Cover Image

RankSteer: Activation Steering for Pointwise LLM Ranking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yumeng, Chen, Catherine, Verberne, Suzan
Format:	Preprint
Published:	2026
Subjects:	Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How role-play shapes relevance judgment in zero-shot LLM rankers
by: Wang, Yumeng, et al.
Published: (2025)

QUIDS: Query Intent Description for Exploratory Search via Dual Space Modeling
by: Wang, Yumeng, et al.
Published: (2024)

TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking
by: Fan, Yongqi, et al.
Published: (2025)

What are the limits of cross-lingual dense passage retrieval for low-resource languages?
by: Wu, Jie, et al.
Published: (2024)

Efficient course recommendations with T5-based ranking and summarization
by: Bijl, Thijmen, et al.
Published: (2024)

LANCER: LLM Reranking for Nugget Coverage
by: Ju, Jia-Huei, et al.
Published: (2026)

Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation
by: Kannen, Nithish, et al.
Published: (2024)

Answer Retrieval in Legal Community Question Answering
by: Askari, Arian, et al.
Published: (2024)

Unifying Search and Recommendation in LLMs via Gradient Multi-Subspace Tuning
by: Zhao, Jujia, et al.
Published: (2026)

Unifying Search and Recommendation with Dual-View Representation Learning in a Generative Paradigm
by: Zhao, Jujia, et al.
Published: (2025)

LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labels
by: Lin, I-Fan, et al.
Published: (2025)

Unbiased Learning to Rank with Query-Level Click Propensity Estimation: Beyond Pointwise Observation and Relevance
by: Yu, Lulu, et al.
Published: (2025)

Precise Zero-Shot Pointwise Ranking with LLMs through Post-Aggregated Global Context Information
by: Long, Kehan, et al.
Published: (2025)

Improving RAG for Personalization with Author Features and Contrastive Examples
by: Yazan, Mert, et al.
Published: (2025)

The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs
by: Yazan, Mert, et al.
Published: (2024)

Controlled Retrieval-augmented Context Evaluation for Long-form RAG
by: Ju, Jia-Huei, et al.
Published: (2025)

Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
by: Ju, Jia-Huei, et al.
Published: (2026)

High Recall, Small Data: The Challenges of Within-System Evaluation in a Live Legal Search System
by: Wiggers, Gineke, et al.
Published: (2024)

RankLLM: A Python Package for Reranking with LLMs
by: Sharifymoghaddam, Sahel, et al.
Published: (2025)

LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking
by: Zeng, Yifan, et al.
Published: (2024)

The Ranking Blind Spot: Decision Hijacking in LLM-based Text Ranking
by: Qian, Yaoyao, et al.
Published: (2025)

RankMixer: Scaling Up Ranking Models in Industrial Recommenders
by: Zhu, Jie, et al.
Published: (2025)

Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking
by: Schlatt, Ferdinand, et al.
Published: (2024)

A Multi-Agent Conversational Recommender System
by: Fang, Jiabao, et al.
Published: (2024)

REALM: Recursive Relevance Modeling for LLM-based Document Re-Ranking
by: Wang, Pinhuan, et al.
Published: (2025)

Can LLM Annotations Replace User Clicks for Learning to Rank?
by: Yu, Lulu, et al.
Published: (2025)

From Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking
by: Zhao, Yuhan, et al.
Published: (2024)

RankTower: A Synergistic Framework for Enhancing Two-Tower Pre-Ranking Model
by: Yan, YaChen, et al.
Published: (2024)

Proactive Recommendation in Social Networks: Steering User Interest with Causal Inference
by: Pan, Hang, et al.
Published: (2024)

Differentiable Semantic ID for Generative Recommendation
by: Fu, Junchen, et al.
Published: (2026)

GoalRank: Group-Relative Optimization for a Large Ranking Model
by: Zhang, Kaike, et al.
Published: (2025)

Harnessing Pairwise Ranking Prompting Through Sample-Efficient Ranking Distillation
by: Wu, Junru, et al.
Published: (2025)

Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking
by: Guo, Huizhong, et al.
Published: (2026)

CoRanking: Collaborative Ranking with Small and Large Ranking Agents
by: Liu, Wenhan, et al.
Published: (2025)

Batched Self-Consistency Improves LLM Relevance Assessment and Ranking
by: Korikov, Anton, et al.
Published: (2025)

InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization
by: Jin, Jiarui, et al.
Published: (2024)

Rank4Gen: RAG-Preference-Aligned Document Set Selection and Ranking
by: Fan, Yongqi, et al.
Published: (2026)

Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation
by: Kabongo, Ben, et al.
Published: (2026)

RankingSHAP -- Listwise Feature Attribution Explanations for Ranking Models
by: Heuss, Maria, et al.
Published: (2024)

RankDCG: Rank-Ordering Evaluation Measure
by: Katerenchuk, Denys, et al.
Published: (2018)