Hugging Face Trending Papers August 19, 2026

Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model

Read the original on Hugging Face Trending Papers →

The study investigates how demographic identity is represented in a language model, using representational similarity analysis against Pew survey data across 169 demographic cells. It finds that standard last‑token read‑outs underestimate the model’s fidelity, while specific attention heads (notably L11 H16) capture demographic structure more accurately, though race‑based types remain weak. Causal interventions reveal that high fidelity does not guarantee causal use, and a 128‑dimensional probe of a single head improves alignment with survey truth but fails to recover per‑question group ordering.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

llms

arXiv AI

Jul 22

Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling

arXiv:2607. 18310v1 Announce Type: cross Abstract: Synthetic-population tools increasingly run every individual as an independent large language model (LLM) agent.

By Gurkan Ozkan

llms agents

arXiv AI

Jul 21

A small language model detects behavioural faithfulness gaps that frontier judges and human raters miss

arXiv:2607. 09306v2 Announce Type: replace-cross Abstract: Whether a language model behaves as it claims is a judgement on which independent human raters cannot agree (Fleiss kappa = 0.

By Kwan Soo Shin, In Seok Kang, Yunkyung Min, Munho Lee

llms benchmarks

arXiv Machine Learning

Jul 16

Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering

arXiv:2607. 13568v1 Announce Type: cross Abstract: Can a language model estimate its familiarity with an entity before generating an answer?

By Grzegorz Brzezinka

llms

arXiv AI

Jun 6

The Self-Correction Illusion: LLMs Correct Others but Not Themselves

arXiv:2606. 05976v1 Announce Type: new Abstract: Recent work shows that LLM agents struggle to correct errors in their own reasoning traces yet show markedly higher correction rates when identical claims appear under external sources.

By Kuan-Yen Chen, Fang-Yi Su, Jung-Hsien Chiang

llms agents

Hugging Face Trending Papers

Jul 8

Dissociating the Internal Representations of Sycophancy in LLMs

Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect. While sycophancy is often treated as a single defined behavior, it can manifest in substantially distinct ways and circumstances, raising the question of whether this multi-faceted nature is reflected in its internal mechanisms.

llms

arXiv AI

Aug 7

Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations

arXiv:2604. 17359v2 Announce Type: replace-cross Abstract: Language models asked to simulate psychiatric patients produce cases that survive inspection one at a time and populations that match no real one.

By Patrick Keough

llms benchmarks

One email a morning, machine-written

Related stories

Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling

A small language model detects behavioural faithfulness gaps that frontier judges and human raters miss

Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering

The Self-Correction Illusion: LLMs Correct Others but Not Themselves

Dissociating the Internal Representations of Sycophancy in LLMs

Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations