Imagen de Portada

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Handa, Divij, Parmar, Mihir, RRV, Aswin, Uddin, Md Nayem, Palangi, Hamid, Baral, Chitta
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ThinkTuning: Instilling Cognitive Reflections without Distillation
por: RRV, Aswin, et al.
Publicado: (2025)

When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
por: Handa, Divij, et al.
Publicado: (2024)

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
por: RRV, Aswin, et al.
Publicado: (2026)

Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies
por: RRV, Aswin, et al.
Publicado: (2024)

Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
por: Tyagi, Nemika, et al.
Publicado: (2024)

PHANTOM RECALL: When Familiar Puzzles Fool Smart Models
por: Mukhopadhyay, Souradeep, et al.
Publicado: (2025)

UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
por: Uddin, Md Nayem, et al.
Publicado: (2024)

PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
por: Parmar, Mihir, et al.
Publicado: (2025)

ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints
por: Handa, Divij, et al.
Publicado: (2024)

Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
por: Parmar, Mihir, et al.
Publicado: (2022)

Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks
por: Saeidi, Amir, et al.
Publicado: (2024)

Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization
por: Saeidi, Amir, et al.
Publicado: (2024)

Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models
por: Patel, Nisarg, et al.
Publicado: (2024)

Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents
por: Kumbhar, Shrinidhi, et al.
Publicado: (2025)

Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
por: Dineen, Jacob, et al.
Publicado: (2026)

From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
por: Uddin, Md Nayem, et al.
Publicado: (2026)

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
por: Parmar, Mihir, et al.
Publicado: (2024)

ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review
por: Goyal, Palash, et al.
Publicado: (2026)

Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models
por: Luo, Man, et al.
Publicado: (2023)

Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark
por: Gupta, Himanshu, et al.
Publicado: (2024)

Diversity of Thought Improves Reasoning Abilities of LLMs
por: Naik, Ranjita, et al.
Publicado: (2023)

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
por: Parmar, Mihir, et al.
Publicado: (2025)

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
por: Miculicich, Lesly, et al.
Publicado: (2025)

OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation
por: Handa, Divij, et al.
Publicado: (2025)

LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science
por: Salemi, Alireza, et al.
Publicado: (2025)

TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems
por: Ahamed, Md Atik, et al.
Publicado: (2026)

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
por: Mishra, Venkatesh, et al.
Publicado: (2025)

QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA
por: Dineen, Jacob, et al.
Publicado: (2025)

Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs
por: Parmar, Mihir, et al.
Publicado: (2024)

ToW: Thoughts of Words Improve Reasoning in Large Language Models
por: Xu, Zhikun, et al.
Publicado: (2024)

When Can LLMs Learn to Reason with Weak Supervision?
por: Rahman, Salman, et al.
Publicado: (2026)

InfSplign: Inference-Time Spatial Alignment of Text-to-Image Diffusion Models
por: Rastegar, Sarah, et al.
Publicado: (2025)

MMTABREAL: Real-World Benchmark for Multimodal Table Understanding
por: Titiya, Prasham, et al.
Publicado: (2025)

Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering
por: Du, Kounianhua, et al.
Publicado: (2025)

Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting
por: Gupta, Divij, et al.
Publicado: (2024)

Reasoning-Aware Training for Time Series Forecasting
por: Ahamed, Md Atik, et al.
Publicado: (2026)

Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Models
por: Gupta, Divij, et al.
Publicado: (2024)

HEART: Emotionally-Driven Test-Time Scaling of Language Models
por: Pinto, Gabriela, et al.
Publicado: (2025)

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs
por: Nguyen, Duy, et al.
Publicado: (2025)

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
por: Li, Jiakang, et al.
Publicado: (2026)