Pith. sign in

REVIEW 5 cited by

Examining Identity Drift in Conversations of LLM Agents

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

arxiv 2412.00804 v2 pith:2EGZCGZR submitted 2024-12-01 cs.CY cs.CL

classification cs.CYcs.CL
keywords identityconversationsdriftllmspersonaeffectfindingshelp
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) show impressive conversational abilities but sometimes show identity drift problems, where their interaction patterns or styles change over time. As the problem has not been thoroughly examined yet, this study examines identity consistency across nine LLMs. Specifically, we (1) investigate whether LLMs could maintain consistent patterns (or identity) and (2) analyze the effect of the model family, parameter sizes, and provided persona types. Our experiments involve multi-turn conversations on personal themes, analyzed in qualitative and quantitative ways. Experimental results indicate three findings. (1) Larger models experience greater identity drift. (2) Model differences exist, but their effect is not stronger than parameter sizes. (3) Assigning a persona may not help to maintain identity. We hope these three findings can help to improve persona stability in AI-driven dialogue systems, particularly in long-term conversations.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Two Confounds in Cross-Model Value Comparison: Response Determinism and the Access Harness

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Cross-model value distances from single draws are inflated by response determinism and confounded by the deployment client; a repeated counterbalanced protocol plus flip/magnitude decomposition separates them.

  2. A Scalable Approach to Evaluating Moral Sensitivity in LLMs

    cs.CY 2026-07 conditional novelty 6.5 of 10

    Under morally irrelevant noise, eight LLMs preserve the semantic content of identified moral features above calibrated floors, despite significant changes in feature counts.

  3. Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes

    cs.CL 2026-01 conditional novelty 6.0 of 10

    A controlled study of 211 personas shows that moral disposition, not profile structure or familiarity, is the main bottleneck in role-playing agents, and a field-aware contrastive decoding method narrows the moral–imm...

  4. AI YOU Town: Make Friends and Money with Your Digital Twin

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A unified LLM pipeline with Bayesian trait updates, conformal sets, and periodic memory-anchor refresh improves calibration and long-horizon persona fidelity over static prompting on module benchmarks.

  5. LLM Harms: A Taxonomy and Discussion

    cs.CY 2025-12 unverdicted novelty 3.0 of 10

    This paper proposes a taxonomy of LLM harms in five categories and suggests mitigation strategies plus a dynamic auditing system for responsible development.

Pith tools