CarryOnBench shows LLMs recover utility from benign intent clarifications in multi-turn talks but exhibit utility lock-in, unsafe recovery, and repetitive responses.
Title resolution pending
6 Pith papers cite this work, alongside 45 external citations. Polarity classification is still indexing.
6
Pith papers citing it
45
external citations · Crossref
representative citing papers
Political bias audits of LLMs largely capture sycophantic accommodation to the inferred political identity of the asker rather than any fixed model ideology.
Each tested LLM shows its own characteristic unreliability when engaging in repair during extended math-question dialogues.
Both humans and LLMs trust content more when labeled human-authored than AI-generated, with LLMs showing denser attention to labels and higher uncertainty under AI labels, mirroring human heuristic patterns.
The paper maps LLM agent architectures onto a six-level continuum and argues that higher levels can enable simulation of emergent social phenomena while requiring attention to reproducibility and ethical issues.
citing papers explorer
-
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
CarryOnBench shows LLMs recover utility from benign intent clarifications in multi-turn talks but exhibit utility lock-in, unsafe recovery, and repetitive responses.
-
Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor
Political bias audits of LLMs largely capture sycophantic accommodation to the inferred political identity of the asker rather than any fixed model ideology.
-
Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs
Each tested LLM shows its own characteristic unreliability when engaging in repair during extended math-question dialogues.
-
Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
Both humans and LLMs trust content more when labeled human-authored than AI-generated, with LLMs showing denser attention to labels and higher uncertainty under AI labels, mirroring human heuristic patterns.
-
Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research
The paper maps LLM agent architectures onto a six-level continuum and argues that higher levels can enable simulation of emergent social phenomena while requiring attention to reproducibility and ethical issues.
- iPOE: Interpretable Prompt Optimization via Explanations