780 citations · 883 across the 48 of their papers we have counts for
11 papers · 1 filter
LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems
Liron Soffer, Ravid Shwartz-Ziv, Chen Shani
Large language models (LLMs) are increasingly deployed in multi-agent settings, where agents observe and influence one another, making social influence a key dimension of AI behavi…
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…
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…
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
Amit LeVi, Raz Lapid, Rom Himelstein +3
Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste…
The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs
Denis Janiak, Jakub Binkowski, Albert Sawczyn +3
Large language models (LLMs) have revolutionized natural language processing, yet their tendency to hallucinate poses serious challenges for reliable deployment. Despite numerous h…
From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
Chen Shani, Liron Soffer, Dan Jurafsky +2
Humans organize knowledge into compact conceptual categories that balance compression with semantic richness. Large Language Models (LLMs) exhibit impressive linguistic abilities,…
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…
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
Colin White, Samuel Dooley, Manley Roberts +15
Test set contamination, wherein test data from a benchmark ends up in a newer model's training set, is a well-documented obstacle for fair LLM evaluation and can quickly render ben…
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
Allen Roush, Yusuf Shabazz, Arvind Balaji +7
We introduce OpenDebateEvidence, a comprehensive dataset for argument mining and summarization sourced from the American Competitive Debate community. This dataset includes over 3.…
When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models
Sunny Sanyal, Ravid Shwartz-Ziv, Alexandros G. Dimakis +1
Large Language Models (LLMs) are known for their performance, but we uncover a significant structural inefficiency: a phenomenon we term attention collapse. In many pre-trained dec…