paper-with-me

Papers

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning

2026-06-01 · Atoosa Chegini, Soheil Feizi arxiv

Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requires a reward model trained with step-level labels. We propose Chunk-Level Guided Generation, a training-free alternative that uses an off-the-shelf large language model as a process scorer. At each step, a small model samples k fixed-length candidate chunks, while the larger model scores the candidates using likelihoods without generating any text. The selected chunk is committed before the next step, steering generation before errors can propagate. We instantiate this framework with two selection rules: Likelihood-Guided Selection (LGS), which selects the chunk with the highest length-normalized large-model log-probability, and Contrastive-Guided Selection (CGS), which subtracts the small model's log-probability to favor chunks where the large model's preference diverges from the small model's. We show that scoring variable-length reasoning steps with large-model likelihoods is unreliable due to a systematic length bias that persists even after length normalization, and that fixed-length chunks avoid this confound. On GSM8K, MATH, Minerva Math, AMC23, and AIME24 with Qwen2.5-1.5B guided by Qwen2.5-32B and Llama-3.2-1B guided by Llama-3.1-70B, CGS outperforms majority voting by up to 28 pp and, under matched guidance budgets, matches or outperforms Qwen2.5-Math-PRM-72B guided search on most benchmarks without reward-model training. With Qwen2.5-7B guided by Qwen2.5-72B, CGS reaches 81.8% on MATH and 63.6% on Minerva Math at k=16, surpassing majority voting by 4--6 pp. Finally, Chunk-Level Guided Generation produces substantially shorter reasoning traces than PRM guided search.

📄 PDF Abstract BibTeX arXiv:2606.01682

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Similar Papers 제목 키워드 기반

Equal Ranking Quality, Different Decisions: Training Order-Consistent LLM Scorers

2026-08-27 · Markus Frohmann, Mahdiyar Alavi, Elizabeth Lingg, Navid Rekabsaz arxiv

Rerankers, reward models and multi-document QA scorers score candidate documents or responses in one LLM prompt, so each score depends on their order. Such scorers are selected on ranking quality, but their scores determ…

Unsupervised Controllable Text Formalization

2018-09-10 · Parag Jain, Abhijit Mishra, Amar Prakash Azad, Karthik Sankaranarayanan

We propose a novel framework for controllable natural language transformation. Realizing that the requirement of parallel corpus is practically unsustainable for controllable generation tasks, an unsupervised training sc…

Decoder

UQLM: A Python Package for Uncertainty Quantification in Large Language Models

2025-07-08 · Dylan Bouchard, Mohit Singh Chauhan, David Skarbrevik, Ho-Kyeong Ra 외

Hallucinations, defined as instances where Large Language Models (LLMs) generate false or misleading content, pose a significant challenge that impacts the safety and trust of downstream applications. We introduce UQLM, …

HallucinationUncertainty Quantification

Beyond Ranking Accuracy: Evaluating LLM-Cited Feature Rationales for Next Basket Repurchase Recommendation

2026-08-31 · Yanan Cao, Anay Dombe, Murali Mohana Krishna Dandu, Shreeranjani Srirangamsridharan 외 arxiv

Next-basket repurchase recommendation is commonly formulated as a ranking task: given a customer's purchase history, the system ranks previously purchased items that may be needed again. In production settings, however, …

PEDANTS: Cheap but Effective and Interpretable Answer Equivalence

2024-02-17 · Zongxia Li, Ishani Mondal, Yijun Liang, Huy Nghiem 외

Question answering (QA) can only make progress if we know if an answer is correct, but current answer correctness (AC) metrics struggle with verbose, free-form answers from large language models (LLMs). There are two cha…

BenchmarkingFormOpen-Domain Question AnsweringQuestion Answering+1