arXiv:2606. 29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes.
The paper proposes an incremental pooled LLM evaluation method for selecting retrieval models in production Retrieval-Augmented Generation (RAG) systems. By having a language model judge the union of documents retrieved by current candidates and expanding the pool only with new documents from added systems, the approach reuses judgments across all systems. Experiments on four benchmarks and a financial news QA deployment show strong correlation with gold-standard rankings, high preservation of pairwise orderings, and significant cost savings—up to 4.9× lower evaluation cost and 65–80% judgment reuse.
arXiv:2608. 10528v1 Announce Type: cross Abstract: Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost.
The paper investigates how scaling hard‑negative training for rerankers can improve industrial legal retrieval systems once embedding recall saturates. On Chinese legal benchmarks, a pipeline that first uses embedding‑mined negatives and then self‑mined negatives yields the best trade‑off, and a 4B‑parameter Stage2 reranker outperforms the native 4B model on STARD, CSAID, and internal datasets. The study demonstrates that evaluating retrieval and reranking stages separately is beneficial for optimizing industrial retrieval performance.
The paper investigates how adding non‑relevant documents to a collection affects the performance of Information Retrieval (IR) models. It distinguishes between Multi‑Document‑Agnostic (MDA) models, which do not rely on other documents, and Multi‑Document‑Dependent (MDD) models, which do, and evaluates both on two collections with little topic overlap. Results show that all models suffer some performance loss when non‑relevant documents are added, but MDA models outperform MDD models in retrieval tasks, while both perform similarly in reranking.
The paper investigates whether System‑1‑style decision models can replace dedicated rerankers in retrieval‑augmented generation (RAG) systems. After screening 21 open‑weight models on 11 benchmarks, the authors compare a promising decision model with a dedicated reranker on identical candidate lists. While limiting candidate text length improves reliability and makes some configurations competitive, a tuned reranker remains faster and uses less GPU memory, indicating that replacing a reranker requires balancing quality, latency, and memory.
arXiv:2610.09412v1 Announce Type: cross Abstract: Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves r...
Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves retrieval and answer quality. We show that its effec...
arXiv:2606. 28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval.
The study evaluates large language models (LLMs) as rerankers in conversational movie recommendation, comparing proprietary, open-weight, and fine-tuned LLMs against collaborative-filtering and sequential baselines on the ReDial benchmark. Results show that the best proprietary LLM achieves an NDCG@10 of 0.1497 with a shared semantic candidate pool, outperforming non-LLM baselines, while open-weight LLMs do not surpass a tuned shallow autoencoder under the same protocol. The analysis also highlights that reranker performance is highly sensitive to candidate generation, pool size, scoring policy, and decoding temperature, suggesting these factors should be reported as standard evaluation fields.
Large Language Model judges are commonly used to rank texts via pairwise comparison, with reliability traditionally measured by position bias, transitivity, and pairwise agreement. This paper argues that these proxies are misleading because they are dominated by close‑rank‑gap pairs, which contribute little to the overall ranking, while far‑gap pairs carry the true ranking signal. Experiments on simulations and human‑rated corpora show weak correlation between the proxies and actual ranking accuracy, suggesting judges should be evaluated using rank‑gap‑conditional metrics against human rankings.
The paper examines LLM-based recommendation rerankers that are often evaluated under an oracle protocol, which guarantees the ground-truth item is present in the scored set. Across Amazon datasets, this protocol overestimates realistic NDCG@10 by 92–95% because realistic retrieval only covers 2–19% of relevant items at K=100, creating a recall ceiling that limits any closed-candidate reranker's top‑k NDCG. The authors find that various optimisation strategies—including prompt engineering, model scaling, sequential models, supervised neural rerankers, LoRA fine‑tuning, hybrid retrieval, score‑aware prompting, and LLM+CF fusion—do not significantly improve over a collaborative‑filtering baseline under realistic retrieval, and they propose a Recall‑Aware Evaluation Protocol (RAEP) to better assess rerankers in low‑recall regimes.