Research map / Large language models / Alignment and preferences
Align to Structure: Aligning Large Language Models with Structural Information
Zae Myung Kim, Anand Ramachandran, Farideh Tavazoee, Joo-Kyung Kim, Oleg Rokhlenko, Dongyeop Kang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| align with graph-level discourse reward (authorship classifier on discourse motifs) | Qwen2-1.5B-Instruct · GovReport | ROUGE-1: 53.21 -> 55.86 | Improved |
| align with surface-level text structure reward | Qwen2-1.5B-Instruct · GovReport | ROUGE-1: 53.21 -> 55.45 | Improved |
| align with off-the-shelf OpenAssistant RLHF reward model | Qwen2-1.5B-Instruct · GovReport | ROUGE-1: 53.21 -> 53.25 | No clear effect |
| align with graph-level discourse reward | Qwen2-1.5B-Instruct · essay quality, GPT-4o pairwise | win rate | Improved |
| align with surface-level reward | Qwen2-1.5B-Instruct · essay quality, GPT-4o pairwise | win rate | Improved |
| apply second-stage alignment with the other structural reward (two-step) (ablation) | SA_S / SA_G · essay quality, GPT-4o pairwise | win rate | No clear effect |
| use dense discourse-motif token rewards with graph reward vs standard PPO (ablation) | Qwen2-1.5B-Instruct · human-distinctive motif proportion in training batches | motif proportion | Improved |
Closest papers by meaning
- Test-Time Alignment for Large Language Models via Textual Model Predictive Control (ICLR 2026 · similarity 0.87)
- W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search (AAAI 2026 · similarity 0.87)
- RMB: Comprehensively benchmarking reward models in LLM alignment (ICLR 2025 · similarity 0.87)
- Embedding-Aligned Language Models (NeurIPS 2024 · similarity 0.87)
- Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback (AAAI 2025 · similarity 0.86)
- Exploring Intrinsic Alignments Within Text Corpus (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
