The paper examines how Preference Inference (PI) models used in large-scale participatory democracy platforms can alter the perceived consensus and minority support by predicting missing votes. It introduces a collective‑centric evaluation framework that assesses whether inferred votes maintain key properties of the overall preference landscape, rather than focusing solely on individual prediction accuracy. Using the largest multilingual dataset to date—four consultations with over 90,000 participants, 1 million votes, and 22 languages—the study finds that models with similar predictive accuracy can differ markedly in how well they preserve the collective structure, underscoring that accuracy alone is insufficient for evaluating PI in democratic contexts.
By Pierre-Antoine Lequeu, Salim Hafid, Paul Lerner, Nazanin Shafiabadi, Laur\`ene Cave, David Mas, Jean-Philippe Cointet, Benjamin Piwowarski, Fran\c{c}ois Yvon
arXiv:2604. 17289v2 Announce Type: replace Abstract: Supervised fine-tuning of large language models relies on human-annotated data, yet annotation pipelines routinely involve multiple crowdworkers of heterogeneous expertise.
By Sajjad Ghiasvand, Mark Beliaev, Mahnoosh Alizadeh, Ramtin Pedarsani
arXiv:2606. 15741v1 Announce Type: cross Abstract: Narrative question answering (NQA) is a challenging task in natural language processing that requires models to understand long textual contexts, capture relationships across events, and generate coherent responses.
By Molham Mohamed, Ali Hamdi
arXiv:2607. 27783v1 Announce Type: cross Abstract: Large Language Models (LLMs) explore problems through chain-of-thought, but this exploration is buried in unstructured prose.
By Amruta Parulekar, Jinu Lee, Dilek Hakkani-T\"ur, Hari Sundaram
arXiv:2608. 10665v1 Announce Type: new Abstract: Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers.
By Rohit Sinha, Kunal Tilaganji, Tanuja Ganu, Nagarajan Natarajan, Amit Sharma, Vineeth Balasubramanian
Chopthin-Consensus Power Sampling (CCPS) is a new inference-time decoding method for large language models that uses the Chopthin resampler to preserve diversity among particle trajectories. By enforcing an upper bound on weight ratios instead of equal-weight resampling, CCPS maintains a richer set of distinct reasoning paths and guarantees a lower bound on effective sample size. Coupled with a semantic-majority selection mechanism, CCPS achieves higher oracle coverage and matches or surpasses baseline accuracy on multiple reasoning benchmarks.
By Minoo Ahmadi, Seyedarmin Azizi, Erfan Baghaei Potraghloo, Mehdi Kamal, Massoud Pedram
Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth. Existing approaches face a dilemma: methods using only human judgments suffer from heterogeneous expertise and inconsistent rating scales, while methods using only model-generated scores must learn from imperfect proxies or incomplete features.
The paper introduces a test-time aggregation framework for multi-agent reasoning with large language models. It mitigates non-semantic biases by normalizing reasoning traces and injects bias to create decision instability, which signals reliability. The method improves accuracy and token efficiency on several mathematical reasoning benchmarks without requiring validation data or prior model strength knowledge.
By Sungjae Lee, Soheil Abbasloo, Jabin Koo, Jungseul Ok
arXiv:2608. 02455v1 Announce Type: new Abstract: Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth.
By Zejun Xie, Xintong Li, Guang Wang, Desheng Zhang
The paper proposes treating an ensemble of language models as a jury rather than an electorate, where each model’s reliability is inferred from patterns of agreement and disagreement without using labels. Using Expectation Maximisation, the authors estimate each expert’s latent reliability and derive a log‑odds weighted linear scoring rule. On a 1560‑question benchmark, this label‑free approach matches the performance of label‑fitted weights and surpasses the best single model and other label‑free alternatives.
By Alessandro Rozza, Davide Mambelli, Steven Motta, Juri Taresch
arXiv:2604. 09497v2 Announce Type: replace-cross Abstract: Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases.
By Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Emmanuel Malherbe, C\'eline Hudelot, Pierre Colombo
The paper introduces LLM‑PeerReview, an unsupervised ensemble method that selects the best response from multiple LLM-generated candidates by scoring each answer with several LLMs, aggregating those scores via averaging or a graphical model, and choosing the highest-scoring response. The approach is peer‑review inspired, transparent, and interpretable, and it outperforms the Smoothie‑Global model by 6.9%–7.3% across factual recall QA, math reasoning, and instruction‑following tasks. The authors also provide a curated benchmark suite of 12 ensemble methods evaluated on four datasets and three task families to aid reproducibility.
By Zhijun Chen, Zeyu Ji, Qianren Mao, Hao Wu, Jinhuan Song, Junhang Cheng, Bangjie Qin, Zhuoran Li, Jingzheng Li, Kai Sun, Zizhe Wang, Yikun Ban, Zhu Sun, Xiangyang Ji, Hailong Sun, Xiao Huang