Fork-think with confidence identifies forking points via model confidence in a single path before sampling continuations, cutting tokens up to 30% and runtime up to 57% on reasoning benchmarks while matching or exceeding parallel thinking performance.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
LLMs can provide cost-effective annotation of credibility in Danish asylum texts but produce inconsistent errors that vary by model and prompt, requiring checks beyond single-model accuracy.
VLMs as judges exhibit informativeness bias by favoring detailed but image-inconsistent answers; BIRCH mitigates it by first correcting answers against the image, reducing bias up to 17% and improving performance up to 9.8%.
Dialectal robustness and generation are dissociated in LLMs: benchmarks are driven by pretraining and SFT while alignment reshapes generation invisibly to benchmarks, and the method maximizing dialectal reward is least preferred by human evaluators.
OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-proof dataset.
Sync-R1 applies cooperative RL with Sync-GRPO and Dynamic Group Scaling to achieve superior cross-task personalized reasoning in multimodal models on the new UnifyBench++ dataset.
LLM-based POS tagging outperforms traditional taggers on medieval Occitan, Catalan, and French, with fine-tuning and cross-lingual transfer providing the largest gains for under-resourced varieties.
citing papers explorer
-
Fork-Think with Confidence
Fork-think with confidence identifies forking points via model confidence in a single path before sampling continuations, cutting tokens up to 30% and runtime up to 57% on reasoning benchmarks while matching or exceeding parallel thinking performance.
-
LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics
LLMs can provide cost-effective annotation of credibility in Danish asylum texts but produce inconsistent errors that vary by model and prompt, requiring checks beyond single-model accuracy.
-
When Vision-Language Models Judge Without Seeing: Exposing Informativeness Bias
VLMs as judges exhibit informativeness bias by favoring detailed but image-inconsistent answers; BIRCH mitigates it by first correcting answers against the image, reducing bias up to 17% and improving performance up to 9.8%.
-
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
Dialectal robustness and generation are dissociated in LLMs: benchmarks are driven by pretraining and SFT while alignment reshapes generation invisibly to benchmarks, and the method maximizing dialectal reward is least preferred by human evaluators.
-
OProver: A Unified Framework for Agentic Formal Theorem Proving
OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-proof dataset.
-
Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning
Sync-R1 applies cooperative RL with Sync-GRPO and Dynamic Group Scaling to achieve superior cross-task personalized reasoning in multimodal models on the new UnifyBench++ dataset.
-
From Traditional Taggers to LLMs: A Comparative Study of POS Tagging for Medieval Romance Languages
LLM-based POS tagging outperforms traditional taggers on medieval Occitan, Catalan, and French, with fine-tuning and cross-lingual transfer providing the largest gains for under-resourced varieties.