Cover Image

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nguyen, Duy, Prasad, Archiki, Stengel-Eskin, Elias, Bansal, Mohit
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
by: Prasad, Archiki, et al.
Published: (2023)

Multi-Attribute Steering of Language Models via Targeted Intervention
by: Nguyen, Duy, et al.
Published: (2025)

LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits
by: Nguyen, Duy, et al.
Published: (2024)

Multimodal Fact-Level Attribution for Verifiable Reasoning
by: Wan, David, et al.
Published: (2026)

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
by: Pothiraj, Atin, et al.
Published: (2025)

RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation
by: Niu, Tianyi, et al.
Published: (2025)

ReGAL: Refactoring Programs to Discover Generalizable Abstractions
by: Stengel-Eskin, Elias, et al.
Published: (2024)

See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
by: Ananthram, Amith, et al.
Published: (2024)

Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training
by: Wan, David, et al.
Published: (2024)

CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval
by: Wan, David, et al.
Published: (2025)

AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge
by: Wang, Han, et al.
Published: (2024)

Retrieval-Augmented Generation with Conflicting Evidence
by: Wang, Han, et al.
Published: (2025)

VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
by: Wang, Ziyang, et al.
Published: (2024)

Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
by: Nguyen, Duy, et al.
Published: (2026)

Soft Self-Consistency Improves Language Model Agents
by: Wang, Han, et al.
Published: (2024)

DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
by: Sivakumaran, Nithin, et al.
Published: (2025)

Executable Functional Abstractions: Inferring Generative Programs for Advanced Math Problems
by: Khan, Zaid, et al.
Published: (2025)

One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
by: Khan, Zaid, et al.
Published: (2025)

PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions
by: Ananthram, Amith, et al.
Published: (2025)

MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
by: Wang, Han, et al.
Published: (2026)

MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
by: Chen, Justin Chih-Yao, et al.
Published: (2024)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
by: Zhang, Yue, et al.
Published: (2026)

Learning to Generate Unit Tests for Automated Debugging
by: Prasad, Archiki, et al.
Published: (2025)

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
by: Stengel-Eskin, Elias, et al.
Published: (2024)

Teaching Models to Balance Resisting and Accepting Persuasion
by: Stengel-Eskin, Elias, et al.
Published: (2024)

Language Models Identify Ambiguities and Exploit Loopholes
by: Choi, Jio, et al.
Published: (2025)

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
by: Singh, Joykirat, et al.
Published: (2025)

System-1.x: Learning to Balance Fast and Slow Planning with Language Models
by: Saha, Swarnadeep, et al.
Published: (2024)

PRInTS: Reward Modeling for Long-Horizon Information Seeking
by: Lee, Jaewoo, et al.
Published: (2025)

GenerationPrograms: Fine-grained Attribution with Executable Programs
by: Wan, David, et al.
Published: (2025)

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
by: Patil, Vaidehi, et al.
Published: (2025)

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
by: Patil, Vaidehi, et al.
Published: (2025)

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
by: Lin, Han, et al.
Published: (2025)

WindowQuant: Mixed-Precision KV Cache Quantization based on Window-Level Similarity for VLMs Inference Optimization
by: Tao, Wei, et al.
Published: (2026)

FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme Detection
by: Bhaskar, Paramananda, et al.
Published: (2026)

Video-Skill-CoT: Skill-based Chain-of-Thoughts for Domain-Adaptive Video Reasoning
by: Lee, Daeun, et al.
Published: (2025)

LAQuer: Localized Attribution Queries in Content-grounded Generation
by: Hirsch, Eran, et al.
Published: (2025)

No Training Wheels: Steering Vectors for Bias Correction at Inference Time
by: Gupta, Aviral, et al.
Published: (2025)

From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
by: Wang, Qidong, et al.
Published: (2026)

AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals
by: Nguyen, Duy, et al.
Published: (2026)