Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
hub
Enabling large language models to generate text with citations
15 Pith papers cite this work, alongside 156 external citations. Polarity classification is still indexing.
15
Pith papers citing it
156
external citations · OpenAlex
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
AuthorityBench shows citation presence (real or fabricated) increases LLM hallucination rates vs no-citation baseline, strongest for fabricated citations on true claims, with domain variation but negligible venue or author effects.
Activation patching reveals that citation decisions in Llama-3.1-8B RAG are implemented by a distributed attributional ensemble of heads and layers; targeted interventions fix most missed and spurious citations on PopQA.
Commercial AI chatbots reach over 90% multiple-choice accuracy on recent news facts but lose 11-17% in free response and drop to 19-70% on subtle false-premise questions, with retrieval failures causing most errors and clear Anglophone bias.
Proposes SCSuff metric for evaluating LLM explanation sufficiency via model-generated alternative inputs, showing explanations are typically insufficient and predictable from hidden states.
Grounded Decoding fuses full-RAG and retrieval-only next-token distributions via normalized geometric mean from a KL-barycenter to improve factual consistency and citation quality in RAG.
BAG prompts LLMs to reason over K sampled responses for strategy selection in multi-turn ambiguous QA, improving accuracy and faithfulness to uncertainty over baselines across six models.
Active Indexing with synthetic data augmentation for bidirectional fact-source binding during pretraining yields up to 30.2% higher citation precision than passive identifier appending on CitePretrainBench for Qwen models.
A code-owned harness enforces source, routing, trace, hygiene, and recommendation contracts for enterprise LLM agents; prompt-only fails and bolt-on guardrails over-refuse.
FaithMed applies reinforcement learning with process-level rewards derived from evidence-based medicine rubrics to improve both task performance and reasoning faithfulness in medical LLMs.
RUBEN discovers minimal rule sets explaining RAG LLM outputs via novel pruning and applies them to evaluate LLM safety against adversarial injections.
VerifAI is an open-source biomedical QA system that decomposes generated answers into claims and verifies them with a fine-tuned NLI engine to reduce hallucinations and provide traceable citations.
MATCH augments sparsified attention with an efficient in-context retrieval system to boost performance on long-range recall tasks in transformers.
Binary groundedness judgments in AI evaluations should be replaced by a reader-centered taxonomy of support relations that distinguishes syntactic and interpretive moves between generated statements and source documents.
The authors propose an evaluation framework for LLM-generated structured search summaries and describe plans for implementing and testing it.
citing papers explorer
-
Evaluating Very Long-Term Conversational Memory of LLM Agents
Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
-
Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models
AuthorityBench shows citation presence (real or fabricated) increases LLM hallucination rates vs no-citation baseline, strongest for fabricated citations on true claims, with domain variation but negligible venue or author effects.
-
How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
Activation patching reveals that citation decisions in Llama-3.1-8B RAG are implemented by a distributed attributional ensemble of heads and layers; targeted interventions fix most missed and spurious citations on PopQA.
-
Evaluating Commercial AI Chatbots as News Intermediaries
Commercial AI chatbots reach over 90% multiple-choice accuracy on recent news facts but lose 11-17% in free response and drop to 19-70% on subtle false-premise questions, with retrieval failures causing most errors and clear Anglophone bias.
-
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
Proposes SCSuff metric for evaluating LLM explanation sufficiency via model-generated alternative inputs, showing explanations are typically insufficient and predictable from hidden states.
-
Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG
Grounded Decoding fuses full-RAG and retrieval-only next-token distributions via normalized geometric mean from a KL-barycenter to improve factual consistency and citation quality in RAG.
-
Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
BAG prompts LLMs to reason over K sampled responses for strategy selection in multi-turn ambiguous QA, improving accuracy and faithfulness to uncertainty over baselines across six models.
-
Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
Active Indexing with synthetic data augmentation for bidirectional fact-source binding during pretraining yields up to 30.2% higher citation precision than passive identifier appending on CitePretrainBench for Qwen models.
-
From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents
A code-owned harness enforces source, routing, trace, hygiene, and recommendation contracts for enterprise LLM agents; prompt-only fails and bolt-on guardrails over-refuse.
-
FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning
FaithMed applies reinforcement learning with process-level rewards derived from evidence-based medicine rubrics to improve both task performance and reasoning faithfulness in medical LLMs.
-
RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems
RUBEN discovers minimal rule sets explaining RAG LLM outputs via novel pruning and applies them to evaluate LLM safety against adversarial injections.
-
VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering
VerifAI is an open-source biomedical QA system that decomposes generated answers into claims and verifies them with a fine-tuned NLI engine to reduce hallucinations and provide traceable citations.
-
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers
MATCH augments sparsified attention with an efficient in-context retrieval system to boost performance on long-range recall tasks in transformers.
-
From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output
Binary groundedness judgments in AI evaluations should be replaced by a reader-centered taxonomy of support relations that distinguishes syntactic and interpretive moves between generated statements and source documents.
-
Plans for Evaluating Structured Generative Search Summaries
The authors propose an evaluation framework for LLM-generated structured search summaries and describe plans for implementing and testing it.