collaborators

12 papers

cs.CL2026

Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models

Alexandrine Fortier, Hazel Chen, Peter West

The lack of diversity in LM content is widely attributed to the alignment process, but how and where exactly in the pipeline this collapse begins is unknown. We argue that output h…

cs.CL2026

UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs

Amirhossein Abaskohi, Amirhossein Dabiriaghdam, Liang Luo +4

We introduce UnpredictaBench, an evaluation that tests the ability of large language models (LLMs) to capture true underlying distributions. As LLMs are increasingly used as substi…

cs.CL2026

SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference

Amirhossein Abaskohi, Giuseppe Carenini, Peter West +1

Large language models increasingly operate over long contexts, where the KV cache becomes a dominant memory bottleneck: its size grows linearly with sequence length and must be ret…

cs.CL2026

Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization

Kunal Samanta, Ari Holtzman, Peter West

The alignment of language models is typically studied through the lens of capability benchmarks, but the dynamics of how models change during post-training remain poorly understood…

cs.CL2026

Resolution Thresholds in VLM Detection of Harmful ASCII Art Across Construction Modes and Languages

Yikai Hua, Peter West

Large Vision-Language Models (VLMs) are increasingly deployed as content moderation tools, yet they remain vulnerable to jailbreak attacks in which harmful text is visually encoded…

cs.CL2026

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3

Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search…