REVIEW 6 cited by
Role-Play with Large Language Models
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
As dialogue agents become increasingly human-like in their performance, it is imperative that we develop effective ways to describe their behaviour in high-level terms without falling into the trap of anthropomorphism. In this paper, we foreground the concept of role-play. Casting dialogue agent behaviour in terms of role-play allows us to draw on familiar folk psychological terms, without ascribing human characteristics to language models they in fact lack. Two important cases of dialogue agent behaviour are addressed this way, namely (apparent) deception and (apparent) self-awareness.
Forward citations
Cited by 6 Pith papers
-
Towards Efficient and Effective Alignment of Large Language Models
A thesis presenting Lion, WebR, LTE, BMC, and FollowBench, five empirical methods that together address LLM alignment data, training, and evaluation.
-
Role Steering of Language Models for Social Simulations
A role-steering screening workflow on 275 roles shows role-specific activation directions beat a non-scale-matched assistant-direction control (63.2 vs 41.1 judged alignment) and flags 38 roles as 'anti-controllable'.
-
LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions
Language agents' believability and goal achievement decline over multi-episode social interactions, and curated memory summaries only partially close the gap with humans.
-
Evaluating Intra-firm LLM Alignment Strategies in Business Contexts
Firms should intentionally align AI assistants' embedded perspectives using supportive, adversarial, or diverse strategies to protect workplace culture and moral norms.
-
Multi-modal Traffic Scenario Generation for Autonomous Driving System Testing
TrafficComposer combines an LLM text parser and computer-vision object and lane detectors to generate executable CARLA/LGSVL traffic scenarios, reporting 97% IR accuracy and improved ADS fuzz testing.
-
Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs
PsPLUG, a soft-prompt plug-in trained with style-conditioned preference pairs, preserves user identity under explicit style instructions and lets users tune personalization strength via an α scalar.
Discussion (0). Continue with ORCID to comment.