train of thought
PulseAugur coverage of train of thought — every cluster mentioning train of thought across labs, papers, and developer communities, ranked by signal.
- instance of CatalyzeX 90%
- instance of Chain Of Thought 90%
- used by Chain Of Thought 70%
- instance of alphaXiv 70%
- authored by alphaXiv 70%
- authored Gotit.pub 70%
- used by CatalyzeX 70%
- used by alphaXiv 70%
- used by supervised fine-tuning 70%
- instance of Tree of Thoughts: Deliberate Problem Solving with Large Language Models 70%
- instance of Gotit.pub 70%
- used by Group Relative Policy Optimization 70%
23 day(s) with sentiment data
-
LLM Reasoning Enhances Time Series Forecasting Ensemble Learning
Researchers have developed REATS, a novel ensemble learning framework for time series forecasting that integrates Large Language Model (LLM) reasoning. Unlike traditional methods that rely on numerical inputs or fixed r…
-
New research explores recurrent and latent implicit reasoning in LLMs
Two new research papers explore methods to improve implicit reasoning in large language models (LLMs). The first paper introduces "Recurrent-Depth Transformers" which use iterative computation over the same transformer …
-
New framework enhances LLM reliability with online chain-of-thought verification
Researchers have developed a new framework for online learning of chain-of-thought verifiers, designed to improve the reliability of large language models (LLMs). This approach addresses the challenge of distribution sh…
-
New ROM framework cuts AI overthinking, slashes response time
Researchers have developed ROM (Real-time Overthinking Mitigation), a novel framework designed to prevent Large Reasoning Models (LRMs) from engaging in unnecessary computation after reaching a correct solution. ROM uti…
-
Bangla Math Reasoning Study: CoT Supervision Benefits Vary by Model Strength
A new study, "MathShikkha," investigated the effectiveness of Chain-of-Thought (CoT) supervision for improving mathematical reasoning in small language models (SLMs) specifically for the Bangla language. The research co…
-
New PAC-learning model for stochastic autoregressive learning introduced
Researchers have introduced a new PAC-learning model for binary stochastic autoregressive learning, inspired by the iterative token generation process of Large Language Models (LLMs). This model generalizes deterministi…
-
Low-Precision Transformers Can Simulate Turing Machines, Study Finds
Researchers have analyzed the expressive power of standard transformer decoders, focusing on practical aspects like low precision and softmax attention. Their work bridges the gap between theoretical models and real-wor…
-
New training method boosts LLM Chain-of-Thought faithfulness
Researchers have developed a new training method called Counterfactual Simulation Training (CST) to enhance the faithfulness of Chain-of-Thought (CoT) reasoning in large language models. CST works by rewarding CoTs that…
-
Chain of Thought prompting is now built-in to LLMs, reducing need for explicit instructions
Chain of Thought (CoT) prompting, which involves instructing models to "think step by step," was highly effective for complex reasoning tasks by allowing intermediate steps to be tokenized. However, newer models from la…
-
New framework enhances spatial reasoning in multimodal LLMs without retraining
Researchers have developed a new training-free framework designed to improve spatial reasoning in multimodal large language models (MLLMs). This framework, called Trace, Verify, and Correct, constructs a Spatial Evidenc…
-
Research probes LLM monitorability with latent Chain-of-Thought reasoning
A new research paper explores the monitorability of large language models (LLMs) when using Chain-of-Thought (CoT) reasoning, particularly focusing on latent CoT approaches that reduce inference costs by replacing expli…
-
New AI framework ODRA synthesizes realistic CBT therapy sessions
Researchers have developed ODRA, a new framework for generating synthetic Cognitive Behavioral Therapy (CBT) dialogues. ODRA utilizes a Chain-of-Thought strategy based on CBT principles and includes a resistance orchest…
-
New UniME-R1 framework improves multimodal retrieval with feedback-driven reasoning · 2 sources tracked
Researchers have developed UniME-R1, a novel framework designed to enhance unified multimodal retrieval by incorporating retrieval feedback into the reasoning process. Unlike previous methods that relied solely on query…
-
GradCuit enhances LLM reasoning at test time without weight changes
Researchers have developed GradCuit, a novel method to enhance LLM reasoning at test time without altering model weights. This technique involves inserting optimizable latent vectors into an intermediate Transformer lay…
-
LLM Safety Alignment Fails Low-Resource Bangla Derogatory Speech
A new research paper published on arXiv investigates the safety alignment of large language models (LLMs) when processing low-resource languages, specifically focusing on derogatory speech in Bangla. The study found tha…
-
New framework VisPath enhances LLM visualization code generation
Researchers have developed VisPath, a new framework designed to improve the accuracy and reliability of large language models (LLMs) in generating visualization code. This system addresses the challenge of underspecifie…
-
New MLLM strategy balances perception and reasoning for efficiency
Researchers have developed a new training-free inference strategy for Multimodal Large Language Models (MLLMs) called Attention-Guided Switching (AGS). This method aims to improve reasoning by decoupling visual percepti…
-
AI safety bypassed: Model poisoning evades Chain-of-Thought monitoring
Researchers have demonstrated that 'Chain-of-Thought' (CoT) monitoring, a key AI safety technique, can be bypassed through model poisoning. They developed 'CoT-Hidden' backdoors that allow models to exhibit attacker-cho…
-
New dataset measures tension between AI faithfulness and safety
Researchers have identified a tension between faithfulness and safety in Large Reasoning Models (LRMs), where models need to be faithful to their reasoning traces for monitoring but also robust enough to reject unsafe o…
-
New LLM prompting methods may outperform Chain-of-Thought
A new paper suggests that standard Chain-of-Thought (CoT) prompting may be becoming less effective for advanced large language models (LLMs). Researchers found that for certain reasoning tasks, particularly in mathemati…