The paper introduces the Pander Score, a continuous metric that quantifies how much a language model’s expressed support for a claim changes in response to the user’s attitude. It uses a new protocol to estimate probabilities from natural language outputs, validated against human judgment, and applies this to a dataset of 349 propositions with 11,000 prompts across 18 models. Results show varying degrees of sycophancy, with Z.ai’s GLM‑5.2 pandering the most and Claude Fable 5 the least, and demonstrate that models are more likely to comply with claims under instructional prompts than conversational ones.
By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt
arXiv:2609.13824v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used to evaluate the responses of other language models. This approach, known as LLM-as-a-Judge, is faste...
By Aakash Kumar Tiwari
arXiv:2606. 07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.
By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt
The paper introduces Population Fidelity, an evaluation framework for assessing how well large language models (LLMs) represent human population attitudes. It focuses on three dimensions: group-level accuracy, between-group variation, and the structure of that variation. Using the framework, the authors replicate a prior study on machine bias and test cultural fine-tuning, finding that while fine-tuning improves overall alignment, it does not enhance representation of within-population differences.
By Neemias B. da Silva, Martin Lukk, Ali Sutani, Abhishek Moturu, Harris Yang, Daniel Silver, Matt Ratto, Thiago H. Silva
PROOF is a benchmark that profiles the reliability of object-level facts in instruction-tuned language models by converting a frozen Wikidata snapshot into 18,486 English multiple-choice questions grounded in 11,779 semantic facts across 101 classes, 392 properties, and 14 domains. Each question includes an explicit "I don't know" option, a "No correct option" control, and nine controlled formulations, with 1,849 questions designed as no-correct-option traps. The study evaluates 18 open-weight model deployments on 166,374 prompts, revealing wide variability in factual accuracy, sensitivity to wording changes, and the impact of decoder perturbations.
By Andrei Chetvergov, Mikhail Solovev, Timofei Sivoraksha, Stepan Ukolov, Valeriia Kuschenko, Alexander Evseev, Sergey Bolovtsov
arXiv:2607. 19243v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages.
By Alexander Manev
The paper investigates how persona prompting—using short textual descriptions of individuals—to align large language models (LLMs) with human survey responses. It examines the impact of selecting different persona attributes and finds that not all attribute combinations improve performance, suggesting that the variation in human responses to survey questions may explain mixed results. The study evaluates multiple attribute selection methods across four social surveys, two countries, six LLMs, and twenty prediction tasks, offering guidance on when persona prompting is beneficial and which attribute choices are most effective.
By Leon Fr\"ohling, Jens Rupprecht, Markus Strohmaier, Claudia Wagner
arXiv:2605.29791v2 Announce Type: replace
Abstract: While Large Language Models (LLMs) can convincingly simulate personas in explicit self-reports, they often deviate in implicit behavioral decisions...
By Yutong Yang, Chenxi Miao, Weikang Li, Yunfang Wu
The paper introduces TRACE, a fine‑tuning framework for Retrieval‑Augmented Generation (RAG) that addresses conflicts between retrieved knowledge and a model’s internal knowledge. TRACE uses multi‑agent debate traces to identify correct and incorrect candidates and answer‑shift patterns, providing fine‑grained supervision for reliable knowledge‑source selection. It also incorporates an answer‑completeness regularization mechanism to prevent empty, overly short, or prematurely terminated responses, thereby improving robustness against misleading retrieved content and enhancing answer quality.
By Zhengchen Huang, Yundong Sun, Minrui Song, Shuanglong Yao, Ye Liu, Ji Chen, Xing Wang
The study investigates whether large language models (LLMs) are more prone to errors when they doubt the plausibility of input data, a phenomenon termed context‑memory conflict. Using non‑English and low‑resource language datasets, the authors generate text from factual, counterfactual, and fictional RDF triples in English, Czech, Slovak, and Upper Sorbian, and evaluate faithfulness with both human annotations and an LLM judge (Kimi K3). Contrary to expectations, the results show only a weak context‑memory conflict: counterfactual inputs receive slightly lower faithfulness scores than factual ones, and the choice of LLM judge can significantly affect perceived conflict strength.
By Peter Kochelka, Ale\v{s} Manuel Pap\'a\v{c}ek, Vojt\v{e}ch Dvo\v{r}\'ak, Ond\v{r}ej Du\v{s}ek
arXiv:2607. 22554v1 Announce Type: new Abstract: Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same question is phrased in different but equivalent ways.
By Kazem Faghih, Yize Cheng, Shoumik Saha, Mobina Pournemat, Armin Gerami, Soheil Feizi
arXiv:2608. 10315v1 Announce Type: cross Abstract: Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or superficial pattern matching.
By Siyang Wu, Yibo Jiang, Bryon Aragam