No article text was recorded for this version.
two-stage reasoning pipeline
Version 1 of 144 papers49 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding
- Blog: Let Me Speak Freely? A Study On The Impact Of Format Restrictions On Large Language Model Performance
- Blog: Multimodal Chain-of-Thought Reasoning in Language Models
- Blog: Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
- Blog: Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models
- Blog: Towards Interactivity and Interpretability: A Rationale-based Legal Judgment Prediction Framework
- Blog: Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models
- Blog: Solving Math Word Problems via Cooperative Reasoning induced Language Models
- Blog: Evaluating Subjective Cognitive Appraisals of Emotions from Large Language Models
- Blog: QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs
- Blog: Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs
- Blog: Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making
- Blog: Identifying Power Relations in Conversations using Multi-Agent Social Reasoning
- Blog: VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
- Blog: SPRI: Aligning Large Language Models with Context-Situated Principles
- Blog: Reasoning-Grounded Natural Language Explanations for Language Models
- Blog: On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
- Blog: Structured Chain-of-Thought Prompting for Code Generation
- Blog: Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
- Blog: From Extraction to Deduction: Resolving Functional Misalignment in RAG via a Collaborative Critic-Reasoner Framework
- Blog: Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Reasoning Large Language Models
- Blog: QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs
- Blog: T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Large Language Model Signals for Science Question Answering
- Blog: Inference and Verbalization Functions During In-Context Learning
- Blog: Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling
- Blog: DDxTutor: Clinical Reasoning Tutoring System with Differential Diagnosis-Based Structured Reasoning
- Blog: How do LLMs' Preferences Affect Event Argument Extraction? CAT: Addressing Preference Traps in Unsupervised EAE
- Blog: Draft-Conditioned Constrained Decoding for Structured Generation in LLMs
- Blog: Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction
- Blog: Clarification des Ambiguïtés : Sur le Rôle des Types d'Ambiguïté dans les Méthodes d'Amorçage pour la Génération de Clarifications
- Blog: Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationales
- Blog: PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales
- Blog: Timeline-based Sentence Decomposition with In Context Learning for Temporal Fact Extraction
- Blog: Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs
- Blog: How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation
- Blog: Large Language Models are Zero-Shot Reasoners
- Blog: Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
- Blog: Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments
- Blog: Clarifying Ambiguities: on the Role of Ambiguity Types in Prompting Methods for Clarification Generation
- Blog: Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection
- Blog: yangqi at SemEval-2024 Task 9: Simulate Human Thinking by Large Language Model for Lateral Thinking Challenges
- Blog: Generating Diverse Hypotheses for Inductive Reasoning
- Blog: Tab-CoT: Zero-shot Tabular Chain of Thought
- Blog: Enhancing human-like multimodal reasoning: a new challenging dataset and comprehensive framework
History & citation
Current · Permanent link
- This direction split from Decoupling Reasoning from Answer Extraction in Language Models (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_two_stage_reasoning_pipeline_3402824d,
title = {two-stage reasoning pipeline},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/two-stage-reasoning-pipeline/rdr_3402824d48504b39bfaa1b0f0d13fb11},
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_two_stage_reasoning_pipeline_3402824d_v1,
title = {two-stage reasoning pipeline},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/two-stage-reasoning-pipeline/rdr_3402824d48504b39bfaa1b0f0d13fb11/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}