hallucination
- Papers
- 3
- Released code
- 0
- First seen
- Oct 2026
- Latest
- Nov 2026
3 papers in the last two months, against 0 in the two before.
Start here
The paper to read first- 1Voice agents lose document grounding as conversations and context grow
Document-grounded voice agents lose factual fidelity as context and conversation grow, often hallucinating instead of abstaining; cascaded systems ground best among those evaluated.
Oct 2026
How fast it is moving
Often studied with
benchmarkA standard set of tasks or data used to evaluate and compare the performance of AI systems.1 togethermemory retentionThe ability of a system to preserve and recall information over time or across contexts, often balancing compression against fidelity.1 togetherreinforcement learningA machine learning method where an agent learns to make sequences of decisions by receiving rewards or penalties for its actions.1 togetherThe papers
Most central to this idea first, not most recent.
- Big Techcs.CL
Voice agents lose document grounding as conversations and context grow
Document-grounded voice agents lose factual fidelity as context and conversation grow, often hallucinating instead of abstaining; cascaded systems ground best among those evaluated.
Adobe Research, University of Maryland College Park · Oct 2026
- Big Techcs.CL
Language models make more scientific discoveries from facts seen only once
The rate of facts appearing exactly once in training data governs large language models' capacity for scientific discovery.
Johns Hopkins University, Microsoft · Nov 2026
- Big Techcs.AI
Optimizing AI persuasion rewards fabrication unless alignment is explicitly enforced
Outcome-only reinforcement learning for persuasion boosts misaligned strategies, but combining guidance and penalties mitigates it.
Microsoft Research, Princeton University · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.