BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Or Levi

Or Levi contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceComputation and LanguageSocial and Information Networks

Trust snapshot

Quick read

Trust 15 - UnverifiedVerification L1Unclaimed author
3works
0followers
3topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

3 published item(s)

preprint2026arXiv

HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model

We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Training employs a three-phase easy-to-hard curriculum with continuous anti-forgetting anchoring, followed by supervised fine-tuning on 2 million bilingual Hebrew--English samples. The curriculum ordering alone yields a 3-point aggregate benchmark gain over the reversed configuration. Hebatron achieves a Hebrew reasoning average of 73.8\%, outperforming DictaLM-3.0-24B-Thinking (68.9\%) and remaining competitive with Gemma-3-27B-IT on GSM8K-HE and Israeli Trivia, while activating only 3B parameters per forward pass across a 30B-parameter model, delivering approximately 9 times higher inference throughput at native context lengths up to 65,536 tokens. To our knowledge, this is the first language-specific adaptation of the Nemotron-3 architecture for any target language, and the first open-weight Hebrew-specialized MoE model with native long-context support. Model weights are released openly to support further research in Hebrew and Semitic-language NLP.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systems

As LLMs are increasingly integrated into human-in-the-loop content moderation systems, a central challenge is deciding when their outputs can be trusted versus when escalation for human review is preferable. We propose a novel framework for supervised LLM uncertainty quantification, learning a dedicated meta-model based on LLM Performance Predictors (LPPs) derived from LLM outputs: log-probabilities, entropy, and novel uncertainty attribution indicators. We demonstrate that our method enables cost-aware selective classification in real-world human-AI workflows: escalating high-risk cases while automating the rest. Experiments across state-of-the-art LLMs, including both off-the-shelf (Gemini, GPT) and open-source (Llama, Qwen), on multimodal and multilingual moderation tasks, show significant improvements over existing uncertainty estimators in accuracy-cost trade-offs. Beyond uncertainty estimation, the LPPs enhance explainability by providing new insights into failure conditions (e.g., ambiguous content vs. under-specified policy). This work establishes a principled framework for uncertainty-aware, scalable, and responsible human-AI moderation workflows.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Automatically Identifying Political Ads on Facebook: Towards Understanding of Manipulation via User Targeting

The reports of Russian interference in the 2016 United States elections brought into the center of public attention concerns related to the ability of foreign actors to increase social discord and take advantage of personal user data for political purposes. It has raised questions regarding the ways and the extent to which data can be used to create psychographical profiles to determine what kind of advertisement would be most effective to persuade a particular person in a particular location for some political event. In this work, we study the political ads dataset collected by ProPublica, an American nonprofit newsroom, using a network of volunteers in the period before the 2018 US midterm elections. We first describe the main characteristics of the data and explore the user attributes including age, region, activity, and more, with a series of interactive illustrations. Furthermore, an important first step towards understating of political manipulation via user targeting is to identify politically related ads, yet manually checking ads is not feasible due to the scale of social media advertising. Consequently, we address the challenge of automatically classifying between political and non-political ads, demonstrating a significant improvement compared to the current text-based classifier used by ProPublica, and study whether the user targeting attributes are beneficial for this task. Our evaluation sheds light on questions, such as how user attributes are being used for political ads targeting and which users are more prone to be targeted with political ads. Overall, our contribution of data exploration, political ad classification and initial analysis of the targeting attributes, is designed to support future work with the ProPublica dataset, and specifically with regard to the understanding of political manipulation via user targeting.

0 citations0 reviewsNo code linkedOpen access