Optimal preference elicitation in conversational recommenders is stage-dependent (attributes early, items later), and a MoE model trained on a new annotated dataset improves offline recommendation and response quality.
2018.Content analysis: An introduction to its methodology
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Analysis of the LMArena dataset reveals heavy topic skew and varying model rankings, leading to an interactive visualization tool for users to define custom evaluation priorities on LLM leaderboards.
Rationale for code changes is scattered across artifact types (Goal in commit messages; Need and Alternatives in issues/PRs), and an LLM pipeline (ARGUS) extracts and summarizes these components with high recall (93.2%) but moderate precision (51.4%).
citing papers explorer
-
When and How to Ask: Dynamic Preference Elicitation Strategies for Conversational Recommendation
Optimal preference elicitation in conversational recommenders is stage-dependent (attributes early, items later), and a MoE model trained on a new annotated dataset improves offline recommendation and response quality.
-
Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards
Analysis of the LMArena dataset reveals heavy topic skew and varying model rankings, leading to an interactive visualization tool for users to define custom evaluation priorities on LLM leaderboards.
-
Recovering Fine-Grained Code Change Rationale from Multiple Software Artifacts
Rationale for code changes is scattered across artifact types (Goal in commit messages; Need and Alternatives in issues/PRs), and an LLM pipeline (ARGUS) extracts and summarizes these components with high recall (93.2%) but moderate precision (51.4%).