REVIEW 30 cited by
Retrieval Augmentation Reduces Hallucination in Conversation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Retrieval Augmentation Reduces Hallucination in Conversation
read the original abstract
Despite showing increasingly human-like conversational abilities, state-of-the-art dialogue models often suffer from factual incorrectness and hallucination of knowledge (Roller et al., 2020). In this work we explore the use of neural-retrieval-in-the-loop architectures - recently shown to be effective in open-domain QA (Lewis et al., 2020b; Izacard and Grave, 2020) - for knowledge-grounded dialogue, a task that is arguably more challenging as it requires querying based on complex multi-turn dialogue context and generating conversationally coherent responses. We study various types of architectures with multiple components - retrievers, rankers, and encoder-decoders - with the goal of maximizing knowledgeability while retaining conversational ability. We demonstrate that our best models obtain state-of-the-art performance on two knowledge-grounded conversational tasks. The models exhibit open-domain conversational capabilities, generalize effectively to scenarios not within the training data, and, as verified by human evaluations, substantially reduce the well-known problem of knowledge hallucination in state-of-the-art chatbots.
Forward citations
Cited by 30 Pith papers
-
TruthfulQA: Measuring How Models Mimic Human Falsehoods
A new benchmark reveals that language models including GPT-3 are truthful on only 58% of questions designed to elicit popular misconceptions, far below human performance of 94%, with larger models performing worse.
-
K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance
K-FinHallu is the first multi-turn Korean financial RAG hallucination benchmark; frontier LLMs struggle especially on justified abstention while an 8B fine-tuned model reaches competitive performance.
-
GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference t...
-
Improving language models by retrieving from trillions of tokens
RETRO matches GPT-3 and Jurassic-1 performance on the Pile benchmark using 25 times fewer parameters by conditioning on retrieved chunks from a 2-trillion-token database.
-
Inference Cost Attacks for Retrieval-Augmented Large Language Models
Poisoning external knowledge bases with LLM-agent-crafted documents can increase RAG inference token consumption by up to 13.12 times at over 90% success rate while preserving answer quality.
-
GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
GraphSteal recovers over 90% of a Graph RAG knowledge graph via depth-wise heuristic search for node attributes and breadth-wise diffusion search for topology.
-
MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration
MindTrellis enables users and AI to co-create evolving knowledge graphs, outperforming retrieval-only tools in expert-rated content coverage, structural quality, and reduced cognitive load during a study of 12 partici...
-
Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
RRPO formulates document reranking as a sequential MDP and optimizes a pointwise reranker with PPO using LLM generation rewards and a reference-anchored deterministic baseline.
-
UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough
UnWeaver disentangles documents into entities via LLM to retrieve original chunks, yielding a simpler alternative to GraphRAG that still reduces noise and preserves source fidelity.
-
MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval
MCERF delivers a 41.1% relative accuracy gain on the DesignQA benchmark by combining ColPali vision-language retrieval with four specialized reasoning modes and dynamic routing.
-
Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation
Fine-tuning on new knowledge induces propagating hallucinations in LLMs by weakening attention to key entities, with mitigation via reintroducing known knowledge during later training stages.
-
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
ZeroSearch uses supervised fine-tuning to create a simulated retrieval module and curriculum-based RL rollouts that degrade document quality to train LLMs on search capabilities without real search API calls.
-
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
ZeroSearch simulates search engine interactions via supervised fine-tuning of a retrieval module and curriculum-based RL degradation of document quality, achieving comparable or superior performance to real search eng...
-
Hallucinations are inevitable but can be made statistically negligible
Hallucinations are inevitable on an infinite set of inputs but can be made statistically negligible with sufficient training data quality and quantity.
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Chain-of-Verification reduces hallucinations in large language models by drafting responses, planning independent verification questions, answering them separately, and generating a final verified output.
-
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Atlas reaches over 42% accuracy on Natural Questions with only 64 examples, outperforming a 540B-parameter model by 3% with 50x fewer parameters.
-
LaMDA: Language Models for Dialog Applications
LaMDA shows that fine-tuning on human-value annotations and consulting external knowledge sources significantly improves safety and factual grounding in large dialog models beyond what scaling alone achieves.
-
X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment
X3-OPD improves audio-grounded reasoning by training the audio student on its own rollouts with token-level teacher feedback, using a three-tier paired text-audio corpus.
-
Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
Four attention metrics enable logistic regression classifiers that detect hallucinations in SpeechLLMs with up to +0.23 PR-AUC gains over baselines on ASR and translation tasks.
-
HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
HG-RAG retrieves context by walking up, across, and down a hierarchical knowledge graph and outperforms flat dense retrieval on synthetic hierarchy queries—though its hallucination-rate claim is contradicted by its ow...
-
UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough
A new RAG method that retrieves chunks through aggregated entity descriptions performs on par with or slightly better than plain vector RAG, and both beat Microsoft's GraphRAG on three QA benchmarks.
-
ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education
ARIA is a multimodal RAG framework that filters domain-specific questions with 97.5% accuracy and outperforms ChatGPT-5 on pedagogical quality for a university civil engineering course.
-
MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval
A multimodal RAG framework with ColPali retrieval and task-specific reasoning variants reports 32.6% relative improvement over prior RAG baselines on DesignQA, but the gain is inflated by test-set-fitted routing and a...
-
Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Evidence-Centered Design for Supporting Physics Problem Solving
An ECD-grounded LLM feedback system for physics problems was rated useful and accurate by students yet contained unnoticed errors in 20% of cases.
-
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
-
RAG-TESTER: Automated End-to-End Testing of Retrieval-Augmented Large Language Models
A coverage-oriented test generator that adds negative-rejection and complex-passage queries to RAG evaluation, reported to detect 6.6% more failures than a strategy-free baseline in 24 model configurations.
-
Silent Failure in LLM Agent Systems: The Entropy Principle and the Inevitable Disorder of Autonomous Agents
LLM agent systems accumulate disorder leading to silent failures, formalized by the exponential Entropy Principle S(t) = S0 * e^(alpha * t) with empirically measured alpha, countered by proposed PIG Engine and ADE protocols.
-
Inteligencia Artificial jur\'idica y el desaf\'io de la veracidad: an\'alisis de alucinaciones, optimizaci\'on de RAG y principios para una integraci\'on responsable
Legal AI hallucination persists in commercial RAG tools (17-34%+ of queries), so the report argues the fix is consultative, source-citing system design plus mandatory human oversight, not better generative models.
-
Agent AI: Surveying the Horizons of Multimodal Interaction
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
-
Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems
A position and survey paper that identifies convergence between neuroscience, AGI, and neuromorphic computing and outlines four key integration challenges.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.