cs.CL · 2026-08-26 · No. 96

Computation and Language, 2026-08-26.

7 new papers in cs.CL. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

7 entries
  1. 01

    Reading Is Not Using: Retrieval, Judgment, and the Design of AI Financial Research Workflows

    Miao Liu, Zhizhe Liu

    cs.CL · cs.AI

    Large language models (LLMs) are increasingly deployed as AI analysts to process financial disclosures and support AI-assisted investment decisions. Yet such systems are usually evaluated by what they can retrieve, not whether retrieved information affects their judgments. We identify a retrieval-integration gap in long-context financial analysis. Holding focal-firm information fixed and varying only unrelated context from 2,000 to 128,000...

    arxiv.org/abs/2608.24842 · PDF

  2. 02

    The RAT: A Unified Bayesian Model for RAG Evaluation

    Pius von Däniken, Felix Matthias Saaro, Mark Cieliebak, Jan Deriu

    cs.CL · cs.AI

    Evaluating Retrieval-Augmented Generation (RAG) systems requires assessing not only end-to-end correctness but also how individual components interact and how errors propagate through the pipeline. We introduce a Bayesian evaluation framework that jointly models retrieval success, abstention behavior, and answer correctness, factorized according to the pipeline's information flow. The model distinguishes task success. Whether the user...

    arxiv.org/abs/2608.24753 · PDF

  3. 03

    FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision

    Qiming Xie, Wenjie Zheng, Xiangqing Shen, Rui Xia

    cs.CL · cs.AI

    To reduce the hallucination risk caused by outcome-driven rewards in large language models trained through reinforcement learning with verifiable rewards, existing mitigation approaches introduce process-level factual supervision. However, due to coarse-grained aggregation of factual signals and the lack of reliability assessment for these signals, they create a mismatch between fact verification and policy updates. We term this noisy factual...

    arxiv.org/abs/2608.24350 · PDF

  4. 04

    SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling

    Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios, Navid Rekabsaz, Markus Schedl

    cs.CL · cs.AI

    Recent controllable text generation (CTG) for sentiment control has largely focused on decoder-based large language models, making causal attention the dominant paradigm. While effective for fluent generation, these models still struggle to satisfy complex constraints and follow fine-grained sentiment signals specified by users. Existing sentiment-aware CTG methods typically simplify the problem by treating sentiment either as a coarse...

    arxiv.org/abs/2608.24304 · PDF

  5. 05

    'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection

    Fawzia Zehra, Kara-Isitt, Sonal Khosla, Stephen Swift

    cs.CL · cs.AI

    Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine years of WOAH proceedings. To investigate whether this absence has measurable consequences for content moderation reliability, five large language models, GPT-4o, Claude Sonnet 4.5, Gemini 2.5 Flash, Qwen-2.5, and Llama-3.1, were tested across six datasets spanning Nastaliq Urdu, Roman Urdu,...

    arxiv.org/abs/2608.24191 · PDF

  6. 06

    PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding

    Md Mahadi Hasan Nahid, Davood Rafiei

    cs.CL · cs.AI · cs.IR

    Large Language Models (LLMs) have shown strong capabilities in table reasoning, but their effectiveness degrades as tables grow in size and complexity due to irrelevant context and difficulty localizing the evidence required for reasoning. Existing approaches typically reason over either the full table or a single reduced view, which can still obscure important row-column relationships. We introducePARTAB (Partition-Aware Reasoning...

    arxiv.org/abs/2608.24082 · PDF

  7. 07

    When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and the Behavior of LLMs

    Zhiyang Qi

    cs.CL · cs.AI

    In psychological counseling, effective support is not always delivered through long, information-rich responses. Minimal responses, such as backchannel cues and concise empathic statements, help convey attentive listening, express empathy, and encourage clients to continue expressing themselves. However, existing counseling dialogue systems and evaluation frameworks often favor explicit, content-rich replies, overlooking the interactional...

    arxiv.org/abs/2608.24080 · PDF

This edition is part of The Daily Abstract — cs.CL archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.