相关论文: When Small Models Are Right for Wrong Reasons: Pro…

Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent works have begun exploring how to train LLMs to use search engines more effectively as tools for…

Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reasoning used to produce it. This highlights a fundamental…

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…

Objective: This study develops a systematic benchmarking framework for testing whether language models can accurately identify constructs of interest in child welfare records. The objective is to assess how different model sizes and…

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claims to be iteratively refined over time. This process requires…

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Large Language Models (LLMs) have great potential to accelerate and support scholarly peer review and are increasingly used as fully automatic review generators (ARGs). However, potential biases and systematic errors may pose significant…

Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-making scenarios where user queries are laden with cognitive…

Artificial intelligence and machine learning are increasingly used for forecasting, optimization, and policy design in the energy sector, yet no standardized framework exists to evaluate whether these systems reason correctly. Current…

Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects critical to trustworthiness. We argue that usable reasoning systems must be trustworthy,…

Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes. A common assumption is that the reasoning chains trained through RLVR reliably represent…

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the…

Incorporating specific knowledge into large language models via retrieval-augmented generation (RAG) is a widespread technique that fuels many of today's industry AI applications. A fundamental problem is to assess if the context retrieved…

Large language models can produce correct answers while relying on flawed reasoning traces, partly because common training objectives reward final-answer correctness rather than faithful intermediate reasoning. This undermines…

Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…

Reasoning in large language models has long been a central research focus, and recent studies employing reinforcement learning (RL) have introduced diverse methods that yield substantial performance gains with minimal or even no external…

Large language models have achieved strong performance on medical reasoning benchmarks, yet their deployment in clinical settings demands rigorous verification to ensure factual accuracy. While reward models offer a scalable approach for…

Foundation model reliability assessment typically requires thousands of evaluation examples, making it computationally expensive and time-consuming for real-world deployment. We introduce microprobe, a novel approach that achieves…

Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works equip reinforcement learning (RL)-based LRMs with retrieval capabilities, they…