Temporal preference in Qwen3-4B-Instruct-2507 localizes to layers 17–35 (especially L24 attention), has curved residual-stream geometry, is behaviorally unstable, and can be bidirectionally steered.
Linear Represen- tations of Political Perspective Emerge in Large Language Models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
A linear probe trained on 190k congressional tweets identifies a partisan direction in Llama 3.1 8B layer 18 that can be causally ablated or amplified to reverse or shift the model's political output.
Empirical test on real news histories shows unconstrained LLM reranking amplifies conspiratorial content exposure while prompt constraints can increase ideological diversity with limited relevance cost.
Early layers of language models predict early-pass human reading times better than surprisal, with surprisal superior for late-pass measures and strong variation by language.
A review synthesizing opinion dynamics research, categorizing models by macroscopic outcomes and microscopic mechanisms while connecting to empirical data and emerging AI tools.
citing papers explorer
-
Temporal Preference Concepts and their Functions in a Large Language Model
Temporal preference in Qwen3-4B-Instruct-2507 localizes to layers 17–35 (especially L24 attention), has curved residual-stream geometry, is behaviorally unstable, and can be bidirectionally steered.
-
The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model
A linear probe trained on 190k congressional tweets identifies a partisan direction in Llama 3.1 8B layer 18 that can be causally ablated or amplified to reverse or shift the model's political output.
-
LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems
Empirical test on real news histories shows unconstrained LLM reranking amplifies conspiratorial content exposure while prompt constraints can increase ideological diversity with limited relevance cost.
-
Probing for Reading Times
Early layers of language models predict early-pass human reading times better than surprisal, with surprisal superior for late-pass measures and strong variation by language.
-
Opinion dynamics: Statistical physics and beyond
A review synthesizing opinion dynamics research, categorizing models by macroscopic outcomes and microscopic mechanisms while connecting to empirical data and emerging AI tools.