No article text was recorded for this version.
parameter-scale reasoning gap
Version 1 of 164 papers64 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Dutch Financial Large Language Model
- Blog: Leveraging Training Data in Few-Shot Prompting for Numerical Reasoning
- Blog: Democratizing Reasoning Ability: Tailored Learning from Large Language Model
- Blog: Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations
- Blog: ScreenAI: A Vision-Language Model for UI and Infographics Understanding
- Blog: References Improve LLM Alignment in Non-Verifiable Domains
- Blog: Eliciting Critical Reasoning in Retrieval-Augmented Generation via Contrastive Explanations
- Blog: Solving Math Word Problems via Cooperative Reasoning induced Language Models
- Blog: The Ability of Large Language Models to Evaluate Constraint-satisfaction in Agent Responses to Open-ended Requests
- Blog: Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models
- Blog: S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
- Blog: Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
- Blog: COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis
- Blog: BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices
- Blog: KoMA: Knowledge-driven Multi-agent Framework for Autonomous Driving with Large Language Models
- Blog: MIRA: A Novel Framework for Fusing Modalities in Medical RAG
- Blog: Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction
- Blog: Cost-efficient Knowledge-based Question Answering with Large Language Models
- Blog: MentalQLM: A lightweight large language model for mental healthcare based on instruction tuning and dual LoRA modules
- Blog: SemEval-2025 Task 8: Question Answering over Tabular Data
- Blog: Distilling LLMs’ Decomposition Abilities into Compact Language Models
- Blog: Towards Policy-Compliant Agents: Learning Efficient Guardrails For Policy Violation Detection
- Blog: It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation
- Blog: Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models
- Blog: Learning Theorem Rationale for Improving the Mathematical Reasoning Capability of Large Language Models
- Blog: Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models
- Blog: Understand the Implication: Learning to Think for Pragmatic Understanding
- Blog: Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review
- Blog: Jellyfish: Instruction-Tuning Local Large Language Models for Data Preprocessing
- Blog: MedGR2: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning
- Blog: Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
- Blog: CSLM: A Framework for Question Answering Dataset Generation through Collaborative Small Language Models
- Blog: Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-consistency Training
- Blog: Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuning
- Blog: Through the Valley: Path to Effective Long CoT Training for Small Language Models
- Blog: Cost-Efficient Serving of LLM Agents via Test-Time Plan Caching
- Blog: Token-Level Accept or Reject: A Micro Alignment Approach for Large Language Models
- Blog: Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
- Blog: Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-Alignment
- Blog: SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding
- Blog: FeRG-LLM : Feature Engineering by Reason Generation Large Language Models
- Blog: Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise: A Case Study on Chinese Legal Domain
- Blog: Probe Then Retrieve and Reason: Distilling Probing and Reasoning Capabilities into Smaller Language Models
- Blog: Variational Open-Domain Question Answering
- Blog: Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs
- Blog: Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding
- Blog: Dataflow-Guided Neuro-Symbolic Language Models for Type Inference
- Blog: Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendation
- Blog: From Individual to Universal: Regularized Multi-view Joint Representation for Multi-view Subspace-Preserving Recovery
- Blog: Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
- Blog: SpatialWebAgent: Leveraging Large Language Models for Automated Spatial Information Extraction and Map Grounding
- Blog: DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models
- Blog: MCC-KD: Multi-CoT Consistent Knowledge Distillation
- Blog: UniCoTT: A Unified Framework for Structural Chain-of-Thought Distillation
- Blog: Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMs
- Blog: Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data
- Blog: Eliciting Harmful Capabilities by Fine-Tuning on Safeguarded Outputs
- Blog: Unlocking Multimodal Mathematical Reasoning via Process Reward Model
- Blog: Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought
- Blog: Intermediate Fine-Tuning Improves Mathematical Reasoning in Smaller Models
Showing 60 of 64 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_parameter_scale_reasoning_gap_5b29e4d8,
title = {parameter-scale reasoning gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-scale-reasoning-gap/rdr_5b29e4d8cc974a61b6e573bfba2ab9c8},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_parameter_scale_reasoning_gap_5b29e4d8_v1,
title = {parameter-scale reasoning gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/parameter-scale-reasoning-gap/rdr_5b29e4d8cc974a61b6e573bfba2ab9c8/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}