REVIEW 8 cited by
Character-LLM: A Trainable Agent for Role-Playing
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
Large language models (LLMs) can be used to serve as agents to simulate human behaviors, given the powerful ability to understand human instructions and provide high-quality generated texts. Such ability stimulates us to wonder whether LLMs can simulate a person in a higher form than simple human behaviors. Therefore, we aim to train an agent with the profile, experience, and emotional states of a specific person instead of using limited prompts to instruct ChatGPT API. In this work, we introduce Character-LLM that teach LLMs to act as specific people such as Beethoven, Queen Cleopatra, Julius Caesar, etc. Our method focuses on editing profiles as experiences of a certain character and training models to be personal simulacra with these experiences. To assess the effectiveness of our approach, we build a test playground that interviews trained agents and evaluates whether the agents \textit{memorize} their characters and experiences. Experimental results show interesting observations that help build future simulacra of humankind.
Forward citations
Cited by 8 Pith papers
-
ProEvent: An Event-centric Benchmark for Proactive Agents
ProEvent is a benchmark showing LLM agents keep a user's event timetable from chats poorly, with the best fully-correct score at 27.2%.
-
LLMs vs. Chinese Anime Enthusiasts: A Comparative Study on Emotionally Supportive Role-Playing
ChatAnime, a new emotionally supportive anime role-play benchmark, reports top LLMs outperforming human enthusiasts on role-playing and emotional support metrics while humans keep the diversity edge.
-
CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
A role-playing LLM that reasons about the scene and its own state before responding, trained with two semantic rewards, beats stronger baselines on role-play benchmarks.
-
H2HTalk: Evaluating Large Language Models as Emotional Companion
H2HTalk is a new 4,650-scenario benchmark that scores LLM emotional companions on dialogue, memory, and itinerary planning, and finds models struggle with implicit needs and long-horizon memory.
-
SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussion
A multi-agent LLM system called SimuPanel simulates expert panel discussions with personas grounded in public academic sources, and a small evaluation suggests the full reasoning pipeline produces higher LLM-judged di...
-
Can Past Experience Accelerate LLM Reasoning?
LLMs can cut reasoning compute by up to 56% on similar questions when memory of past correct solutions is combined with adaptive early stopping, though the benchmark is small and synthetic.
-
SPeCtrum: A Grounded Framework for Multidimensional Identity Representation in LLM-Based Agent
SPeCtrum shows that short personal essays (life context) are the most powerful identity signal for LLM personas of fictional characters, but real people rate a persona built from all three layers as most authentic.
-
Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects
Hiding character names lowers role-play performance, and adding self-generated personality descriptions partially restores fidelity in anonymous role-playing.
Discussion (0). Continue with ORCID to comment.