ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
cs.AI, cs.HC
Submitted: 2026-02-23
Updated: 2026-11-07
Code: https://github.com/MaartenGr/BERTopic5https:
Terminology
Sources
- Human Expertise in Algorithmic Prediction
- Top2Vec: Distributed Representations of Topics
- Towards Human-AI Complementarity in Matching Tasks
- Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
- BERTopic: Neural topic modeling with a class-based TF-IDF procedure
- Explaining and Improving Information Complementarities in Multi-Agent Decision-making
- On the Effect of Information Asymmetry in Human-AI Teams
- Designing Closed Human-in-the-loop Deferral Pipelines
- Causal Inference on Outcomes Learned from Text
- Sparse Autoencoders for Hypothesis Generation
- TopicGPT: A Prompt-based Topic Modeling Framework
- The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Autoencoding Variational Inference For Topic Models
- OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
- Hypothesis Generation with Large Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents