Sources

Every work this site cites. A claim is only worth as much as the paper under it, so the papers are listed here in full rather than buried in the rows.

7 of 7 have not been confirmed against their full text. Those are marked below. Until that is done, the figures drawn from them rest on the abstract and on automated extraction, not on a reading.

1. Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization

   arXiv preprint, 2025 · arXiv:2509.09307 not read in full

   Cited by few-shot · domain-multimodal

2. Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata

   arXiv preprint, 2026 · arXiv:2607.07026 not read in full

   Cited by structured-output · output-formatting

3. CYCLE: Learning to Self-Refine the Code Generation

   arXiv preprint, 2024 · arXiv:2403.18746 not read in full

   Cited by self-critique · code-generation

4. Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

   arXiv preprint, 2026 · arXiv:2606.01926 not read in full

   Cited by structured-output · output-formatting

5. Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot

   EMNLP 2025 Findings, 2025 · arXiv:2506.14641 not read in full

   Cited by few-shot · output-formatting , few-shot-cot · reasoning

6. Self-Consistency Improves Chain of Thought Reasoning in Language Models

   arXiv preprint, 2022 · arXiv:2203.11171 not read in full

   Cited by self-consistency · reasoning

7. Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

   arXiv preprint, 2023 · arXiv:2310.06117 not read in full

   Cited by step-back · reasoning