Challenge: Retrieval-Augmented Large Language Models (RALMs) do not consistently outperform the original retrieval-free Language Model (LM).
Approach: They propose a trainable framework that can adaptively retrieve from different knowledge sources and effectively decrease unpredictable reader errors.
Outcome: The proposed framework significantly improves performance over the RALM with a single retriever by significantly reducing inconsistent behaviors.

Similar Papers

Retrieval-Augmented Retrieval: Large Language Models are Strong Zero-Shot Retriever (2024.findings-acl)

Copied to clipboard

Challenge: Large-scale retrieval is indispensable in information-seeking tasks such as open-domain question answering and knowledgegrounded dialogue.
Approach: They propose to use a large language model (LLM) to augment a query with its potential answers by prompting LLMs with a composition of the query and the query’s in-domain candidates.
Outcome: The proposed method breaks brute-force combinations of retrievers with LLMs and lifts the performance of zero-shot retrieval to be very competitive on benchmark datasets.
The Effect of Scaling, Retrieval Augmentation and Form on the Factual Consistency of Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are useful interfaces to factual knowledge, but their usefulness is limited by their tendency to deliver inconsistent answers to semantically equivalent questions.
Approach: They evaluate the effectiveness of up-scaling and augmenting the LM with a passage retrieval database to reduce inconsistency.
Outcome: The proposed models reduce inconsistency but retrieval augmentation is more efficient.
Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Large language models (LMs) excel in retrieving popular facts, but encounter difficulty with infrequent entity-relation pairs compared to retrievers.
Approach: They propose to use a WiTQA dataset to explore the effects of combinations of entities and relations on LMs.
Outcome: The proposed model can retain popular relations of less common entities while retaining the same popular relations.
In-Context Retrieval-Augmented Language Models (2023.tacl-1)

Copied to clipboard

Challenge: Existing RALM methods focus on modifying the LM architecture to facilitate incorporation of external information, complicating deployment.
Approach: They propose to condition a language model on relevant documents from a grounding corpus during generation by conditioning on external knowledge sources.
Outcome: The proposed method significantly improves language modeling performance and provides natural source attribution mechanism.
Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model (2023.findings-emnlp)

Copied to clipboard

Challenge: kNN-LM, REALM, DPR + FiD, Contriever + ATLAS, and Contriver + Flan-T5 are popular retriever-augmented language models for a variety of tasks.
Approach: They evaluate the strengths and weaknesses of kNN-LM, REALM, DPR + FiD, Contriever + ATLAS, and Contriver + Flan-T5 in reasoning over retrieved statements across different tasks.
Outcome: The proposed models do not exhibit strong reasoning even when provided with only the required statements.
BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated efficacy in knowledge-intensive tasks such as open-domain QA, but inconsistencies between retrieval knowledge and the necessary knowledge for LLMs, leading to a decline in LLM’s answer quality.
Approach: They propose a retrieval-augmented large language model that refines retrieval documents into Key Supporting Evidence (KSE) through knowledge synthesis, supervised fine-tuning, and preference alignment.
Outcome: The proposed model outperforms existing methods in five datasets and boosts answer quality by 7% while reducing input content length by 80%.
Generative Giants, Retrieval Weaklings: Why do Multimodal Large Language Models Fail at Multimodal Retrieval? (2026.findings-acl)

Copied to clipboard

Challenge: Rapid advances in multimodal large language models have revolutionized cross-modality understanding.
Approach: They propose a method that uses whitening transformations to adjust MLLM representation spaces . they propose ML models that are dominated by textual semantics and visual semantics .
Outcome: The proposed approach improves zero-shot multimodal retrieval performance without fine-tuning efforts.
Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study (2024.findings-naacl)

Copied to clipboard

Challenge: a significant portion of correct answers remain compromised by hallucinations in large language models.
Approach: They examine whether every generated sentence is grounded in retrieved documents or the model’s pre-training data.
Outcome: The findings highlight the need for more robust mechanisms in large language models to mitigate the generation of ungrounded content.
ARL2: Aligning Retrievers with Black-box Large Language Models via Self-guided Adaptive Relevance Labeling (2024.acl-long)

Copied to clipboard

Challenge: Existing retrievers are misaligned with large language models due to separate training processes and inherent black-box nature of LLMs.
Approach: They propose a retriever learning technique that harnesses LLMs as labelers to annotate and score adaptive relevance evidence.
Outcome: Extensive experiments show that ARL2 improves accuracy and reduces the cost of API calls.
Making Large Language Models Efficient Dense Retrievers (2026.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that fine-tuning large language models for dense retrieval yields strong performance, but their substantial parameter counts make them computationally inefficient.
Approach: They propose a framework for developing efficient retrievers that performs coarse-to-fine compression through a coarse-grained coarse-tuning strategy.
Outcome: The proposed framework reduces model size and inference cost while preserving performance of full-size models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations