LONSREX introduces a metric-based pipeline to identify necessary and sufficient rationales when creating training data for fine-tuning LLMs on explainable misinformation detection, addressing limitations of naive label-based filtering.
Deconstructing long chain-of-thought: A structured reasoning optimization framework for long cot distillation
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
CoRD uses collaborative multi-teacher step-wise decoding with perplexity-guided beam search to generate higher-quality Long-CoT data that lets smaller models reach near-teacher performance with less supervision.
Average log probability selection for LLM reasoning datasets is confounded by step length because longer steps dilute low-probability first tokens; ASLEC-DROP and ASLEC-CASL remove this bias.
Training-Trajectory-Aware Token Selection (T3S) reconstructs the token-level training objective to overcome a performance bottleneck in continual distillation of reasoning capabilities from large to small language models.
TRUST is a decentralized AI auditing framework that decomposes reasoning into HDAGs, maps agent interactions via the DAAN protocol to CIGs, and uses stake-weighted multi-tier consensus to achieve 72.4% accuracy while proving a Safety-Profitability Theorem that rewards honest auditors.
Reasoning LLMs aggregate social biases through stereotype repetition and irrelevant information injection in their thinking processes, and a self-review prompt mitigates this on BBQ, StereoSet, and BOLD benchmarks.
citing papers explorer
-
Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection
LONSREX introduces a metric-based pipeline to identify necessary and sufficient rationales when creating training data for fine-tuning LLMs on explainable misinformation detection, addressing limitations of naive label-based filtering.
-
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
CoRD uses collaborative multi-teacher step-wise decoding with perplexity-guided beam search to generate higher-quality Long-CoT data that lets smaller models reach near-teacher performance with less supervision.
-
On the Step Length Confounding in LLM Reasoning Data Selection
Average log probability selection for LLM reasoning datasets is confounded by step length because longer steps dilute low-probability first tokens; ASLEC-DROP and ASLEC-CASL remove this bias.
-
Training-Trajectory-Aware Token Selection
Training-Trajectory-Aware Token Selection (T3S) reconstructs the token-level training objective to overcome a performance bottleneck in continual distillation of reasoning capabilities from large to small language models.
-
TRUST: A Framework for Decentralized AI Service v.0.1
TRUST is a decentralized AI auditing framework that decomposes reasoning into HDAGs, maps agent interactions via the DAAN protocol to CIGs, and uses stake-weighted multi-tier consensus to achieve 72.4% accuracy while proving a Safety-Profitability Theorem that rewards honest auditors.
-
Investigating Thinking Behaviours of Reasoning-Based Language Models for Social Bias Mitigation
Reasoning LLMs aggregate social biases through stereotype repetition and irrelevant information injection in their thinking processes, and a self-review prompt mitigates this on BBQ, StereoSet, and BOLD benchmarks.