The paper gives the first tight necessity and sufficiency conditions for successful reward poisoning attacks in linear MDPs.
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval , pages =
7 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 7roles
background 2polarities
background 2representative citing papers
AWARE augments generative next-POI recommendation with LLM agents that produce user-anchored narratives capturing events, culture, and trends, delivering up to 12.4% relative gains on three real datasets.
Single-prompt evaluations of instruction-tuned embedding models misrepresent performance and allow any model to be ranked first by favorable prompt choice.
SPLADE models produce wacky expansion terms whose prevalence rises with larger vocabularies and falls with stricter sparsity; these terms primarily aid in-domain retrieval rather than out-of-domain generalization.
Marketplace Evaluation uses repeated-interaction simulations to assess information access systems with marketplace-level metrics such as retention and market share that complement traditional accuracy measures.
JU'A is a new heterogeneous benchmark for Brazilian legal IR that distinguishes retrieval methods and shows domain-adapted models excel on aligned subsets while BM25 stays competitive elsewhere.
LLM-generated reference documents enable dynamic ranked list truncation and adaptive batching for listwise reranking, outperforming prior RLT methods and accelerating processing by up to 66% on TREC benchmarks.
citing papers explorer
-
When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs
The paper gives the first tight necessity and sufficiency conditions for successful reward poisoning attacks in linear MDPs.
-
Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation
AWARE augments generative next-POI recommendation with LLM agents that produce user-anchored narratives capturing events, culture, and trends, delivering up to 12.4% relative gains on three real datasets.
-
One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
Single-prompt evaluations of instruction-tuned embedding models misrepresent performance and allow any model to be ranked first by favorable prompt choice.
-
Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance
SPLADE models produce wacky expansion terms whose prevalence rises with larger vocabularies and falls with stricter sparsity; these terms primarily aid in-domain retrieval rather than out-of-domain generalization.
-
Evaluation of Agents under Simulated AI Marketplace Dynamics
Marketplace Evaluation uses repeated-interaction simulations to assess information access systems with marketplace-level metrics such as retention and market share that complement traditional accuracy measures.
-
JU\'A -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections
JU'A is a new heterogeneous benchmark for Brazilian legal IR that distinguishes retrieval methods and shows domain-adapted models excel on aligned subsets while BM25 stays competitive elsewhere.
-
Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents
LLM-generated reference documents enable dynamic ranked list truncation and adaptive batching for listwise reranking, outperforming prior RLT methods and accelerating processing by up to 66% on TREC benchmarks.