MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction

• URL: http://arxiv.org/abs/2512.07846v1
• Date: Tue, 25 Nov 2025 21:23:04 GMT
• Title: MixLM: High-Throughput and Effective LLM Ranking via Text-Embedding Mix-Interaction
• Abstract summary: Large language models (LLMs) excel at capturing semantic nuances.<n>They suffer from high computational overhead under industrial latency and throughput requirements.<n>We propose MixLM, a novel LLM-based ranking framework.
• Score: 28.43509939465397
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) excel at capturing semantic nuances and therefore show impressive relevance ranking performance in modern recommendation and search systems. However, they suffer from high computational overhead under industrial latency and throughput requirements. In particular, cross-encoder ranking systems often create long context prefill-heavy workloads, as the model has to be presented with the user, query and item information. To this end, we propose MixLM, a novel LLM-based ranking framework, which significantly improves the system throughput via reducing the input context length, while preserving the semantic strength of cross-encoder rankers. In contrast to a standard ranking system where the context is presented to the model as pure text, we propose to use mix-interaction, a mixture of text and embedding tokens to represent the input. Specifically, MixLM encodes all items in the catalog into a few embedding tokens and stores in a nearline cache. The encoded item descriptions are used during online inference, effectively reducing the item length from a few thousand text tokens to a few embedding tokens. We share insights from deploying our MixLM framework to a real-world search application at LinkedIn, including a detailed discussion of our training pipelines, as well as a thorough analysis of our online serving infrastructure optimization. Comparing with strong baselines, MixLM increased throughput by 10.0x under the same latency budget, while maintaining relevance metrics. The efficiency gains delivered by MixLM enabled full-traffic deployment of LLM-powered search, which resulted in a significant 0.47% increase in Daily Active Users (DAU) in online A/B tests.

Related papers

• One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States [5.647839536820347]
  This paper introduces a lightweight projection head that maps hidden states directly into the embedding space, eliminating the need for a separate embedding model.<n> Experiments on the QReCC conversational search benchmark show competitive Recall@10 and MRR@10 compared to the standard generate-then-encode pipeline.
  arXiv  Detail & Related papers  (2026-03-09T14:25:35Z)
• Large Scale Retrieval for the LinkedIn Feed using Causal Language Models [4.742257164636025]
  This paper presents a novel retrieval approach that fine-tunes a large causal language model as a dual encoder to generate high quality embeddings for both users (members) and content (items)<n>We describe the end to end pipeline, including prompt design for embedding generation, techniques for fine-tuning at LinkedIn's scale, and infrastructure for low latency, cost effective online serving.
  arXiv  Detail & Related papers  (2025-10-16T02:01:33Z)
• MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval [50.062817677022586]
  Zero-Shot Image Retrieval (ZS-CIR) methods typically train adapters that convert reference images into pseudo-text tokens.<n>We propose MLLM-Guided VLM Fine-Tuning with Joint Inference (MVFT-JI) to construct two complementary training tasks using only unlabeled images.
  arXiv  Detail & Related papers  (2025-05-26T08:56:59Z)
• LLM-based Semantic Augmentation for Harmful Content Detection [5.954202581988127]
  This paper introduces an approach that prompts large language models to clean noisy text and provide context-rich explanations.<n>We evaluate on the SemEval 2024 multi-label Persuasive Meme dataset and validate on the Google Jigsaw toxic comments and Facebook hateful memes datasets.<n>Our results reveal that zero-shot LLM classification underperforms on these high-context tasks compared to supervised models.
  arXiv  Detail & Related papers  (2025-04-22T02:59:03Z)
• QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension [86.0749609778104]
  We propose QuoTA, an ante-hoc training-free modular that extends existing large video-language models.<n>QuoTA strategically allocates frame-level importance scores based on query relevance.<n>We decouple the query through Chain-of-Thoughts reasoning to facilitate more precise LVLM-based frame importance scoring.
  arXiv  Detail & Related papers  (2025-03-11T17:59:57Z)
• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences.<n>We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries.<n>We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• HyQE: Ranking Contexts with Hypothetical Query Embeddings [9.23634055123276]
  In retrieval-augmented systems, context ranking techniques are commonly employed to reorder the retrieved contexts based on their relevance to a user query. Large language models (LLMs) have been used for ranking contexts. We introduce a scalable ranking framework that combines embedding similarity and LLM capabilities without requiring LLM fine-tuning.
  arXiv  Detail & Related papers  (2024-10-20T03:15:01Z)
• Sparsity Meets Similarity: Leveraging Long-Tail Distribution for Dynamic Optimized Token Representation in Multimodal Large Language Models [6.467840081978855]
  multimodal large language models (MM-LLMs) have achieved significant success in various tasks.<n>Main computational burden arises from processingd text and visual tokens.<n>We propose a dynamic pruning algorithm that identifies the inflection point in the visual CLS token similarity curve.
  arXiv  Detail & Related papers  (2024-09-02T10:49:10Z)
• Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024 [61.189875635090225]
  Large Language Models (LLMs) are currently under exploration for various tasks, including Automatic Speech Recognition (ASR), Machine Translation (MT), and even End-to-End Speech Translation (ST)
  arXiv  Detail & Related papers  (2024-06-24T16:38:17Z)
• Reindex-Then-Adapt: Improving Large Language Models for Conversational Recommendation [50.19602159938368]
  Large language models (LLMs) are revolutionizing conversational recommender systems. We propose a Reindex-Then-Adapt (RTA) framework, which converts multi-token item titles into single tokens within LLMs. Our framework demonstrates improved accuracy metrics across three different conversational recommendation datasets.
  arXiv  Detail & Related papers  (2024-05-20T15:37:55Z)
• Zero-Shot Topic Classification of Column Headers: Leveraging LLMs for Metadata Enrichment [0.0]
  We propose a method to support metadata enrichment using topic annotations generated by three Large Language Models (LLMs): ChatGPT-3.5, GoogleBard, and GoogleGemini. We evaluate the impact of contextual information (i.e., dataset description) on the classification outcomes.
  arXiv  Detail & Related papers  (2024-03-01T10:01:36Z)
• Making Large Language Models A Better Foundation For Dense Retrieval [19.38740248464456]
  Dense retrieval needs to learn discriminative text embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding. We propose LLaRA (LLM adapted for dense RetrievAl), which works as a post-hoc adaptation of dense retrieval application.
  arXiv  Detail & Related papers  (2023-12-24T15:10:35Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM [65.74934004876914]
  Retrieval-enhanced language models (LMs) condition their predictions on text retrieved from large external datastores. One such approach, the $k$NN-LM, interpolates any existing LM's predictions with the output of a $k$-nearest neighbors model. We empirically measure the effectiveness of our approach on two English language modeling datasets.
  arXiv  Detail & Related papers  (2022-10-28T02:57:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.