Sameer Singh, Shayne Longpre, Anthony Chen, Kartik Perisetla, Chris Dubois, Nikhil
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Knowledge-dependent tasks typically use two sources of knowledge: parametric, learned at training time, and contextual, given as a passage at inference time. To understand how models use these sources together, we formalize the problem of knowledge conflicts, where the contextual information contradicts the learned information. Analyzing the behaviour of popular models, we measure their over-reliance on memorized information (the cause of hallucinations), and uncover important factors that exacerbate this behaviour. Lastly, we propose a simple method to mitigate over-reliance on parametric knowledge which minimizes hallucination and improves out-of-distribution generalization by 4% -7%. Our findings demonstrate the importance for practitioners to evaluate model tendency to hallucinate rather than read, and show that our mitigation strategy encourages generalization to evolving information (i.e., time-dependent queries). To encourage these practices, we have released our framework for generating knowledge conflicts. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.05052")
get_code_for_paper("2109.05052")
have("2109.05052")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.05052.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.05052)
Connect an agent — have() is free.