相关论文: Reasoning on Multiple Needles In A Haystack

Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations.…

The recent rise of Large Reasoning Models (LRMs) has significantly improved multi-step reasoning performance, but often at the cost of generating excessively long reasoning chains. This paper revisits the efficiency of such reasoning…

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose…

LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs. This limitation, known as the…

Large Language Models (LLMs) have evolved from simple chatbots into sophisticated agents capable of automating complex real-world tasks, where browsing and reasoning over live web content is key to assessing retrieval and cognitive skills.…

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors.…

The rapid advancements in large language models (LLMs) have highlighted the challenge of context window limitations, primarily due to the quadratic time complexity of the self-attention mechanism (\(O(N^2)\), where \(N\) denotes the context…

Self-reflection for Large Language Models (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs' internal reflection ability or external feedback. However,…

Recent reasoning LLMs (RLMs), especially those trained with verifier-based reinforcement learning, often perform worse with few-shot CoT than with direct answering. We revisit this paradox using high-quality reasoning traces from…

This paper introduces a novel method, referred to as "hashing", which involves masking potentially bias-inducing words in large language models (LLMs) with hash-like meaningless identifiers to reduce cognitive biases and reliance on…

Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning methods compress reasoning chains by designing elaborate…

Recent advancements in long-context modeling have enhanced language models (LMs) for complex tasks across multiple NLP applications. Despite this progress, we find that these models struggle with multi-hop reasoning and exhibit decreased…

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs significant…

$K$-nearest neighbor language models ($k$NN-LMs), which integrate retrieval with next-word prediction, have demonstrated strong performance in language modeling as well as downstream NLP benchmarks. These results have led researchers to…

Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reasoning over multiple pieces of information. However, existing…

Large language models (LLMs) have demonstrated remarkable progress in understanding long-context inputs. However, benchmarks for evaluating the long-context reasoning abilities of LLMs fall behind the pace. Existing benchmarks often focus…

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…

Recent advancements in Large Language Models (LLMs) are increasingly focused on "reasoning" ability, a concept with many overlapping definitions in the LLM discourse. We take a more structured approach, distinguishing meta-level reasoning…

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…