Entity · paper

Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints

paperactiveprovisionaldo-language-models-dream-of-binding-molecules-benchmarking-llms-under-spatial-constraints-8591ced0·1 events·first seen Jul 21, 2026

Aliases: Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints

Co-occurring entities

3D-Fit

More like this (12)

Co-LMLM: Continuous-Query Limited Memory Language Models Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs Diffusion Language Models A sleep-like consolidation mechanism for LLMs SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model Self-Compacting Language Model Agents Reasoning Language Models Towards Root Memories: Benchmarking and Enhancing Implicit Logical Memory Retrieval for Personalized LLMs Multimodal Large Language Models Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs Civil Court Simulation with Large Language Models

Recent events (1)

5arXiv · cs.CL·Jul 21, 2026·source ↗

3D-Fit benchmark evaluates LLMs on spatially-constrained drug molecule generation

A new arXiv preprint introduces 3D-Fit, a token-efficient benchmarking strategy for evaluating general-purpose LLMs on structure-based drug design (SBDD) tasks requiring 3D spatial reasoning. The study compares LLMs against specialized diffusion model baselines on pocket-conditioned ligand generation with constraints including anchor fragments, pharmacophore points, and mandatory pocket-ligand interactions. Results show LLMs still lag behind state-of-the-art diffusion models but demonstrate promising ability to handle multiple simultaneous spatial constraints, suggesting a viable path for LLM-based molecular design.

Evaluation and Benchmarking 3D-Fit Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints