Problem Solving
Parameter Competition Balancing for Model Merging
Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model.
Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
Further, IPRM's internal computations can be visualized across reasoning steps, aiding interpretability and diagnosis of its errors.
Unchosen Experts Can Contribute Too: Unleashing MoE Models ' Power by Self-Contrast
Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency.
MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations
However, there's a lack of insight into how these models perform in terms
Self-Discover: Large Language Models Self-Compose Reasoning Structures Pei Zhou
Full BBH results are in Appendix C Table 3.
Instance-adaptive Zero-shot Chain-of-Thought Prompting
CoT reasoning scheme by adaptively differentiating good and bad prompts.
Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?
Our findings on NoRa dataset reveal a prevalent vulnerability to such noise among current LLMs, with existing robust methods like self-correction and self-consistency showing limited efficacy.
Learning Goal-Conditioned Representations for Language Reward Models
Nevertheless, it is unclear how improved representation learning can benefit reinforcement learning from human feedback on language models.