33 citations · 34 across the 11 of their papers we have counts for
11 papers
Context Compression Is Not One Thing: Readable Symbolic Re-expression vs. Coherent Summary at Matched Budget
Sisong Bei, Mikhail L. Arbuzov, Ziwei Dong +2
We study context compression for multi-hop question answering with small language models. We propose Telegraph English, a readable symbolic format that rewrites retrieved passages…
Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
Karthik Raghu Iyer, Yazdan Jamshidi, Nicholas Bray +1
We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 46 Target Technique matrix grounded in STRIDE…
The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
Mikhail L. Arbuzov, Lee Mosbacker, Sisong Bei +3
Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, new intervention-distinguishabl…
Estimated Dynamic Equilibrium Model: Supply and Demand as a Sample Path of a Stochastic Process
Mikhail L. Arbuzov, Sisong Bei, Alexey Shvets
We introduce the Estimated Dynamic Equilibrium Model (EDEM), an agent-based framework that treats supply and demand as a coupled stochastic process driven by heterogeneous, noisy a…
The Critical Renyi Order for Sharp Minimax Channel Design
Alex Shvets
We study categorical channel design under a bound on the maximum directed pairwise Renyi divergence. We determine exactly which orders make randomized response optimal in every dim…
Simultaneous Reconstruction of Shuffled Histograms from a Retained Statistic: Exact leading coefficients for finite hypothesis families
Alex Shvets
Le Cam deficiency is the largest increase in Bayes risk caused by retaining a statistic, over all priors and decision problems with losses in . We compute its exact leading…
Minimax Binary Counting under Shuffle Privacy: Poisson Limits and Randomized-Response Optimality
Alex Shvets
We study estimation of a deterministic binary count from the shuffled outputs of a common single-message local channel. Privacy is required for every neighboring composition at fix…
Growing Alphabets in Canonical Shuffle Experiments: Likelihood-Ratio Laws, Estimation Bounds, and Low-Budget Equivariant Design
Alex Shvets
We study canonical one-step neighboring shuffle experiments for finite-output epsilon_0-LDP d-ary channels along growing alphabets, with frequency estimation and mechanism design u…
Fixed-Composition Shuffle Asymptotics in the Full-Support Gaussian Regime
Alex Shvets
We study privacy amplification by shuffling for binary-input local randomizers with a fixed finite output alphabet and full support. For a dataset containing exactly k ones among n…
Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models
Mikhail L. Arbuzov, Sisong Bei, Ziwei Dong +2
The prevailing assumption of an exponential decay in large language model (LLM) reliability with sequence length, predicated on independent per-token error probabilities, posits an…
Sequence Heterogeneity Accelerates Protein Search for Targets on DNA
Alexey A. Shvets, Anatoly B. Kolomeisky
The process of protein search for specific binding sites on DNA is fundamentally important since it marks the beginning of all major biological processes. We present a theoretical…