LLM chain-of-thought crosses a commitment boundary early; subsequent steps are epiphenomenal, enabling early-exit that shortens traces 55% with negligible performance change.
ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios , volume=
6 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
6
Pith papers citing it
5
external citations · OpenAlex
years
2026 6verdicts
UNVERDICTED 6representative citing papers
ACTS models LLM reasoning control as an MDP solved by a controller agent initialized on synthetic multi-budget trajectories and refined with budget-conditioned RL, achieving token savings while matching full-reasoning accuracy.
AcquisitionSynthesis uses acquisition functions as rewards to train generators that produce higher-quality synthetic data, delivering 2-7% gains on math, medical QA, and coding tasks with improved robustness to forgetting.
SEMJ is a self-evolving multilingual LLM judge that turns cross-lingual inconsistency into iterative self-reflection, outperforming voting and reflection baselines on accuracy and consistency.
MLP activations measured as massive activations or first four moments correlate weakly (max |Spearman| = 0.33) with in-context example quality across Llama-3.2-3B, Qwen2.5-3B, and multiple classification/generative tasks, so activation-based active learning should not be used for ICL.
The paper introduces a three-source decomposition showing that answer flips in multi-agent LLM debate include 37% spontaneous instability and 29% harmful conformity, with even vacuous reasoning persuading 20-39% of resistant agents and interventions reducing harmful conformity by 13.6 points.
citing papers explorer
-
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
LLM chain-of-thought crosses a commitment boundary early; subsequent steps are epiphenomenal, enabling early-exit that shortens traces 55% with negligible performance change.
-
Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning
ACTS models LLM reasoning control as an MDP solved by a controller agent initialized on synthetic multi-budget trajectories and refined with budget-conditioned RL, achieving token savings while matching full-reasoning accuracy.
-
AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
AcquisitionSynthesis uses acquisition functions as rewards to train generators that produce higher-quality synthetic data, delivering 2-7% gains on math, medical QA, and coding tasks with improved robustness to forgetting.
-
When Languages Disagree: Self-Evolving Multilingual LLM Judges
SEMJ is a self-evolving multilingual LLM judge that turns cross-lingual inconsistency into iterative self-reflection, outperforming voting and reflection baselines on accuracy and consistency.
-
Activation-Based Active Learning for In-Context Learning: Challenges and Insights
MLP activations measured as massive activations or first four moments correlate weakly (max |Spearman| = 0.33) with in-context example quality across Llama-3.2-3B, Qwen2.5-3B, and multiple classification/generative tasks, so activation-based active learning should not be used for ICL.
-
Not All Flips Are Conformity: Decomposing Stance Convergence in Multi-Agent LLM Debate
The paper introduces a three-source decomposition showing that answer flips in multi-agent LLM debate include 37% spontaneous instability and 29% harmful conformity, with even vacuous reasoning persuading 20-39% of resistant agents and interventions reducing harmful conformity by 13.6 points.