arXiv AI
CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 20
CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition
Large Language Models (LLMs) are increasingly used as research collaborators for hypothesis refinement, methodological planning, and technical analysis across multi-turn interactions. In this setting,...
arXiv Machine Learning
Jul 31
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
arXiv:2604. 07343v2 Announce Type: replace-cross Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values.
Hugging Face Trending Papers
Aug 18
Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking
Large language models (LLMs) are increasingly used for scientific hypothesis generation. However, evaluating generated hypotheses remains a challenge for trustworthy AI-enabled scientific workflows.
arXiv Computation and Language
Oct 5
Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting
The Writerslogic team participated in the CLEF 2026 SimpleText shared task, tackling both text simplification (Task 1) and complexity spotting (Task 2). For simplification, they built a multi‑candidate pipeline with GPT‑4o‑mini, selecting the best candidate via a reference‑free heuristic, and their Claude Sonnet 4 submission achieved a SARI of 47.43 and BLEU of 14.21, ranking third overall on the Task 1 leaderboard. For complexity spotting, they fine‑tuned a DeBERTa‑v3‑large NLI model on 350 K labeled pairs, achieving a macro F1 of 0.8081 (0.8085 in an ensemble) on binary over‑generation identification and 0.804 accuracy on multi‑class error classification, placing them second among unique teams.
arXiv AI
Aug 19
Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking
The paper investigates whether large language models (LLMs) can reliably assess scientific hypotheses by using a logit-based energy scoring method that leverages the model’s intrinsic confidence. Across 1,323 papers in 12 disciplines, this intrinsic scoring achieved a 33.0% Hit@1 rate, outperforming a prompted listwise ranking approach that scored 16.6%. The best result, a 1‑billion‑parameter model with logit-based energy scoring, reached 53.1% Hit@1, suggesting that confidence‑based evaluation could improve trustworthy AI‑enabled scientific discovery.
arXiv Computation and Language
Sep 1
PaperGym: Rubric-Centered Evolution for Research-Plan Generation
PaperGym is a framework that transforms each research paper into a training environment for AI research planning, using rubrics extracted from the paper’s method and experiments as a critic. It synthesizes research questions from the goal and background, and derives evaluation criteria from the method and experiments, reducing criterion leakage to 3.7%. Experiments with Qwen models show that training with PaperGym’s rubric improves benchmark performance by up to 5.6 points and outperforms existing datasets and fine‑tuning baselines.