Abulhair Saparov

Identifiers

• name variant Abulhair Saparov 0.60 · backfill

Papers (19)

1. Learning to Reason Efficiently with A* Post-Training cs.AI · 2026 · author #3
2. Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key cs.AI · 2026 · author #7
3. Transformers Can Learn Connectivity in Some Graphs but Not Others cs.CL · 2025 · author #2
4. Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting cs.CL · 2025 · author #2
5. Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective cs.LG · 2025 · author #18
6. Transformers Struggle to Learn to Search cs.CL · 2024 · author #1
7. MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs cs.LG · 2024 · author #4
8. LLMs Are Prone to Fallacies in Causal Inference cs.CL · 2024 · author #2
9. Foundational Challenges in Assuring Alignment and Safety of Large Language Models cs.LG · 2024 · author #2
10. Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? cs.CL · 2024 · author #7
11. Noisy Exemplars Make Large Language Models More Robust: A Domain-Agnostic Behavioral Analysis cs.CL · 2023 · author #2
12. Personas as a Way to Model Truthfulness in Language Models cs.CL · 2023 · author #3
13. Retrieval-Augmented Chain-of-Thought in Semi-structured Domains cs.CL · 2023 · author #2
14. World Models for Math Story Problems cs.CL · 2023 · author #3
15. Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples cs.CL · 2023 · author #1
16. Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought cs.CL · 2022 · author #1
17. Towards General Natural Language Understanding with Probabilistic Worldbuilding cs.CL · 2021 · author #1
18. Jelly Bean World: A Testbed for Never-Ending Learning cs.LG · 2020 · author #2
19. A Probabilistic Generative Grammar for Semantic Parsing cs.CL · 2016 · author #1

Mentions

• 2506.14965 #18 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2412.04703 #1 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2306.04347 #3 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2410.13502 #4 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2404.09932 #2 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2406.12158 #2 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2401.18070 #7 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2310.18168 #3 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2305.15269 #1 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2311.00258 #2 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2310.14435 #2 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2210.01240 #1 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 1606.06361 #1 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2105.02486 #1 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2002.06306 #2 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2605.24597 #3 · arxiv_oai · confidence 0.70 Abulhair Saparov
• 2605.06638 #7 · arxiv_oai · confidence 0.70 Abulhair Saparov

Frequent Coauthors

• He He 6 shared papers
• Andreas Opedal 4 shared papers
• Mrinmaya Sachan 4 shared papers
• Nitish Joshi 4 shared papers
• Bernhard Sch\"olkopf 3 shared papers
• Najoung Kim 3 shared papers
• Haruki Shirakami 2 shared papers
• Javier Rando 2 shared papers
• Richard Yuanzhe Pang 2 shared papers
• Ryan Cotterell 2 shared papers
• Seyed Mehran Kazemi 2 shared papers
• Vishakh Padmakumar 2 shared papers
• Alan Chan 1 shared papers
• Aleksandar Petrov 1 shared papers
• Alessandro Stolfo 1 shared papers
• Alexander Pan 1 shared papers
• Amit Roy 1 shared papers
• Anton Korinek 1 shared papers
• Atoosa Kasirzadeh 1 shared papers
• Benjamin L. Edelman 1 shared papers