Sample, Don't Search: Rethinking Test-Time Alignment for Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Faria, Gonçalo, Smith, Noah A.
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Why Don't Prompt-Based Fairness Metrics Correlate?
by: Zayed, Abdelrahman, et al.
Published: (2024)

Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers
by: Leemann, Tobias, et al.
Published: (2024)

Sampling from Your Language Model One Byte at a Time
by: Hayase, Jonathan, et al.
Published: (2025)

Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation
by: Dasgupta, Sayantan, et al.
Published: (2026)

If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
by: Hernandez, Adriano
Published: (2024)

Reasoning Models Don't Just Think Longer, They Move Differently
by: Gjølbye, Anders, et al.
Published: (2026)

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
by: Cohen, Roi, et al.
Published: (2024)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
by: Tyukin, Georgy, et al.
Published: (2024)

Large Language Models Must Be Taught to Know What They Don't Know
by: Kapoor, Sanyam, et al.
Published: (2024)

Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Search
by: Fadeeva, Ekaterina, et al.
Published: (2025)

Don't Walk the Line: Boundary Guidance for Filtered Generation
by: Ball, Sarah, et al.
Published: (2025)

Reasoning Models Don't Always Say What They Think
by: Chen, Yanda, et al.
Published: (2025)

Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank
by: Roy, Debjyoti Saha, et al.
Published: (2024)

Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
by: Deng, Yang, et al.
Published: (2024)

Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling
by: Xia, Fanzeng, et al.
Published: (2025)

Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming
by: Kavumba, Pride, et al.
Published: (2026)

Don't Read Everything: A Curvature-Conditioned Query for Linear Attention
by: Le, Dong, et al.
Published: (2026)

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
by: Hariri, Mohsen, et al.
Published: (2025)

Learn and Don't Forget: Adding a New Language to ASR Foundation Models
by: Qian, Mengjie, et al.
Published: (2024)

Kinetics: Rethinking Test-Time Scaling Laws
by: Sadhukhan, Ranajoy, et al.
Published: (2025)

Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation
by: Vernikos, Giorgos, et al.
Published: (2024)

Rethinking the Role of Proxy Rewards in Language Model Alignment
by: Kim, Sungdong, et al.
Published: (2024)

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
by: Cao, Mingyu, et al.
Published: (2024)

QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
by: Faria, Gonçalo R. A., et al.
Published: (2024)

Efficient Alignment of Large Language Models via Data Sampling
by: Khera, Amrit, et al.
Published: (2024)

Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models
by: Zausinger, Jonas, et al.
Published: (2024)

You Don't Need Prompt Engineering Anymore: The Prompting Inversion
by: Khan, Imran
Published: (2025)

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
by: Zhou, Jin Peng, et al.
Published: (2024)

Don't lie to your friends: Learning what you know from collaborative self-play
by: Eisenstein, Jacob, et al.
Published: (2025)

Don't Shoot The Breeze: Topic Continuity Model Using Nonlinear Naive Bayes With Attention
by: Pi, Shu-Ting, et al.
Published: (2026)

Partially Rewriting a Transformer in Natural Language
by: Paulo, Gonçalo, et al.
Published: (2025)

Cascade Reward Sampling for Efficient Decoding-Time Alignment
by: Li, Bolian, et al.
Published: (2024)

On the Robustness of Reward Models for Language Model Alignment
by: Hong, Jiwoo, et al.
Published: (2025)

Automatically Interpreting Millions of Features in Large Language Models
by: Paulo, Gonçalo, et al.
Published: (2024)

Don't throw away your value model! Generating more preferable text with Value-Guided Monte-Carlo Tree Search decoding
by: Liu, Jiacheng, et al.
Published: (2023)

SuperBPE: Space Travel for Language Models
by: Liu, Alisa, et al.
Published: (2025)

Test-Time Safety Alignment
by: Saglam, Baturay, et al.
Published: (2026)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
by: Jedidi, Nour, et al.
Published: (2025)

Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
by: Morrison, Jacob, et al.
Published: (2024)

Value Augmented Sampling for Language Model Alignment and Personalization
by: Han, Seungwook, et al.
Published: (2024)