REVIEW 6 cited by
The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
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
read the original abstract
Hallucination is a persistent challenge in large language models (LLMs), where even with rigorous quality control, models often generate distorted facts. This paradox, in which error generation continues despite high-quality training data, calls for a deeper understanding of the underlying LLM mechanisms. To address it, we propose a novel concept: knowledge overshadowing, where model's dominant knowledge can obscure less prominent knowledge during text generation, causing the model to fabricate inaccurate details. Building on this idea, we introduce a novel framework to quantify factual hallucinations by modeling knowledge overshadowing. Central to our approach is the log-linear law, which predicts that the rate of factual hallucination increases linearly with the logarithmic scale of (1) Knowledge Popularity, (2) Knowledge Length, and (3) Model Size. The law provides a means to preemptively quantify hallucinations, offering foresight into their occurrence even before model training or inference. Built on overshadowing effect, we propose a new decoding strategy CoDa, to mitigate hallucinations, which notably enhance model factuality on Overshadow (27.9%), MemoTrap (13.1%) and NQ-Swap (18.3%). Our findings not only deepen understandings of the underlying mechanisms behind hallucinations but also provide actionable insights for developing more predictable and controllable language models.
Forward citations
Cited by 6 Pith papers
-
Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints
Pointwise constrained fine-tuning via sample-wise augmented Lagrangians and learned relaxations reduces tail constraint violations across safety, tool-calling, and re-ranking while preserving average task performance.
-
Reliability Scales Inversely: Hallucinations Snowball Faster in Bigger Language Models
Hallucination in LLMs is driven by an oracle-invisible “decoding risk” term that grows with scale and causally compounds errors within a response.
-
Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
PhantomCircuit traces knowledge overshadowing to attention circuits during training and prunes circuit edges to recover the overshadowed answer.
-
Concept Incongruence: An Exploration of Time and Death in Role Playing
LLMs asked to role-play dead historical figures rarely abstain from answering post-death questions, and their factual accuracy drops due to poorly encoded death states and role-playing-induced shifts in temporal repre...
-
Large Language Models for Spreadsheets: Benchmarking Progress and Evaluating Performance with FLARE
FLARE, a new spreadsheet benchmark, shows that 20 LLMs do well on simple formulas but frequently fail on multi-step, logic-heavy spreadsheet tasks.
-
A comprehensive taxonomy of hallucinations in Large Language Models
A survey that organizes LLM hallucination types, causes, benchmarks, and mitigations, and restates the theorem that hallucination is inevitable for computable LLMs.
Discussion (0). Continue with ORCID to comment.