16 papers
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Ziyan Wang, Shuqing Shi, James Oldfield +5
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM…
Conformalized Large Language Models under Configuration Shift
Yuqicheng Zhu, Jialin Yu, Lin Li +7
Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets…
OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents
Kaicheng Zhang, Wen Ge, Lei Jiang +5
Although large language model agents are increasingly applied to quantitative-finance workflows, their evaluation remains fragmented across isolated tasks, while the financial rele…
A Low-Rank Subspace Analysis of LLM Interventions
Angira Sharma, Christian Schroeder de Witt, Philip Torr +2
Interventions designed to modify a particular behavior in LLMs, such as refusal or sycophancy, often produce unintended changes in other behaviors. This lack of targeted control ma…
When Language Representations Interact: Separability and Cross-Lingual Effects in LLMs
Boris Marinov, Angira Sharma, Christian Schroeder de Witt +3
Large language models exhibit strong multilingual capabilities, however, their internal representations are difficult to interpret. Understanding these interactions is important fo…
Retrieval-Augmented Linguistic Calibration
Yi-Fan Yeh, Linwei Tao, Minjing Dong +4
Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic c…
ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
Zeyuan He, Bowen Yang, Zhirui Fang +9
Vision-Language-Action (VLA) models have shown promise for robotic manipulation, yet most existing policies operate reactively by directly regressing actions from current observati…
The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models
Bohang Sun, Max Zhu, Francesco Caso +5
Diffusion large language models promise faster generation by refining many token positions in parallel, but this parallelism introduces a hidden control problem: which proposed tok…
Checkup2Action: A Multimodal Clinical Check-up Report Dataset for Patient-Oriented Action Card Generation
Sike Xiang, Shuang Chen, Kevin Qinghong Lin +4
Routine clinical check-up reports combine laboratory measurements, physiological assessments, imaging findings and visually structured information, but rarely tell patients what to…
Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode
Zeyuan He, Yupeng Chen, Lang Lin +7
Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation efficiency. Beyond the utility benefit…
Distribution-Free Sequential Prediction with Abstentions
Jialin Yu, Moïse Blanchard
We study a sequential prediction problem in which an adversary is allowed to inject arbitrarily many adversarial instances in a stream of i.i.d. instances, but at each round, the l…
MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction
Marc Boubnovski Martell, Josefa Lia Stoisser, Lawrence Phillips +6
Predicting transcriptional responses to unseen genetic perturbations is essential for understanding gene regulation and prioritizing large-scale perturbation experiments. Existing…
Benchmarking at the Edge of Comprehension
Samuele Marro, Jialin Yu, Emanuele La Malfa +8
As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improv…
Permission Manifests for Web Agents
Samuele Marro, Alan Chan, Xinxing Ren +12
The rise of Large Language Model (LLM)-based web agents represents a significant shift in automated interactions with the web. Unlike traditional crawlers that follow simple conven…
Can Large Language Models Express Uncertainty Like Human?
Linwei Tao, Yi-Fan Yeh, Bo Kai +6
Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhanc…
DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model
Sarah Bonna, Yu-Cheng Huang, Ekaterina Novozhilova +11
Ethical intervention prompting has emerged as a tool to counter demographic biases of text-to-image generative AI models. Existing solutions either require to retrain the model or…