CBEA with LCV bounds evidence sets and validates commitments before response generation, achieving zero failures in scoped tests at 0.49-0.60 availability versus near-zero for baselines.
Kexin Li, Pengjin Wang, and Gaowei Chen
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 3polarities
background 3representative citing papers
Omni-Persona benchmark with 18 tasks shows open-source models have audio-visual grounding gaps, RLVR narrows them but leads to conservative outputs, and scale or recall alone fail as diagnostics.
Introduces MPT benchmark and PRefine method that models user preferences as evolving hypotheses to improve personalized tool calling accuracy with 1.24% of full-history token cost.
Malleable Prompting reifies subjective preferences from natural language into GUI widgets and modulates LLM token probabilities during decoding to enable controllable generation, with a user study showing improved precision and perceived controllability over standard prompting.
MAESTRO adds a shared preference memory plus GUI-adaptation and workflow-navigation mechanisms to conversational agents with GUIs and tests them in a 33-person movie-booking study.
Debiasing-DPO reduces bias to spurious social contexts by 84% and improves predictive accuracy by 52% on average for LLMs evaluating U.S. classroom transcripts.
citing papers explorer
-
Recall Isn't Enough: Bounding Commitments in Personalized Language Systems
CBEA with LCV bounds evidence sets and validates commitments before response generation, achieving zero failures in scoped tests at 0.49-0.60 availability versus near-zero for baselines.
-
Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization
Omni-Persona benchmark with 18 tasks shows open-source models have audio-visual grounding gaps, RLVR narrows them but leads to conservative outputs, and scale or recall alone fail as diagnostics.
-
Latent Preference Modeling for Cross-Session Personalized Tool Calling
Introduces MPT benchmark and PRefine method that models user preferences as evolving hypotheses to improve personalized tool calling accuracy with 1.24% of full-history token cost.
-
From Words to Widgets for Controllable LLM Generation
Malleable Prompting reifies subjective preferences from natural language into GUI widgets and modulates LLM token probabilities during decoding to enable controllable generation, with a user study showing improved precision and perceived controllability over standard prompting.
-
MAESTRO: Adapting GUIs and Guiding Navigation with User Preferences in Conversational Agents with GUIs
MAESTRO adds a shared preference memory plus GUI-adaptation and workflow-navigation mechanisms to conversational agents with GUIs and tests them in a 33-person movie-booking study.
-
Mitigating LLM biases toward spurious social contexts using direct preference optimization
Debiasing-DPO reduces bias to spurious social contexts by 84% and improves predictive accuracy by 52% on average for LLMs evaluating U.S. classroom transcripts.