collaborators

6 papers

cs.AI2026

LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?

Juliusz Ziomek, William Bankes, Lorenz Wolf +3

We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wi…

cs.CL2026

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

William Lugoloobi, Thomas Foster, William Bankes +1

Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging. We investigate whether the…

cs.LG2026

Robust Multi-Objective Controlled Decoding of Large Language Models

Seongho Son, William Bankes, Sangwoong Yoon +3

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruct…

cs.LG2026

Detecting High-Stakes Interactions with Activation Probes

Alex McKenzie, Urja Pawar, Phil Blandfort +4

Monitoring is an important aspect of safely deploying Large Language Models (LLMs). This paper examines activation probes for detecting ``high-stakes'' interactions -- where the te…

cs.LG2026

Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift

Seongho Son, William Bankes, Sayak Ray Chowdhury +2

Current Large Language Model (LLM) preference optimization algorithms do not account for temporal preference drift, which can lead to severe misalignment. To address this limitatio…

cs.LG2024

REDUCR: Robust Data Downsampling Using Class Priority Reweighting

William Bankes, George Hughes, Ilija Bogunovic +1

Modern machine learning models are becoming increasingly expensive to train for real-world image and text classification tasks, where massive web-scale data is collected in a strea…