Papers with Retrieval
Semantic Specialization of Distributional Word Vectors (D19-2)
Copied to clipboard
| Challenge: | Distributional word vectors conflate various paradigmatic and syntagmatic lexico-semantic relations. |
| Approach: | This tutorial provides an overview of specialization methods for distributional word vectors . a common solution is to include external lexico-semantic knowledge in a reshaped vector space . |
| Outcome: | This paper provides an overview of specialization methods for distributional word vectors . the most recent developments include a new method for asymmetric relations in Euclidean . |
On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models (2024.acl-short)
Copied to clipboard
Dongyang Li, Junbing Yan, Taolin Zhang, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang
| Challenge: | Existing RAG methods focus on improving the task performance, without fine-grained process of knowledge. |
| Approach: | They propose a method that detects long-tail knowledge in large language models by analyzing retrieved documents and enhancing queries indiscriminately with retrieved information. |
| Outcome: | The proposed method achieves over 4x speedup in average inference time and consistent performance improvement in downstream tasks compared to existing pipelines. |
NEST: Nested Evidence Survival for Retrieval (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to retrieval-augmented generation (RAG) rely on rigid heuristics or computational overhead. |
| Approach: | They propose a lightweight, training-free RAG framework that separates recall amplification from precision selection. |
| Outcome: | Evaluated on WebQuestions, HotpotQA and internalQA benchmarks, NEST outperforms strong adaptive RAG baselines. |
Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to document retrieval are coarse and efficient, but expensive. |
| Approach: | a plug-and-play two-stage hybrid-vector framework is proposed to retrieve visually rich documents . HEAVEN efficiently retrieves candidate pages using a single-vektor method over VS-Pages . it also reranks candidates with a multi-vecctor method while filtering query tokens by linguistic importance . |
| Outcome: | HEAVEN achieves 99.87% of the Recall@1 performance of multi-vector models on average . it reduces per-query computation by 99.8%, achieving efficiency and accuracy . |
CoSe-Co: Text Conditioned Generative CommonSense Contextualizer (2022.naacl-main)
Copied to clipboard
| Challenge: | Pre-trained language models (PTLMs) have been shown to perform well on natural language tasks. |
| Approach: | They propose a commonsense contextualizer conditioned on sentences as input to make it generically usable in tasks involving natural language text. |
| Outcome: | The proposed model improves on existing methods on CSQA, ARC, QASC and OBQA datasets. |
TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG (2025.emnlp-industry)
Copied to clipboard
Savini Kashmira, Jayanaka L. Dantanarayana, Joshua Brodsky, Ashish Mahendra, Yiping Kang, Krisztian Flautner, Lingjia Tang, Jason Mars
| Challenge: | Retrieval-Augmented Generation (RAG) relies on query-chunk text-to-text similarity in the embedding space for retrieval, can fail to capture deeper semantic relationships across chunks, is highly sensitive to chunking strategies, and is prone to hallucinations. |
| Approach: | They propose a graph-based retrieval framework that first constructs the knowledge graph from unstructured data dynamically and automatically. |
| Outcome: | The proposed framework outperforms multiple RAG implementations in both precision and recall, significantly enhancing user experience through improved retrieval accuracy. |
PEARL: Preference Extraction with Exemplar Augmentation and Retrieval with LLM Agents (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing systems specialize in extracting customer preferences from standalone queries . absence of a conversational interface often leaves customers feeling the need for humanlike assistance . |
| Approach: | They propose a shopping assistant chatbot that extracts customer preferences as key-value filters from a multi-turn conversation on an e-commerce website. |
| Outcome: | The proposed solution improves performance on exact match by 10% compared to baselines and improves inference latency by 1%. |
Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. |
| Approach: | They propose an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoding model. |
| Outcome: | Empirically, for k > 10, our approach provides test-time recall-vs-computational cost trade-offs superior to the current widely-used methods that re-rank items retrieved using a dual-encoder or TF-IDF. |
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training (2020.emnlp-main)
Copied to clipboard
| Challenge: | HERO is a framework for large-scale video+language omni-representation learning. |
| Approach: | They propose a framework for large-scale video+language omni-representation learning that encodes multimodal inputs in a hierarchical structure and uses Masked Language Modeling and Masked Frame Modeling to train models. |
| Outcome: | The proposed framework achieves state-of-the-art on multiple benchmarks over text-based video/video-moment retrieval, video question answering (QA), Video-and-language Inference and video Captioning tasks across different domains. |
Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models that ground retrieval on external evidence are limited in their ability to implement retrieval-augmented generation. |
| Approach: | They propose a retrieval-augmented generation model that embeds retrieval control directly into generation. |
| Outcome: | The proposed model surpasses strong RAG baselines and uses substantially fewer parameters. |
Open Schrödinger’s Closed Box: Identifying Retrieval Augmented Generation in API-Accessible Large Language Model Services (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are powerful at question-answering but prone to hallucinations due to limited domain-specific or up-to-date knowledge. |
| Approach: | They propose a framework for IDentifying RAG properties in LLM services that integrates LLMs with retrieval systems and adds an external retriever and knowledge database to mitigate hallucinations. |
| Outcome: | The proposed framework detects RAG-enhanced LLMs with 99.97% accuracy with partial or no optional knowledge and nearly 100% when the LLM and database are known. |
CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work on counterfactual data augmentation only considered restricted classes of perturbations, limiting their effectiveness. |
| Approach: | They propose a retrieval-augmented framework for creating diverse counterfactual perturbations for CDA. |
| Outcome: | Experiments on natural language inference and sentiment analysis show that the proposed framework can be used to encourage diversity in manually authored perturbations. |
Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation (2025.naacl-long)
Copied to clipboard
Satyapriya Krishna, Kalpesh Krishna, Anhad Mohananey, Steven Schwarcz, Adam Stambler, Shyam Upadhyay, Manaal Faruqui
| Challenge: | Recent advances in Large Language Models (LLMs) have significantly enhanced their capabilities across various cognitive tasks. |
| Approach: | They propose a high-quality evaluation dataset to test LLMs' ability to provide factual responses, assess retrieval capabilities, and evaluate the reasoning required to generate final answers. |
| Outcome: | The proposed framework improves performance in end-to-end RAG scenarios. |
The Inefficiency of Language Models in Scholarly Retrieval: An Experimental Walk-through (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing work does not critically analyze the scientific language models to the best of our knowledge. |
| Approach: | They evaluate scientific language models in handling short-query texts and textual neighbors by leveraging perturbations to generate textual neighbor classes. |
| Outcome: | The proposed model is ineffective for retrieving documents for short-query texts under the most relaxed conditions. |
Multi-Modal Retrieval For Large Language Model Based Speech Recognition (2024.findings-acl)
Copied to clipboard
Aditya Gourav, Jari Kolehmainen, Prashanth Shivakumar, Yile Gu, Grant Strimel, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko
| Challenge: | kNN-LM and cross-attention techniques are used to extend text based retrieval to other modalities . wide adoption of large language models has driven new application areas leveraging this technology . |
| Approach: | They propose to use kNN-LM and cross-attention techniques to extend text retrieval methods to other modalities. |
| Outcome: | The proposed methods outperform text-based retrieval and improve word error rate on a speech recognition dataset. |
LLatrieval: LLM-Verified Retrieval for Verifiable Generation (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models struggle with factual errors and often produce non-factual and fabricated content. |
| Approach: | They propose to use large language models to generate text with supporting documents to enable the user to flexibly verify the answer. |
| Outcome: | Experiments on ALCE show that LLatrieval significantly outperforms extensive baselines and achieves state-of-the-art results. |
Graph Neural Network Enhanced Retrieval for Question Answering of Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing retrieval methods divide reference documents into passages, treating them in isolation. Existing methods only use contiguous passages or keywords. |
| Approach: | They propose a retrieval method that leverages graph neural networks to exploit relatedness between passages to enhance retrieval. |
| Outcome: | The proposed method improves retrieval by exploiting the relatedness between passages. |
Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLP (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that retrievers underperform on rarer entities that share a name . open-domain tasks require a knowledge source to perform reasoning and produce an answer . |
| Approach: | They propose an evaluation benchmark for retrieving entities that share a name . they define Ambiguous Entity Retrieval sets as a collection of entities that have a common name - and query about those entities. |
| Outcome: | The proposed sets underperform on rarer entities that share a name . the retrievers exhibit popularity bias, and are twice as likely to retrieve erroneous documents . |
HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for retrieving dialogue data often face challenges in capturing semantic intent or require extensive labeling and fine-tuning. |
| Approach: | They propose a framework that enhances semantic understanding in conversational data retrieval by optimizing data ingestion. |
| Outcome: | The proposed framework outperforms fine-tuned models in retrieval and intent analysis. |
CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era (2025.acl-long)
Copied to clipboard
| Challenge: | Graphs are used for storing open-domain knowledge and domain-specific enterprise data. |
| Approach: | They propose to use property graph views on top of the underlying RDF graph to efficiently query LLMs. |
| Outcome: | The proposed graph views can be efficiently queried by LLMs using Cypher . the proposed graphs have a large schema, overlapping and ambiguous relation types and lack of normalization. |
Scaling up the State Size of RNN LLMs for Long-Context Scenarios (2025.acl-long)
Copied to clipboard
| Challenge: | Existing RNN-based LLMs struggle with long-context scenarios due to their quadratic computational complexity and linear memory requirements. |
| Approach: | They propose an efficient scaling method to scale RNN models to match the 2k context length of Transformers with small parameters overhead. |
| Outcome: | The proposed method improves long-context understanding and improves performance on FDA recall-intensive tasks. |
R2AG: Incorporating Retrieval Information into Retrieval Augmented Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to augment large language models with external documents are lacking in the semantic gap between LLMs and retrievers due to differences in their training objectives and architectures. |
| Approach: | They propose to integrate R2AG into R2etrieval augmented generation framework by using a R2-Former to capture retrieval information. |
| Outcome: | The proposed framework fills the semantic gap between LLMs and retrievers due to differences in their training objectives and architectures. |
RA2FD: Distilling Faithfulness into Efficient Dialogue Systems (2024.emnlp-main)
Copied to clipboard
| Challenge: | Retrieval Augmented Generation (RAG) is effective but inference inefficient, while Retrieral Free Generations (RFG) are more efficient but sacrifice faithfulness. |
| Approach: | They propose a retrieval-free model training scheme that uses a teacher-student framework to distill the faithfulness capacity of a student's knowledge-infused responses. |
| Outcome: | The proposed model surpasses the previous SOTA RFG model on knowledge-grounded dialogue datasets by an average of 33% while improving inference efficiency. |
Ambiguous Learning from Retrieval: Towards Zero-shot Semantic Parsing (2023.acl-long)
Copied to clipboard
Shan Wu, Chunlei Xin, Hongyu Lin, Xianpei Han, Cao Liu, Jiansong Chen, Fan Yang, Guanglu Wan, Le Sun
| Challenge: | Existing neural semantic parsers require a large amount of training data which is expensive and difficult to obtain. |
| Approach: | They propose a framework for a supervised retrieval system based on pretrained language models . they propose ambiguous supervision to improve the precision and coverage of the task . |
| Outcome: | The proposed approach outperforms state-of-the-art zero-shot parsing methods in ambiguous supervision. |
Shifting from Ranking to Set Selection for Retrieval Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches primarily rerank top-k passages based on individual relevance, often failing to meet the information needs of complex queries in multi-hop question answering. |
| Approach: | They propose a set-wise passage selection approach and introduce SetR which explicitly identifies the information requirements of a query through Chain-of-Thought reasoning. |
| Outcome: | The proposed approach outperforms both proprietary LLM-based rerankers and open-source baselines in terms of answer correctness and retrieval quality. |
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multiple fine-tuning strategies exist with different costs and benefits for RAG pipelines. |
| Approach: | They evaluate several RAG fine-tuning strategies with different costs and benefits . embedding and generator models can be fine- tuned to increase performance . |
| Outcome: | The proposed techniques improve quality metrics, but have different computational costs. |
CSTree-SRI: Introspection-Driven Cognitive Semantic Tree for Multi-Turn Question Answering over Extra-Long Contexts (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved remarkable success in natural language processing (NLP), particularly in single-turn question answering (QA) on short-text. |
| Approach: | They propose a framework that captures logical correlations across chunks of ELC and maintains coherence of multi-turn Questions. |
| Outcome: | The proposed framework is able to capture logical correlations across chunks of ELC and maintain coherence of multi-turn Questions. |
Memory OS of AI Agent (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) face a shortage of long-term memory capabilities and limited personalization due to fixed context windows. |
| Approach: | They propose a Memory Operating System to achieve efficient memory management for AI agents . MemoryOS enables hierarchical memory integration and dynamic updating . |
| Outcome: | The proposed architecture enables hierarchical memory integration and dynamic updating. |
Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have not linked the behavior of retrieval augmented generation (RAG) with imperfect retrieval, including irrelevant, misleading, or even malicious information. |
| Approach: | They propose an approach that integrates external knowledge with source-awareness to overcome imperfect retrieval errors in RAG. |
| Outcome: | The proposed approach is superior to previous robustness-enhanced approaches under the worst-case scenario. |
Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-training (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for constructing long-context data by concatenating short documents have overlooked a crucial characteristic of long-constituency data quality, semantic dependency. |
| Approach: | They propose a framework called Retrieval, Dependency Recognition, and Reorder for data synthesis which leverages semantic similarity to retrieve relevant documents and form several batches. |
| Outcome: | The proposed framework leverages semantic similarity to retrieve relevant documents and form several batches. |
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies either overlook temporal shifts or hardly capture rich shifting patterns of both semantic and knowledge. |
| Approach: | They develop a temporal adaptive learning framework that captures temporal shifts . they use medical ontology and other knowledge sources to integrate temporal adaptation . |
| Outcome: | The proposed framework improves classification tasks across multiple domains and domains with knowledge integration. |
Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reasoning-intensive information retrieval suffer from inefficiency . Chain-of-Thought (CoT) approaches suffer from lack of token efficiency . Existing models lack episodic memory, which stores the history of prior states . |
| Approach: | They propose an algorithm that enhances state-based frameworks with an episodic memory module that stores the full history of prior states for a query. |
| Outcome: | The proposed model outperforms CoT and state-based models on the BRIGHT benchmark and is highly token-efficient. |