Human Feedback and Eval Paper Explorer

Match reason: Matched by broad semantic/index fallback.

• Using 1,200 annotated notes, we evaluated candidate open-weight models with multi-prompt ensemble inference and further adapted selected models using QLoRA-based supervised fine-tuning and direct preference optimization.
• Model performance varied substantially, highlighting the need for task-specific evaluation rather than reliance on generic benchmarks.

Match reason: Matched by broad semantic/index fallback.

Match reason: Matched by broad semantic/index fallback.

• To address this, we present CuraView, a multi-agent framework for sentence-level detection and evidence-grounded explanation of faithfulness hallucinations in discharge summaries.
• We evaluate CuraView on a subset of 250 patients from the Discharge-Me benchmark, with 50 patients held out for testing.

Match reason: Matched by broad semantic/index fallback.

• As conversational AI therapists are increasingly used in psychological support settings, reliable offline evaluation of therapeutic response quality remains an open problem.
• We evaluate DESG on a constructed diagnostic stress-test benchmark of 3{,}000 dialogue windows from EmpatheticDialogues, ESConv, and CRADLE-Dialogue, covering peer support, counseling dialogue, and crisis-oriented interaction.

Match reason: Matched by broad semantic/index fallback.

Match reason: Matched by broad semantic/index fallback.

• Conventional evaluation methods rely heavily on annotation-intensive reference standards or incomplete structured data, limiting feasibility at population scale.
• Using judge-evaluated outputs as references, the primary LLM achieved an F1 score of 0.80 under relaxed matching criteria.

Match reason: Matched by broad semantic/index fallback.

Match reason: Matched by broad semantic/index fallback.

• Under the same Llama3.1-8B backbone, our approach achieves an 8.2-point improvement in macro-F1 at only 20% of the training cost of standard SFT, and provides explicit supporting evidence for each predicted code, enabling human auditing and…

Match reason: Matched by broad semantic/index fallback.

• Existing artificial intelligence approaches typically optimize individual components of phenotyping but do not operationalize the full clinical workflow of extracting features from clinical text, standardizing them to Human Phenotype…
• Using clinician-curated HPO terms as the gold standard, RARE-PHENIX consistently outperformed a state-of-the-art deep learning baseline (PhenoBERT) across ontology-based similarity and precision-recall-F1 metrics in end-to-end evaluation…

Match reason: Matched by broad semantic/index fallback.

• OraPO enables single-stage, RL-only training by converting failed GRPO explorations on rare or difficult studies into direct preference supervision via a lightweight oracle step.

Match reason: Matched by broad semantic/index fallback.

• Across model sizes, Reason2Decide outperforms other fine-tuning baselines and some zero-shot LLMs in prediction (F1) and rationale fidelity (BERTScore, BLEU, LLM-as-a-Judge).
• This indicates that LLM-generated rationales are suitable for pretraining models, reducing reliance on human annotations.