LLM Digest

Story

arxiv_agent_systems_research · Nov 11, 2026 · paper

Source brief

Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance Throttling

arxiv.orgNov 11, 2026
original source linked

In brief

A benchmark score is commonly read as a proxy for model capability. We study the inverse problem: can a model be driven to a target score, and do its failures resemble those of a naturally weaker model? We operationalize believable performance reduction along three axes: target c

Read the original at arxiv.org →Open in live feed Read that day’s brief

Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance Throttling

Earlier in this thread 4 items

Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them

Aligning Language Models with General Preferences: An Empirical Study of Direct Nash Optimization

An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks

How Well Do Decision Models Transfer to Vietnamese? An Empirical Study of Text Classification