Chain of Thought risk decomposes into oracle-trajectory benefit and trajectory-mismatch cost, with stability determining bounded, linear, or exponential error growth.
Implicit reasoning in large language models: A comprehensive survey.arXiv preprint arXiv:2509.02350
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 10roles
background 2polarities
background 2representative citing papers
CopT reverses CoT by eliciting a draft answer first then using continuous-embedding contrastive verification and on-policy thinking to reflect and correct, yielding up to 23% higher accuracy and 57% fewer tokens without training.
LAnR unifies retrieval-augmented generation inside a single LLM by deriving dense retrieval vectors from a [PRED] token's hidden states and using entropy to adaptively stop retrieval, outperforming prior RAG on six QA benchmarks with better efficiency.
S²GR adds stepwise thinking tokens with contrastive supervision on codebook clusters to balance computational focus and ground reasoning paths in generative recommendation.
A looped padded Transformer with parallel gold-CoT cross-entropy supervision matches explicit CoT accuracy at 3B scale and is 2.5–6.9× faster in the thought phase.
LoRi distills implicit chain-of-thought by matching low-rank structures in hidden states, raising math-reasoning accuracy toward explicit CoT levels on LLaMA and Qwen models.
Prohibited concepts remain recoverable from hidden states, influence attention routing, and shape generations in transformers under instruction-based suppression.
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
EVA generates adaptive Latent_slot tokens as internal visual thoughts, trained end-to-end with text tokens via D-GSPO on the EVA-230K dataset, claiming performance gains and better inference efficiency.
A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).
citing papers explorer
-
On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
Chain of Thought risk decomposes into oracle-trajectory benefit and trajectory-mismatch cost, with stability determining bounded, linear, or exponential error growth.
-
CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
CopT reverses CoT by eliciting a draft answer first then using continuous-embedding contrastive verification and on-policy thinking to reflect and correct, yielding up to 23% higher accuracy and 57% fewer tokens without training.
-
Latent Abstraction for Retrieval-Augmented Generation
LAnR unifies retrieval-augmented generation inside a single LLM by deriving dense retrieval vectors from a [PRED] token's hidden states and using entropy to adaptively stop retrieval, outperforming prior RAG on six QA benchmarks with better efficiency.
-
S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation
S²GR adds stepwise thinking tokens with contrastive supervision on codebook clusters to balance computational focus and ground reasoning paths in generative recommendation.
-
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
A looped padded Transformer with parallel gold-CoT cross-entropy supervision matches explicit CoT accuracy at 3B scale and is 2.5–6.9× faster in the thought phase.
-
LoRi: Low-Rank Distillation for Implicit Reasoning
LoRi distills implicit chain-of-thought by matching low-rank structures in hidden states, raising math-reasoning accuracy toward explicit CoT levels on LLaMA and Qwen models.
-
The Attentional White Bear Effect in Transformer Language Models
Prohibited concepts remain recoverable from hidden states, influence attention routing, and shape generations in transformers under instruction-based suppression.
-
SeLaR: Selective Latent Reasoning in Large Language Models
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
-
Latent Visual States for Efficient Multimodal Reasoning
EVA generates adaptive Latent_slot tokens as internal visual thoughts, trained end-to-end with text tokens via D-GSPO on the EVA-230K dataset, claiming performance gains and better inference efficiency.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
A 22M-parameter hyperbolic model answers structured EHR questions with accuracy close to LLM-based systems (EHRXQA 89.5%, MIMIC-Instr 76.0%).