DecisionRank introduces an on-policy distillation (OPD) method that trains decision models to replicate a generative LLM’s ranking knowledge by converting the student’s document scores into a ranked sequence and using a teacher to provide conditional feedback. The approach combines item‑space OPD with offline ranking supervision, achieving state‑of‑the‑art results on retrieval benchmarks such as TREC DL, BEIR, and BRIGHT. Even with a 1.7B parameter model, DecisionRank outperforms its 27B generative teacher on TREC DL19–23, and at 8B it surpasses the generative listwise counterpart while running 24.5× faster on TREC DL and 16.7× faster on BRIGHT.
Compact instruction-following rerankers are attractive for deployment, but conventional distillation pipelines typically train students by offline imitation of teacher outputs on a fixed set of exampl...
The paper introduces a two‑stage training framework for compact instruction‑following rerankers. Stage 1 strengthens a 4B teacher reranker with off‑policy GRPO using LLM‑judge feedback on 88K examples, while Stage 2 trains a 1B student by sampling its own rankings and receiving soft teacher‑derived rewards, blending exploration with knowledge transfer. The method achieves superior nDCG and MRR scores on MAIR‑11 and MAIR‑Full benchmarks, outperforming offline distillation baselines and larger RL‑trained rerankers.
arXiv:2610.22797v1 Announce Type: cross Abstract: Reasoning rerankers write a rationale before ranking a candidate slate, and existing systems read item metadata to do so, even though generative reco...
arXiv:2610.35218v1 Announce Type: new Abstract: Generative recommendation with semantic IDs (SIDs) represents each item as a sequence of discrete tokens and autoregressively predicts the next item's...
hLLM (Hungarian LLM) is a decoding strategy that efficiently produces ranked lists from large language models by decoding all ordinal positions in a single forward pass. It extracts an item‑position score matrix from the model’s hidden states, then applies the Hungarian algorithm to obtain a valid permutation, avoiding the sequential token generation of traditional autoregressive decoding. Experiments show that LoRA‑based fine‑tuning with teacher ranking distillation achieves 28 ms end‑to‑end inference, a 64× speed‑up while preserving ranking quality comparable to the teacher model.
The paper introduces a new scorer for generative answer engines that ranks candidate pages by the likelihood of being cited. It evaluates pretrained rerankers, a hosted typed decision model (Jev), eight open decision models, and a distilled 4B student on GEO‑Bench queries answered by ten engines. The distilled student, fine‑tuned with low‑rank adapters, achieves comparable performance to larger models and the authors release the model, benchmark, predictions, and code.
arXiv:2604. 23336v3 Announce Type: replace-cross Abstract: Unlike traditional fact-based retrieval, rationale-based retrieval typically necessitates cross-encoding of query-document pairs using large language models, incurring substantial computational costs.
arXiv:2605. 04495v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance.
arXiv:2609.14565v1 Announce Type: new Abstract: LLM-based sequential recommenders usually cast next-item prediction as text generation, but this interface is poorly matched to full-catalog top-K rank...
arXiv:2602. 07774v5 Announce Type: replace-cross Abstract: Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge.
arXiv:2607. 05734v1 Announce Type: cross Abstract: Chain-of-thought (CoT) distillation in the recommendation domain is a necessary precursor to RL training, but raw teacher traces are ill-suited to this task.
The paper introduces SPD (Single Forward Pass), a decoding strategy that efficiently produces ranked lists from large language models by emitting only the ordinal positions of items. SPD extracts an item‑position score matrix from the model’s hidden states, then solves a bipartite assignment problem via the Hungarian algorithm to generate a valid permutation in a single forward pass. Experiments show that LoRA‑based fine‑tuning combined with autoregressive ranking distillation achieves 28 ms end‑to‑end inference, a 64× speed‑up while preserving ranking quality.