…
ACeD: Scalable Data Availability Oracle
Peiyao Sheng, Bowen Xue, Sreeram Kannan +1
A popular method in practice offloads computation and storage in blockchains by relying on committing only hashes of off-chain data into the blockchain. This mechanism is acknowled…
BFT Protocol Forensics
Peiyao Sheng, Gerui Wang, Kartik Nayak +2
Byzantine fault-tolerant (BFT) protocols allow a group of replicas to come to a consensus even when some of the replicas are Byzantine faulty. There exist multiple BFT protocols to…