<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="3.10.0">Jekyll</generator><link href="https://gililior.github.io/feed.xml" rel="self" type="application/atom+xml" /><link href="https://gililior.github.io/" rel="alternate" type="text/html" /><updated>2026-08-26T08:52:17-07:00</updated><id>https://gililior.github.io/feed.xml</id><title type="html">Gili Lior</title><subtitle>personal description</subtitle><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><entry><title type="html">Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning</title><link href="https://gililior.github.io/agentic-automata-learning/" rel="alternate" type="text/html" title="Can LLM Agents Infer World Models? Evidence from Agentic Automata Learning" /><published>2026-06-15T00:00:00-07:00</published><updated>2026-06-15T00:00:00-07:00</updated><id>https://gililior.github.io/agentic-automata-learning</id><content type="html" xml:base="https://gililior.github.io/agentic-automata-learning/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">Extending Item Response Theory for Efficient and Meaningful Multilingual Evaluation</title><link href="https://gililior.github.io/multilingual-irt/" rel="alternate" type="text/html" title="Extending Item Response Theory for Efficient and Meaningful Multilingual Evaluation" /><published>2026-06-14T00:00:00-07:00</published><updated>2026-06-14T00:00:00-07:00</updated><id>https://gililior.github.io/multilingual-irt</id><content type="html" xml:base="https://gililior.github.io/multilingual-irt/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation</title><link href="https://gililior.github.io/prompt-suite/" rel="alternate" type="text/html" title="PromptSuite: A Task-Agnostic Framework for Multi-Prompt Generation" /><published>2025-07-20T00:00:00-07:00</published><updated>2025-07-20T00:00:00-07:00</updated><id>https://gililior.github.io/prompt-suite</id><content type="html" xml:base="https://gililior.github.io/prompt-suite/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments</title><link href="https://gililior.github.io/reliable-eval/" rel="alternate" type="text/html" title="ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments" /><published>2025-05-28T00:00:00-07:00</published><updated>2025-05-28T00:00:00-07:00</updated><id>https://gililior.github.io/reliable-eval</id><content type="html" xml:base="https://gililior.github.io/reliable-eval/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">WildIFEval: Instruction Following in the Wild</title><link href="https://gililior.github.io/wild-if-eval/" rel="alternate" type="text/html" title="WildIFEval: Instruction Following in the Wild" /><published>2025-03-09T00:00:00-08:00</published><updated>2025-03-09T00:00:00-08:00</updated><id>https://gililior.github.io/wild-if-eval</id><content type="html" xml:base="https://gililior.github.io/wild-if-eval/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">Comparing the Framing Effect in Humans and LLMs on Naturally Occurring Texts</title><link href="https://gililior.github.io/framing/" rel="alternate" type="text/html" title="Comparing the Framing Effect in Humans and LLMs on Naturally Occurring Texts" /><published>2025-02-24T00:00:00-08:00</published><updated>2025-02-24T00:00:00-08:00</updated><id>https://gililior.github.io/framing</id><content type="html" xml:base="https://gililior.github.io/framing/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">Computation or Weight Adaptation? Rethinking the Role of Plasticity in Learning</title><link href="https://gililior.github.io/cognitive-icl/" rel="alternate" type="text/html" title="Computation or Weight Adaptation? Rethinking the Role of Plasticity in Learning" /><published>2024-03-07T00:00:00-08:00</published><updated>2024-03-07T00:00:00-08:00</updated><id>https://gililior.github.io/cognitive-icl</id><content type="html" xml:base="https://gililior.github.io/cognitive-icl/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">SEAM: A Stochastic Benchmark for Multi-Document Tasks</title><link href="https://gililior.github.io/SEAM/" rel="alternate" type="text/html" title="SEAM: A Stochastic Benchmark for Multi-Document Tasks" /><published>2024-03-07T00:00:00-08:00</published><updated>2024-03-07T00:00:00-08:00</updated><id>https://gililior.github.io/SEAM</id><content type="html" xml:base="https://gililior.github.io/SEAM/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">Leveraging Collection-Wide Similarities for Unsupervised Document Structure Extraction</title><link href="https://gililior.github.io/acl-conceptual-toc/" rel="alternate" type="text/html" title="Leveraging Collection-Wide Similarities for Unsupervised Document Structure Extraction" /><published>2024-02-21T00:00:00-08:00</published><updated>2024-02-21T00:00:00-08:00</updated><id>https://gililior.github.io/acl-conceptual-toc</id><content type="html" xml:base="https://gililior.github.io/acl-conceptual-toc/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry><entry><title type="html">Comparing Humans and Models on a Similar Scale: Towards Cognitive Gender Bias Evaluation in Coreference Resolution</title><link href="https://gililior.github.io/cogsci-gender-bias/" rel="alternate" type="text/html" title="Comparing Humans and Models on a Similar Scale: Towards Cognitive Gender Bias Evaluation in Coreference Resolution" /><published>2023-05-24T00:00:00-07:00</published><updated>2023-05-24T00:00:00-07:00</updated><id>https://gililior.github.io/cogsci-gender-bias</id><content type="html" xml:base="https://gililior.github.io/cogsci-gender-bias/"><![CDATA[]]></content><author><name>Gili Lior</name><email>gili.lior96@gmail.com</email></author><summary type="html"><![CDATA[]]></summary></entry></feed>