Papers with LCLMs
Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models (2026.eacl-short)
Copied to clipboard
| Challenge: | Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative to retrieval-augmented generation (RAG). |
| Approach: | They propose to use LCLMs to encode documents with context windows of millions of tokens to improve their performance. |
| Outcome: | The proposed training strategies improve long-context performance and their robustness under compression techniques. |
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent Long-Context Language Models (LCLMs) do not capture how evidence should be connected . a new framework that integrates thought templates into LCLM frameworks is proving useful . |
| Approach: | They propose a framework that iteratively refines reusable reasoning patterns derived from prior problem solving to improve their templates. |
| Outcome: | The proposed framework outperforms baselines on knowledge-intensive multi-hop reasoning benchmarks and practical scenarios without retrieval. |
Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks like LOFT often overestimate LCLM performance by providing overly simplified contexts. |
| Approach: | They propose to use retrieval-attention-probing to filter and de-noise long contexts during decoding and joint retrieval head training alongside the generation head to improve LCLM performance. |
| Outcome: | The proposed approach outperforms RAG and GPT-4-Turbo on most tasks despite being a much smaller model. |
Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps (2025.findings-emnlp)
Copied to clipboard
| Challenge: | despite their extensive context window, long-context language models fail in some basic cases . a recent study shows that long-cot methods are not necessary for long-constituency tasks . |
| Approach: | a new study evaluates long-context language models with a large context window . the authors propose a method that can be well addressed with arbitrary reasoning steps . |
| Outcome: | The proposed methods are well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts. |
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel (2025.findings-acl)
Copied to clipboard
Yijiong Yu, Huiqiang Jiang, Xufang Luo, Qianhui Wu, Chin-Yew Lin, Dongsheng Li, Yuqing Yang, Yongfeng Huang, Lili Qiu
| Challenge: | Long-context language models exhibit position bias, also known as "lost in the middle" research shows that even long-contemporary LLMs fail to utilize all context information effectively . |
| Approach: | They propose a method to mitigate position bias by scaling positional hidden states . they propose to use a channel of hidden states to modify positional Hidden states a LCLM's positional bias . |
| Outcome: | The proposed method can improve performance by 15.2% in a "lost in the middle" benchmark. |
LOFT: Scalable and More Realistic Long-Context Evaluation (2025.findings-naacl)
Copied to clipboard
Jinhyuk Lee, Anthony Chen, Zhuyun Dai, Dheeru Dua, Devendra Singh Sachan, Michael Boratko, Yi Luan, Séb Arnold, Vincent Perot, Siddharth Dalmia, Hexiang Hu, Xudong Lin, Panupong Pasupat, Aida Amini, Jeremy R. Cole, Sebastian Riedel, Iftekhar Naim, Ming-Wei Chang, Kelvin Guu
| Challenge: | Long-context language models (LCLMs) can be used to perform tasks traditionally reliant on external tools like retrieval systems or databases. |
| Approach: | They propose a benchmark to evaluate LCLMs' performance on in-context retrieval and reasoning tasks using a set of tokens. |
| Outcome: | The proposed model outperforms state-of-the-art retrieval and RAG systems on in-context retrieval tasks while still requiring prompting strategies. |
Efficient Long Context Language Model Retrieval with Compression (2025.acl-long)
Copied to clipboard
| Challenge: | Long Context Language Models (LCLMs) are a new paradigm for Information Retrieval . however, processing large number of passages within in-context for retrieval is computationally expensive . a proposed compression approach for LCLM retrieval maximizes retrieval performance while minimizing the length of the compressed passages. |
| Approach: | They propose a new compression approach tailored to maximize retrieval performance while minimizing the length of compressed passages. |
| Outcome: | The proposed approach maximizes retrieval performance while minimizing the length of compressed passages while reducing the in-context size by 1.91. |
Efficient Context Selection for Long-Context QA: No Tuning, No Iteration, Just Adaptive‐k (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing adaptive methods struggle with aggregation QA where optimal external context is unknown and variable. |
| Approach: | They propose a single-pass method that selects a query-specific number of passages . Adaptivek retrieval matches or outperforms fixedk baselines while using 10x fewer tokens compared to full-context input . |
| Outcome: | Adaptivek retrieval matches or outperforms fixedk baselines on factoid and aggregation QA benchmarks . it uses 10x fewer tokens than full-context input and still retrieves 70% of relevant passages compared to previous methods . |
Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Long-context language models have impressive capabilities in long-contrast understanding tasks, but long-text referencing remains underexplored. |
| Approach: | They propose a benchmark to assess long-context referencing capability of LCLMs . they use three subsets to test the model's ability to identify key indexes based on contextual relationships . |
| Outcome: | The proposed benchmark assesses the long-context referencing capability of LCLMs. |
On Many-Shot In-Context Learning for Long-Context Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks primarily evaluate long-context language models' retrieval capabilities. |
| Approach: | They propose a benchmark to evaluate long-context language models' retrieval capabilities by using MANYICLBENCH. |
| Outcome: | The proposed model performs better with additional demonstrations than translation and reasoning tasks. |
Benchmarking Long-Context Language Models on Long Code Understanding (2025.acl-long)
Copied to clipboard
Jia Li, Xuyuan Guo, Lei Li, Kechi Zhang, Ge Li, Jia Li, Zhengwei Tao, Fang Liu, Chongyang Tao, Yuqi Zhu, Zhi Jin
| Challenge: | Currently, long-context language models are limited by the lack of a rigorous evaluation framework for long code understanding. |
| Approach: | They propose to use a long code understanding benchmark LongCodeU to evaluate LCLMs' long code comprehension ability for practical applications. |
| Outcome: | The proposed benchmarks show that current LCLMs are limited in their long code understanding ability, particularly when the long code length is greater than 32K, falling far short of their claimed 128K to 1M context windows. |
Revisiting In-Context Learning with Long Context Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) is a technique by which language models make predictions based on examples provided in their input context. |
| Approach: | They revisited previous studies using in-context learning techniques . they found that using a data augmentation approach, they significantly improved ICL performance . |
| Outcome: | The proposed approach significantly improves ICL performance on 18 datasets spanning 4 tasks . the proposed approach does not improve performance over a simple random sample selection method . |