1 citations · 3 across the 11 of their papers we have counts for
11 papers
Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time
Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder +2
Large Language Models generate text autoregressively, but open-ended generation is prone to verbatim looping, in which models repeat spans already present in context. Standard defe…
XTC: Head-Aware Sampling by Excluding Top Choices
Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder +2
Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-probability tail. These strategies…
CoGate: Confidence-Gated Co-Decoding for Secure Code Generation
Minghao Hu, Lannan Luo, Allen Roush +1
Large language models are widely used for code generation, but they can also produce insecure programs due to patterns learned from their pretraining data. Decoding-time steering h…
Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling
Phillip Howard, Xin Su, Allen Roush +3
Recent advances in truncation-based sampling have helped mitigate drawbacks of high-temperature sampling such as neural text degeneration, thereby enabling greater diversity withou…
Mirage Probes: How Vision Models Fake Visual Understanding
Daniel Ben-Levi, Judah Goldfeder, Weiliang Zhao +5
Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores with…
Do Multi-Agents Dream of Electric Screens? Achieving Perfect Accuracy on AndroidWorld Through Task Decomposition
Pierre-Louis Favreau, Jean-Pierre Lo, Clement Guiguet +5
We present Minitap, a multi-agent system that achieves 100% success on the AndroidWorld benchmark, the first to fully solve all 116 tasks and surpassing human performance (80%). We…
A superpersuasive autonomous policy debating system
Allen Roush, Devin Gonier, John Hines +4
The capacity for highly complex, evidence-based, and strategically adaptive persuasion remains a formidable great challenge for artificial intelligence. Previous work, like IBM Pro…
Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
Samuel Paech, Allen Roush, Judah Goldfeder +1
Widespread LLM adoption has introduced characteristic repetitive phraseology, termed "slop," which degrades output quality and makes AI-generated text immediately recognizable. We…
Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests
Alexandra Yost, Shreyans Jain, Shivam Raval +6
Persona conditioning is widely used to steer large language model (LLM) behavior, but it is unclear whether it induces stable behavioral structure or superficial variation. We prop…
NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks
Alex Reneau, Jerry Yao-Chieh Hu, Zhongfang Zhuang +6
In deep learning, processing multidimensional inputs (e.g., images, medical scans, and time series) is an important task that often requires flattening the inputs. We introduce $\m…
Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs
Minh Nhat Nguyen, Andrew Baker, Clement Neo +3
Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. Popular sampling methods like top-p…